EIP complexity assessment

EIP-7610: Revert creation in case of non-empty storage

Assessed in Amsterdam / Glamsterdam. The score describes the EIP text available at the assessment cutoff, not the EIP as it stands today.

RetrospectiveAmsterdam / GlamsterdamAssessment cutoff 2025-09-24Included by cutoffLayers: execution

LLM Completescore 9

Human Completescore 7 · Checklist revision 1· merged checklist

LLM · Checklist revision 22026-08-25 · Primary study score · 9 LLM · Checklist revision 12026-08-25 · Re-run for the human comparison · 10 Human · Checklist revision 1Complete · 7 CompareHuman vs LLM · same checklist revision

Evaluated on: 2026-08-25 · Spec revision: 2024-11-07 · fd89c8f734

Scope at the cutoff. At the selected historical revision, EIP-7610 extends the contract-creation collision rule so that creation transactions, CREATE, CREATE2, and any other creation path must fail when the destination has non-empty storage, in addition to the existing nonzero-nonce and nonzero-code conditions. It amends EIP-684 to protect legacy accounts whose zero nonce and zero-length code could coexist with storage before EIP-161, and specifies the same invalid-init-code failure behavior for all creation paths. The EIP expects existing non-empty-storage deployment tests to provide coverage after their expected results are refilled.

9LowLow

Evaluator: LLMChecklist v2
Confidence: High
Under-specified at assessment cutoff: No
Plausible range: 9–9 (Low)
Assessment cutoff: 2025-09-24 · EIP revision fd89c8f734 (2024-11-07)

Score bands · Checklist revision 2

Low <12
Medium 12–22
High ≥23

28 criteria scored 0–3 (4 in exceptional cases; cross-EIP interactions is uncapped); nominal maximum 84.

Complexity profile

Each segment is one criterion's contribution to the LLM total. Hover or focus a segment for its score and rationale.

Under-specified at assessment cutoff: No

The EIP text available at the assessment cutoff left material behavior unresolved. The affected criteria and the plausible total range record that uncertainty.

The assessor found no material behavior left unresolved by the EIP text at the cutoff.

Notable ambiguities noted by the assessor (1)

The EIP does not quantify what share of the existing test corpora is meant by "quite a number," so the boundary between scores one and two for affected pre-existing tests is judgmental.

Criterion breakdown

EIP-7610 Amsterdam / Glamsterdam: LLM criterion scores and rationale
Criterion	Score	Why this score	Evidence / uncertainty
Modified opcodes	3	At least two pre-existing opcodes have a non-gas behavioral result changed; the rubric's binary modified-opcode anchor therefore requires score three.	eip.md · Specification, lines 22-24 CREATE and CREATE2 must now throw when the destination has non-empty storage, extending their pre-existing collision behavior beyond nonzero nonce or code length. supporting/eip-684.md · Specification, lines 17-21 The prior collision rule for CREATE and CREATE2 rejects only a nonzero destination nonce or nonzero code length. Confidence: High
Security risks	2	A mistake could leave a creation path able to violate the intended code- immutability protection. The change is limited to creation collision and destination state but spans several existing entry paths, supporting the targeted-review score-two anchor rather than a fully isolated score one.	eip.md · Security Considerations, lines 42-44 The EIP characterizes the change as a security upgrade that enforces the immutability of deployed code. eip.md · Specification, lines 22-24 The protection must be implemented consistently across creation transactions, CREATE, CREATE2, and other creation paths, and it amends the existing EIP-684 collision rule. Confidence: High
Cross-EIP interactions	2	The proposal directly modifies EIP-684 and must account for the EIP-161 historical boundary. Coordinated testing is therefore required across two identified EIPs, but the interaction is confined to creation collision and legacy account state, matching score two.	eip.md · Specification and Rationale, lines 22-30 EIP-7610 explicitly amends EIP-684 with the storage condition and explains that the relevant legacy state was possible before EIP-161 began incrementing a newly created contract's nonce. supporting/eip-684.md · Specification, lines 17-21 EIP-684 supplies the existing nonce-or-code collision rule that EIP-7610 modifies. supporting/eip-161.md · Specification, lines 18-26 EIP-161 changes creation nonce handling and account-state invariants, defining the historical boundary relevant to the newly covered accounts. Confidence: High Interacting EIPs: EIP-161, EIP-684
Patterns affecting pre-existing tests	1	Existing expected outcomes must be updated, but only for the narrow and contrived category of creation into non-empty storage. This is best matched by the minor-subset score-one anchor.	eip.md · Test Cases, lines 36-40 The EIP identifies existing tests in two test repositories for deployment to non-empty-storage targets and says refilling those tests is sufficient coverage. Confidence: Medium Uncertainty: The EIP calls the affected tests "quite a number" but does not quantify their share of either test corpus.
Edge/boundary conditions	1	The EIP introduces one edge-case-prone mechanism: distinguishing empty from non-empty destination storage when the other collision fields are zero. Multiple entry paths are cases of that single mechanism, matching score one.	eip.md · Rationale, lines 26-30 The motivating boundary case is a legacy destination with zero nonce and zero-length code but non-empty storage, which the two existing EIP-684 conditions do not reject. eip.md · Specification, lines 22-24 The same collision boundary applies to creation transactions, CREATE, CREATE2, and any other creation reason. Confidence: High

Show 23 zero-score criteria

Zero-score criteria (Checklist revision 2)
Criterion	Why this score	Evidence / uncertainty
Added opcodes	No opcode is added.	eip.md · Specification, lines 22-24 CREATE and CREATE2 are named as existing creation paths to which the new condition applies; no new opcode is defined.
Added precompiles	No precompile is added.	eip.md · Specification, lines 18-24 The normative change is confined to contract creation and does not define a precompile.
Modified precompiles	No pre-existing precompile is modified.	eip.md · Specification, lines 18-24 The proposal changes creation collision handling and identifies no precompile logic or gas schedule.
Added system contracts	No system contract is added.	eip.md · Specification, lines 18-24 The proposal adds a general contract-creation rejection condition and does not introduce a contract or reserved address.
Modified system contracts	No direct or package-identified indirect system-contract modification is introduced, so the zero anchor applies.	eip.md · Specification, lines 18-24 The rule applies generically to creation attempts and identifies no pre-existing system contract code, state, or behavior to modify.
EVM Gas rule changes	The proposal changes the result of a creation collision, not EVM gas accounting, so it matches the zero anchor.	eip.md · Specification, lines 18-24 The specification adds non-empty storage to the conditions that make a creation throw, without changing any gas price, charge, or accounting mechanism.
State-access ordering within opcode execution	The added condition changes the collision result but does not specify a new ordering point or move an existing state access inside an opcode, matching the zero anchor.	eip.md · Specification, lines 22-24 Non-empty storage is added to the existing destination-collision predicate inherited from EIP-684; the text does not move that predicate within CREATE or CREATE2 or change gas charging relative to it. supporting/eip-684.md · Specification, lines 17-21 EIP-684 already performs a destination-account collision check for nonce and code across creation transactions, CREATE, CREATE2, and other paths. Uncertainty: The proposal does not discuss whether an implementation treats determining storage emptiness as a separate observable access, but it places the condition in the already existing collision check.
Blob gas accounting changes	No blob gas accounting mechanism is introduced or modified.	eip.md · Specification, lines 18-24 The entire normative change concerns contract-creation collision state and contains no blob gas rule.
State gas accounting changes	A state-dependent validity condition is not a state gas accounting change, so the zero anchor applies.	eip.md · Specification, lines 18-24 The specification reads whether destination storage is empty to decide a collision but defines no charge for writing state, state-gas rate, budget, reservoir, or spill rule.
New EVM gas refund	No new gas-refund mechanism is introduced.	eip.md · Specification, lines 18-24 The collision rule only requires creation to throw under an added state condition and introduces no refund behavior.
New transaction types	No new transaction type is introduced.	eip.md · Specification, lines 22-24 Existing contract-creation transactions are one path governed by the new collision condition; no transaction type is defined.
New or modified transaction validity mechanisms	The change is to execution outcome after a creation is attempted, not to transaction validity or intrinsic-gas calculation, so the zero anchor applies.	eip.md · Specification, lines 22-24 A creation transaction whose destination collides must execute as a throwing creation; the text does not make the transaction itself invalid or alter intrinsic gas.
New block / header fields	No block or block-header field is added.	eip.md · Specification, lines 18-24 The rule relies on existing destination account state and introduces no block or header field.
Encoding changes (RLP/SSZ)	No RLP, SSZ, or other covered encoding change is introduced.	eip.md · Specification, lines 18-24 The proposal defines an execution-state collision predicate without changing transaction, block, or interface encoding.
Block syncing changes	No block RLP validation mechanism is introduced.	eip.md · Specification, lines 18-24 The proposal changes execution behavior for contract creation and defines no block RLP field or validation rule.
New fork activation mechanism	Activating an execution rule in a hard fork is not itself the special activation-block modification covered by this anchor, so the score is zero.	eip.md · Backwards Compatibility, lines 32-34 The EIP says the execution-layer change requires a hard fork but specifies no activation-block state transition or mutation of an internal variable.
Engine API changes	The Engine API is unchanged, matching the zero anchor.	eip.md · Specification, lines 18-24 The creation-collision predicate uses execution-state information and adds no Engine API field, endpoint, or communication mechanism.
Transition-tool interface changes	No transition-tool interface modification is required by the proposal, so the zero anchor applies.	eip.md · Specification, lines 18-24 The rule is expressed entirely in terms of existing creation context and destination account state, with no new input or output field.
New invariant on pre-existing tests	The affected tests change their expected result; pre-existing unrelated tests gain no additional invariant to assert, matching the zero anchor.	eip.md · Test Cases, lines 36-40 Coverage is described as refilling tests that already target the precise non-empty-storage creation scenario, not adding a new assertion to tests about unrelated behavior.
New test-framework primitives	Reusing and refilling existing tests indicates that existing framework primitives suffice, matching the zero anchor.	eip.md · Test Cases, lines 36-40 The EIP states that refilling existing tests will provide sufficient coverage.
Performance risks	The historical text presents no mechanism whose test complexity requires performance benchmarking, so the zero anchor is the best-supported score.	eip.md · Specification, lines 22-24 The only added work described is evaluating one more destination-account condition in the existing creation-collision rule. eip.md · Test Cases, lines 36-40 The testing plan calls only for refilling existing functional tests and identifies no performance-validation requirement. Uncertainty: The EIP does not discuss the runtime cost of determining storage emptiness; no package evidence establishes a material performance risk.
Cryptography	No cryptography mechanism is introduced or changed.	eip.md · Specification, lines 18-24 The specified mechanism is a destination-account state predicate and contains no cryptographic construction or modification.
Unspecified behavior requiring cross-client consensus	For constructible empty-versus-non-empty-storage collision cases, the proposal supplies a single result and inherited failure semantics. The reported prior disagreement is the behavior the rule resolves, not an open choice left for cross-client agreement.	eip.md · Specification, lines 22-24 The text enumerates the creation paths and collision conditions and specifies that a collision throws as though the first init-code byte were invalid. eip.md · Test Cases, lines 36-40 Although clients previously handled the scenario differently, the EIP states that refilling the existing tests is sufficient under the new rejection rule. Uncertainty: "Non-empty storage" is not separately formalized in the EIP, but its intended state predicate is sufficiently direct that no alternative outcome is supported by the package.

Assessment provenance

Assessed EIP revision: ethereum/EIPs@fd89c8f734 EIPS/eip-7610.md committed 2024-11-07 · information cutoff 2025-09-24T14:40:52Z
Current master · File history · blob 6e7d1900da · sha256 32737f15ce36
Rubric: Checklist revision 2 · ethspecs/pm@3d8c0128c5
Evaluator: gpt-5.6-sol at xhigh reasoning effort · isolation bubblewrap_one_eip_capsule_v1
Source record: Frozen research record research/tasks/05-retrospective-complexity-assignment/outputs/fork-eips/amsterdam/eip-7610.yaml · sha256 01edd717bb9c
Supporting documents in the sealed package: supporting/eip-161.md, supporting/eip-684.md

Evaluated on: 2026-08-25 · Spec revision: 2024-11-07 · fd89c8f734

Scope at the cutoff. At the sealed historical revision, EIP-7610 adds non-empty storage to EIP-684's contract-creation collision predicate for creation transactions, CREATE, CREATE2, and any other creation cause. A collision must throw as though init code began with an invalid opcode; the rule is stated to apply retroactively and to require a hard fork.

10MediumMedium

Evaluator: LLMChecklist v1
Confidence: Medium
Under-specified at assessment cutoff: Yes — 4 criteria affected
Plausible range: 8–12 (Low–Medium)
Assessment cutoff: 2025-09-24 · EIP revision fd89c8f734 (2024-11-07)

Score bands · Checklist revision 1

Low <10
Medium 10–19
High ≥20

24 criteria scored 0–3 (4 in exceptional cases; cross-EIP interactions is uncapped); nominal maximum 72.

Complexity profile

Each segment is one criterion's contribution to the LLM total. Hover or focus a segment for its score and rationale.

Top complexity drivers

Modified opcodes3
Patterns affecting pre-existing tests2
Security risks2
Cross-EIP interactions2

Under-specified at assessment cutoff: Yes

The EIP text available at the assessment cutoff left material behavior unresolved. The affected criteria and the plausible total range record that uncertainty.

Why: The proposal defines the collision predicate and failure result but does not quantify the affected test inventory, enumerate creation causes covered by 'any other reason,' detail storage-emptiness and reversion handling, or explain performance and security validation. These omissions are kept localized to test breadth, edge cases, performance, and security.

Plausible total

8–12
recorded score 10 · plausible tiers Low, Medium

Affected criteria (4)

Patterns affecting pre-existing tests (2)
Security risks (2)
Performance risks (0)
Edge/boundary conditions (1)

Unresolved questions at the cutoff (4)

How many existing tests, forks, and execution paths need changed expectations rather than simple refilling?
Which creation causes are included by 'any other reason,' and what boundary cases are required for nested creation and state reversion?
How is non-empty storage determined in each relevant state context, and does that check require isolated performance validation?
What targeted security and consensus-divergence review is required for retroactive application?

Notable ambiguities noted by the assessor (4)

The historical checklist includes Engine API encoding changes but supplies no dedicated definition.
The requirement to apply the change retroactively to all existing blocks is not reconciled with the statement that activation requires a hard fork.
The phrase 'or any other reason' leaves additional contract-creation causes open-ended.
The phrase 'quite a number of tests' does not quantify the affected subset or its fork and client breadth.

Criterion breakdown

EIP-7610 Amsterdam / Glamsterdam: LLM criterion scores and rationale
Criterion	Score	Why this score	Evidence / uncertainty
Modified opcodes	3	The binary rubric anchor assigns 3 when any pre-existing opcode behavior changes; both CREATE and CREATE2 gain an additional failure case.	eip.md · Specification, second paragraph Requires attempts caused by CREATE or CREATE2 to throw when the destination has non-empty storage, adding a new non-gas failure condition. Confidence: High Uncertainty: The rule also covers creation transactions and other causes, but that broader scope does not change the direct opcode modification.
Patterns affecting pre-existing testsUnder-specified	2	A considerable existing-test subset is described as affected, but it is confined to the contrived category of deployment against destinations with non-empty storage.	eip.md · Test Cases States that quite a number of existing Ethereum tests and execution-spec tests cover deployment to targets with non-empty storage and that refilling those tests provides coverage. Confidence: Medium Uncertainty: The package gives no test count, fork matrix, or inventory, so the affected subset could prove minor rather than considerable.
Security risksUnder-specified	2	The mechanism touches a limited set of critical components—contract creation, collision checks, and destination storage—and changes a code-immutability security assumption, warranting targeted review and fuzzing.	eip.md · Security Considerations Calls the proposal a security upgrade that enforces immutability of deployed code. eip.md · Specification and Rationale Changes creation collision handling for all creation paths to protect addresses having zero nonce and code length but non-empty storage. Confidence: Medium Uncertainty: The package does not specify review or fuzzing breadth, so a self-contained score of 1 remains plausible; it does not support the multi-component breadth required for 3.
Cross-EIP interactions	2	The proposal directly modifies EIP-684 and relies on EIP-161-era account semantics, requiring coordinated consideration while keeping the interaction narrowly scoped to contract creation.	eip.md · Specification and Rationale Explicitly amends EIP-684 with an empty-storage condition and explains the historical account state in relation to EIP-161. supporting/eip-684.md · Specification Defines the existing creation-collision rule using nonzero nonce or nonzero code length, which EIP-7610 extends. supporting/eip-161.md · Specification item a and Rationale Requires newly created accounts to increment nonce before initialization and explains avoiding zero nonce for created accounts. Confidence: High Uncertainty: The dependency is explicit, but the package does not enumerate the exact coordinated cross-EIP test matrix.
Edge/boundary conditionsUnder-specified	1	The storage-emptiness decision is one edge-condition-prone mechanism; the several creation entry paths are applications of that same predicate.	eip.md · Specification, second paragraph Introduces one new collision boundary—empty versus non-empty destination storage—and applies it to creation transactions, CREATE, CREATE2, and any other creation cause. Confidence: Medium Uncertainty: The open-ended phrase 'any other reason' and retroactive application may add cases, but the package does not enumerate them or define a larger boundary matrix.

Show 19 zero-score criteria

Zero-score criteria (Checklist revision 1)
Criterion	Why this score	Evidence / uncertainty
Added opcodes	No opcode is added.	eip.md · Specification, second paragraph References the existing CREATE and CREATE2 opcodes as entry paths and introduces no new opcode. Uncertainty: None material; all named opcodes are pre-existing mechanisms being covered by the rule.
Added precompiles	No precompile is introduced.	eip.md · Abstract and Specification The proposal adds a creation-collision condition and specifies no precompile address, interface, or logic. Uncertainty: None material; precompiles are absent from the proposal.
Modified precompiles	No pre-existing precompile logic or gas schedule is modified.	eip.md · Specification No precompile behavior or gas accounting is part of the contract-creation collision rule. Uncertainty: None material; the package identifies no precompile interaction.
Added system contracts	No new system contract is introduced.	eip.md · Abstract and Specification Adds a general contract-creation rejection condition and does not deploy or designate any system contract. Uncertainty: None material; no contract address, code, state, or system action is specified.
Modified system contracts	The proposal does not directly or indirectly identify a modification to a pre-existing system contract.	eip.md · Specification Applies a general creation-collision rule without naming or changing the code or state of any pre-existing system contract. Uncertainty: The package does not inventory system-contract creation behavior, but it identifies no system contract affected by the change.
EVM Gas rule changes	The proposal changes a contract-creation failure condition, not an EVM gas-accounting mechanism, so the no-change anchor applies.	eip.md · Specification, second paragraph Adds non-empty storage to the destination-address collision predicate and requires creation to throw; it specifies no gas schedule or accounting rule. Uncertainty: The invalid-opcode-equivalent failure changes which attempts consume failure-path gas, but the package defines no gas-accounting rule or schedule change.
Blob gas accounting changes	No blob gas mechanism is introduced or modified.	eip.md · Abstract and Specification The proposal is limited to rejecting contract creation at an address with non-empty storage; no blob behavior or blob accounting is specified. Uncertainty: None material within the package; the normative scope is execution-layer contract creation.
New EVM gas refund	The proposal introduces no EVM gas-refund mechanism.	eip.md · Specification The only prescribed outcome is a creation throw on a destination collision involving nonce, code, or storage; no refund is prescribed. Uncertainty: The package does not discuss refunds, but nothing in the specified rule creates or modifies one.
New transaction types	No new transaction type is introduced.	eip.md · Specification, second paragraph Applies to an existing creation transaction and opcode-based creation paths; it defines no new transaction envelope or type. Uncertainty: None material; creation transactions are an existing path within the proposal's stated scope.
New or modified transaction validity mechanisms	The change affects execution outcome for contract creation, not transaction validity rules or intrinsic gas calculation.	eip.md · Specification, second paragraph A creation transaction encountering the new collision condition throws as if init code began with an invalid opcode; the transaction itself is not declared invalid and intrinsic gas is unchanged. Uncertainty: There is a rubric-boundary ambiguity between transaction execution failure and transaction invalidity, but the specification consistently describes a throw rather than invalidation.
New block / header fields	No block or header field is introduced.	eip.md · Specification Defines a contract-creation state check and adds no block or block-header field. Uncertainty: None material; block structure is outside the specified change.
Encoding changes (RLP/SSZ)	No encoding change is introduced at transaction, block, or interface level.	eip.md · Specification Changes an execution validity outcome without adding or changing transaction, block, interface, RLP, or SSZ encoding. Uncertainty: None material; the proposal defines no serialized field or format.
Block syncing changes	No block RLP validation mechanism requiring sync testing is introduced.	eip.md · Specification Changes execution-time contract-creation collision handling and defines no block RLP field or RLP validation mechanism. Uncertainty: Retroactive application may motivate historical execution tests, but the rubric row is specifically about block RLP validation, which is unchanged in the package.
New fork activation mechanism	A fork is required, but the rubric scores activation-block state or internal-variable modifications, none of which are specified.	eip.md · Specification and Backwards Compatibility States that the rule applies retroactively and requires a hard fork, but specifies no state or internal-variable modification at the activation block. Uncertainty: The relationship between retroactive application and hard-fork activation is not explained, though no activation-block state transition is stated.
Engine API changes	No Engine API fields or endpoints are introduced.	eip.md · Specification The normative rule uses existing account state and creation execution; it adds no Engine API endpoint, field, or communication mechanism. Uncertainty: The Engine API is not discussed explicitly, but no new information exchange is specified.
Engine API encoding changes	Scored conservatively from the row label: the proposal describes no Engine API encoding change.	eip.md · Specification Specifies only a contract-creation state predicate and throw behavior, with no Engine API encoding change. rubric.md · Checklist row 'Engine API encoding changes' The checklist contains this row but provides no dedicated scoring definition. Uncertainty: The historical checklist has no dedicated definition for this row, so the exact intended scoring boundary is unavailable.
Transition-tool interface changes	No transition-tool interface field or communication mechanism is introduced.	eip.md · Specification Defines an internal contract-creation collision check and failure outcome without adding any transition-tool input or output field. Uncertainty: The transition tool is not discussed explicitly, so implementation implications are not enumerated, but the proposal requests no interface data.
Performance risksUnder-specified	On the sealed evidence, no mechanism is identified as requiring performance validation, so the zero anchor is applied.	eip.md · Specification Adds a destination-storage-emptiness predicate to contract creation but gives no performance requirement, benchmark concern, or broader performance mechanism. Uncertainty: The package omits how storage emptiness is determined and its cost; an isolated performance check could justify score 1 if that detail were material.
Cryptography	No cryptography mechanism is introduced or modified.	eip.md · Abstract and Specification The change is a state predicate over destination nonce, code length, and storage emptiness; it introduces no cryptographic primitive or operation. Uncertainty: None material; cryptography is outside the stated mechanism.

Assessment provenance

Assessed EIP revision: ethereum/EIPs@fd89c8f734 EIPS/eip-7610.md committed 2024-11-07 · information cutoff 2025-09-24T14:40:52Z
Current master · File history · blob 6e7d1900da · sha256 32737f15ce36
Rubric: Checklist revision 1 · ethspecs/pm@d936bcb349
Evaluator: gpt-5.6-sol at xhigh reasoning effort · isolation bubblewrap_one_eip_capsule_v1
Source record: Frozen research record research/tasks/05c-amsterdam-human-assessment-alignment/outputs/automated/eip-7610.yaml · sha256 d377fa85b325
Supporting documents in the sealed package: supporting/eip-161.md, supporting/eip-684.md

Evaluated on: Not recorded · Spec revision: 2025-11-06 · 7707fe3333

7LowLow

Evaluator: HumanChecklist v1
Confidence: Not recorded
Under-specified at assessment cutoff: Not recorded in the checklist
Checklist published: 2026-01-09 · EIP at 7707fe3333
Source: merged ethspecs/pm checklist

Score bands · Checklist revision 1

Low <10
Medium 10–19
High ≥20

24 criteria scored 0–3 (4 in exceptional cases; cross-EIP interactions is uncapped); nominal maximum 72.

Complexity profile

Each segment is one criterion's contribution to the Human total. Hover or focus a segment for its score and rationale.

Top complexity drivers

Patterns affecting pre-existing tests3
New or modified transaction validity mechanisms2
Transition-tool interface changes2

Criterion breakdown

EIP-7610 Amsterdam / Glamsterdam: Human criterion scores and rationale
Criterion	Score	Why this score	Notes
Patterns affecting pre-existing tests	3	Some static tests might break as noted by Pawel in the magicians thread.	—
New or modified transaction validity mechanisms	2	The EIP is an even stricter version of `684`, adding the rule that the storage also has to be empty.	—
Transition-tool interface changes	2	EELS might be updated to handle this EIP.	—

Show 21 zero-score criteria

Zero-score criteria (Checklist revision 1)
Criterion	Why this score	Notes
Added opcodes	No rationale recorded.	—
Modified opcodes	No rationale recorded.	—
Added precompiles	No rationale recorded.	—
Modified precompiles	No rationale recorded.	—
Added system contracts	No rationale recorded.	—
Modified system contracts	No rationale recorded.	—
EVM Gas rule changes	No rationale recorded.	—
Blob gas accounting changes	No rationale recorded.	—
New EVM gas refund	No rationale recorded.	—
New transaction types	No rationale recorded.	—
New block / header fields	No rationale recorded.	—
Encoding changes (RLP/SSZ)	No rationale recorded.	—
Block syncing changes	No rationale recorded.	—
New fork activation mechanism	No rationale recorded.	—
Engine API changes	No rationale recorded.	—
Engine API encoding changes	No rationale recorded.	—
Security risks	The EIP helps improve security.	—
Performance risks	No rationale recorded.	—
Edge/boundary conditions	No rationale recorded.	—
Cryptography	No rationale recorded.	—
Cross-EIP interactions	No rationale recorded.	—

Assessment provenance

Assessed EIP revision: ethereum/EIPs@7707fe3333 EIPS/eip-7610.md committed 2025-11-06
EIP master revision at the time of the human checklist commit; the checklist itself does not pin an EIP revision.
Current master · File history · blob 5e96d30303 · sha256 e934db8fded8
Rubric: Checklist revision 1 · ethspecs/pm@d936bcb349
Evaluator: STEEL team · ethspecs/pm complexity_assessments
Source record: Merged checklist ethspecs/pm@0a80baf174 complexity_assessments/EIPs/EIP-7610.md · committed 2026-01-09
blob d9250b95ed · sha256 ebca2ea04f8f
Research record: research/tasks/05c-amsterdam-human-assessment-alignment/inputs/human/eip-7610.yaml · sha256 2bd91d1cf2c5

Both assessments applied Checklist revision 1 (24 criteria) to EIP-7610 in Amsterdam / Glamsterdam. Δ is LLM minus Human.

LLM10Medium

Human7Low

Δ total+3Tiers differ: Medium vs Low

Criteria17/24agree exactly · 2 differ by 1 · 5 differ by 2+

Confounded comparison. The human checklist evaluated the EIP as it stood when the checklist was written; the LLM evaluated the sealed historical revision. Input alignment: substantive drift; human hindsight exposure: possible exposure. The study's primary LLM score under checklist revision 2 is 9; it uses a different criterion inventory and thresholds and is not directly comparable to either total here.

Exposure evidence

The assessment cites a Magicians observation and possible EELS work, but describes the implementation as prospective.

Substantive intervening revisions: Adds an explicit EIP-7702 non-interference statement to the Specification (PR #10734): 'This EIP will not affect EIP-7702, since the authority's nonce is always incremented after an authorization is applied, which conflicts with the condition required for contract deployment.' Simultaneously deletes the Rationale sentence 'As one of the core tenets of smart contracts is that its code will not change...'.

Complexity profiles side by side

LLM

Human

Largest disagreements: Modified opcodes (+3), Transition-tool interface changes (−2), New or modified transaction validity mechanisms (−2), Security risks (+2), Cross-EIP interactions (+2)

Show differences only (7 criteria)

Per-criterion scores, Human versus LLM, ordered by the size of the difference
Criterion	LLM	Human	Δ	Agreement	Rationale from each source
Modified opcodes	3	0	+3	Differ by 2+	Show rationale LLM The binary rubric anchor assigns 3 when any pre-existing opcode behavior changes; both CREATE and CREATE2 gain an additional failure case. Human No rationale recorded.
New or modified transaction validity mechanisms	0	2	−2	Differ by 2+	Show rationale LLM The change affects execution outcome for contract creation, not transaction validity rules or intrinsic gas calculation. Human The EIP is an even stricter version of `684`, adding the rule that the storage also has to be empty.
Transition-tool interface changes	0	2	−2	Differ by 2+	Show rationale LLM No transition-tool interface field or communication mechanism is introduced. Human EELS might be updated to handle this EIP.
Security risks	2	0	+2	Differ by 2+	Show rationale LLM The mechanism touches a limited set of critical components—contract creation, collision checks, and destination storage—and changes a code-immutability security assumption, warranting targeted review and fuzzing. Human The EIP helps improve security.
Cross-EIP interactions	2	0	+2	Differ by 2+	Show rationale LLM The proposal directly modifies EIP-684 and relies on EIP-161-era account semantics, requiring coordinated consideration while keeping the interaction narrowly scoped to contract creation. Human No rationale recorded.
Patterns affecting pre-existing tests	2	3	−1	Differ by 1	Show rationale LLM A considerable existing-test subset is described as affected, but it is confined to the contrived category of deployment against destinations with non-empty storage. Human Some static tests might break as noted by Pawel in the magicians thread.
Edge/boundary conditions	1	0	+1	Differ by 1	Show rationale LLM The storage-emptiness decision is one edge-condition-prone mechanism; the several creation entry paths are applications of that same predicate. Human No rationale recorded.
Added opcodes	0	0	0	Agree	Show rationale LLM No opcode is added. Human No rationale recorded.
Added precompiles	0	0	0	Agree	Show rationale LLM No precompile is introduced. Human No rationale recorded.
Modified precompiles	0	0	0	Agree	Show rationale LLM No pre-existing precompile logic or gas schedule is modified. Human No rationale recorded.
Added system contracts	0	0	0	Agree	Show rationale LLM No new system contract is introduced. Human No rationale recorded.
Modified system contracts	0	0	0	Agree	Show rationale LLM The proposal does not directly or indirectly identify a modification to a pre-existing system contract. Human No rationale recorded.
EVM Gas rule changes	0	0	0	Agree	Show rationale LLM The proposal changes a contract-creation failure condition, not an EVM gas-accounting mechanism, so the no-change anchor applies. Human No rationale recorded.
Blob gas accounting changes	0	0	0	Agree	Show rationale LLM No blob gas mechanism is introduced or modified. Human No rationale recorded.
New EVM gas refund	0	0	0	Agree	Show rationale LLM The proposal introduces no EVM gas-refund mechanism. Human No rationale recorded.
New transaction types	0	0	0	Agree	Show rationale LLM No new transaction type is introduced. Human No rationale recorded.
New block / header fields	0	0	0	Agree	Show rationale LLM No block or header field is introduced. Human No rationale recorded.
Encoding changes (RLP/SSZ)	0	0	0	Agree	Show rationale LLM No encoding change is introduced at transaction, block, or interface level. Human No rationale recorded.
Block syncing changes	0	0	0	Agree	Show rationale LLM No block RLP validation mechanism requiring sync testing is introduced. Human No rationale recorded.
New fork activation mechanism	0	0	0	Agree	Show rationale LLM A fork is required, but the rubric scores activation-block state or internal-variable modifications, none of which are specified. Human No rationale recorded.
Engine API changes	0	0	0	Agree	Show rationale LLM No Engine API fields or endpoints are introduced. Human No rationale recorded.
Engine API encoding changes	0	0	0	Agree	Show rationale LLM Scored conservatively from the row label: the proposal describes no Engine API encoding change. Human No rationale recorded.
Performance risks	0	0	0	Agree	Show rationale LLM On the sealed evidence, no mechanism is identified as requiring performance validation, so the zero anchor is applied. Human No rationale recorded.
Cryptography	0	0	0	Agree	Show rationale LLM No cryptography mechanism is introduced or modified. Human No rationale recorded.

Compare EIP-7610 with other assessments All Amsterdam / Glamsterdam assessments

Criterion legend and glossary

Every stacked bar, comparison matrix, and criterion table on this site uses the same criterion colours, abbreviations, and order. Colour marks the criterion group; the abbreviation and name identify the criterion. Scores are 0–3 per criterion (4 is exceptional; cross-EIP interactions is uncapped).

EVM surface

Opcodes, precompiles, and system contracts that are added or modified.

OP+
Added opcodes
Introduces new opcodes
Score anchors
0
No new opcodes are introduced.
1
A new simple opcode is introduced (no data portion, no complex stack mechanics, and a constant gas cost).
2
Multiple new simple opcodes are introduced, or a single new complex opcode is introduced (has data portion, or complex stack mechanics, or a dynamic gas cost).
3
Multiple new opcodes are introduced, and at least one of them is complex (has data portion, or complex stack mechanics, or a dynamic gas cost).
- Cryptography opcodes are not considered complex by default. Refer to the "Cryptography" section for a separate assessment.
Modified opcodes
Modifies pre-existing opcodes
Score anchors
0
No pre-existing opcode modifications are introduced.
3
At least one pre-existing opcode's behavior is modified (not including gas changes) or a pre-existing opcode is deprecated.
PC+
Added precompiles
Introduces new precompiles
Score anchors
0
No new precompiles are introduced.
1
A new simple precompile is introduced (constant input length, constant gas cost).
2
Multiple new simple precompiles are introduced, or a single new complex precompile is introduced (dynamic input length or dynamic gas cost).
3
Multiple new precompiles are introduced, and at least one of them is complex (dynamic input length or dynamic gas cost).
- Cryptography precompiles are not considered complex by default. Refer to the "Cryptography" for a separate assessment.
Modified precompiles
Modifies pre-existing precompiles logic or gas-accounting
Score anchors
0
No pre-existing precompiles are modified.
1
At least one pre-existing precompile has its gas schedule modified.
2
Multiple pre-existing precompiles have their gas schedule modified, or a single pre-existing precompile has its behavior modified.
3
The behavior of multiple pre-existing precompiles, or a single complex pre-existing precompile modified.
Added system contracts
Introduces new system contract, stateful or not
Score anchors
0
No new system contracts are introduced.
1
A new system contract is introduced that is not stateful nor does it trigger a new system action (e.g. requests to the consensus layer).
2
Multiple new system contracts are introduced or a single new system contract that is either stateful or triggers a new system action (e.g. requests to the consensus layer).
3
Multiple new system contracts are introduced and at least one of them is either stateful or triggers a new system action (e.g. requests to the consensus layer).
Modified system contracts
Modifies pre-existing system contracts
Score anchors
0
No modifications to pre-existing system contracts are introduced, directly or indirectly.
1
Does not directly modify any system contract, but its behavior has minor indirect effects on one or more system contracts.
2
Does not directly modify any system contract, but its behavior has major indirect effects on one or more system contracts.
3
At least one pre-existing system contract code or state is modified, which would involve irregular state transition or a similarly complex transition methodology.

Gas and accounting

Execution, blob, and state gas rules, refunds, and where charges happen inside opcodes.

EVM Gas rule changes
New EVM gas accounting rules
Score anchors
0
No gas accounting changes.
1
Existing gas accounting mechanism is updated.
2
A new gas accounting mechanism is introduced but it does not affect existing mechanisms nor does it affect existing tests.
3
A new gas accounting mechanism is introduced and affects existing mechanisms which in turn affect existing tests.
ORD
State-access ordering within opcode execution · Checklist revision 2 only
Changes *where inside an opcode's execution* state is accessed, or where gas is charged relative to that access. Because a state access is recorded in the block-level access list only if execution had enough gas to reach it, this ordering is consensus-critical: moving it changes the BAL at every gas boundary of every affected opcode.
Score anchors
0
No change to where state is accessed, or to where gas is charged relative to a state access, within any opcode.
1
A single opcode's state-access or gas-charge ordering changes.
2
Multiple opcodes' ordering changes, or a new state-accessing operation is introduced whose position in the order must be settled.
3
The ordering rule changes for a whole class of state-accessing opcodes at once, or what counts as a recordable state access is redefined — requiring existing BAL vectors to be re-derived across opcodes and forks.
- Distinct from "Modified opcodes", which asks whether an opcode's **result** changed. This row asks about the **path to the result**, which is observable even when the result is identical. An EIP can be 0 on that row and 3 on this one.
- Score changes **to** the ordering. Do not score the fact that state accesses are observable — they always are.
- Each boundary must be re-tested against every other dimension that can change the answer (cold/warm, static/non-static, delegated/direct, revert/success), so the case count grows multiplicatively rather than additively. Note this explicitly under Special Considerations.
Blob gas accounting changes
New Blob gas accounting rules which potentially affect pre-existing tests
Score anchors
0
No blob gas accounting changes.
1
Existing blob gas accounting mechanism is updated.
2
A new blob gas accounting mechanism is introduced but it does not affect existing mechanisms nor does it affect existing tests.
3
A new blob gas accounting mechanism is introduced and affects existing mechanisms which in turn affect existing tests.
SGAS
State gas accounting changes · Checklist revision 2 only
New state gas accounting rules. State gas is the cost of *writing* state, as opposed to accessing or executing it: `StateGasCosts`, `COST_PER_STATE_BYTE`, the block-level state gas budget, and the spill path into execution gas.
Score anchors
0
No state gas accounting changes.
1
An existing state gas cost or `STATE_BYTES_PER_*` rate is adjusted.
2
A new state-gas-charging site is introduced, or the block-level state gas budget or reservoir allocation is modified.
3
A new state gas charging mechanism is introduced, or the spill interaction between state gas and execution gas is modified, affecting existing gas tests.
- Harder to test than blob gas: the spill path means state gas cannot be metered independently of execution gas, and some costs (e.g. `NEW_ACCOUNT`) are state-dependent.
New EVM gas refund
New gas-refund mechanism
Score anchors
0
No new gas-refund mechanisms are introduced.
1
A new simple gas-refund mechanism is introduced that does not affect either existing tests or existing gas-refund mechanisms.
2
A new complex gas-refund mechanism is introduced or a simple mechanism that affects existing tests or existing gas-refund mechanisms.
3
A new complex gas-refund mechanism is introduced that affects existing tests or existing gas-refund mechanisms.

Blocks, transactions, and encoding

Transaction types and validity, block and header fields, encodings, syncing, and activation-time changes.

New transaction types
Introduces a new transaction type
Score anchors
0
No new transaction types are introduced.
3
A new transaction type is introduced.
New or modified transaction validity mechanisms
Creates new or modifies pre-existing transaction types' validation mechanisms
Score anchors
0
No changes are introduced to the validity rules of existing transaction types or to their intrinsic gas cost calculation.
1
Minor adjustments are introduced to validity rules or intrinsic gas cost calculation, but they do not significantly affect existing tests.
2
Changes to validity rules or intrinsic gas cost calculation affect existing tests, but require only limited updates to test cases and no redesign of the testing infrastructure.
3
Changes to validity rules or intrinsic gas cost calculation require extensive rework or redesign of the tests or testing infrastructure.
New block / header fields
Introduces new block or block header fields
Score anchors
0
No new block or header fields are introduced.
3
A new block or header field is introduced.
ENC
Encoding changes (RLP/SSZ)
Introduces encoding changes at the transaction/block/interfaces level
Score anchors
0
No encoding changes are introduced at the transaction, block, or interfaces levels.
3
An encoding change is introduced at transaction, block or interfaces level (e.g. RLP -> SSZ).
- "Interfaces level" includes the Engine API. Score an Engine API encoding change (e.g. JSON -> SSZ) here.
Block syncing changes
Modifies block RLP validation mechanisms that require test client syncing.
Score anchors
0
No new RLP validation mechanism is introduced.
1
A single simple RLP validation mechanism is introduced.
2
Multiple simple RLP validation mechanisms are introduced or a single complex one.
3
Multiple RLP validation mechanisms are introduced and at least one of them is deemed complex.
ACT
New fork activation mechanism
Modifies state, internal variables, or similar, at the fork activation block
Score anchors
0
No state modifications, internal variables or similar are modified at the fork activation block.
3
Either a state modification or internal variables are modified at the fork activation block.
- Initialization of new internal variable is not considered a modification.

Client interfaces

Engine API and transition-tool interface changes.

Engine API changes
Introduces new fields to the Engine API directives
Score anchors
0
No new fields or communication mechanisms are introduced to the Engine API.
1
A single new field is introduced in one of the Engine API endpoints.
2
Multiple fields are introduced to one or multiple Engine API end points, or a new Engine API end-point is introduced.
3
Multiple fields are introduced to one or multiple Engine API end points and a new Engine API end-point is introduced.
Engine API encoding changes · Checklist revision 1 only
Engine API encoding changes (the revision-1 template defines no anchor text for this row).
T8N
Transition-tool interface changes
Modifies or adds new fields to the transition tool interface.
Score anchors
0
No modifications to the transition tool interface are required.
1
A single new field needs to be introduced to the transition tool interface.
2
Multiple new fields or a new mechanism has to be introduced to the transition tool interface.
3
Multiple new fields and a new mechanism has to be introduced to the transition tool interface.
- Special consideration must be paid to this section if the EIP introduces a mechanism that requires the state transition tool to be aware whether the block it is processing is the fork-activation block.

Testing impact

Rework, new invariants, and new primitives required in the test framework.

Patterns affecting pre-existing tests
Implements a new validation mechanism or rule that translates in reworking pre-existing tests
Score anchors
0
No pre-existing tests are affected by this change.
1
Minor subset of existing tests are affected by this change.
2
Considerable subset of existing tests are affected by this change but involves only a contrived category of tests.
3
Major subset of existing tests are affected, including diverse category of tests (benchmarks, static, multiple forks, etc.).
INV
New invariant on pre-existing tests · Checklist revision 2 only
Tests that are **not about this EIP** must nonetheless assert something this EIP produces. Their logic does not change; they gain a new thing to check.
Score anchors
0
Pre-existing tests assert nothing new.
1
A narrow, contrived category of pre-existing tests gains a new assertion.
2
A broad category gains a new assertion, applied mechanically.
3
Every test in the fork gains the assertion regardless of what it tests, and pre-fork vectors must be re-derived to satisfy it.
- Paired with the row above, and easy to confuse with it. "Patterns affecting pre-existing tests" asks whether existing tests must be **reworked**; this row asks whether they must **additionally assert something new**. Score both — an EIP can be low on one and high on the other.
New test-framework primitives · Checklist revision 2 only
Requires new abstractions in the test framework itself — expectation types, modifiers, helpers — beyond writing test functions with what already exists.
Score anchors
0
Existing test primitives suffice.
1
Existing primitives need minor extension.
2
New expectation or modifier primitives are required, reusable within this EIP's own test suite.
3
New framework-level primitives are required that become a permanent part of the framework and are used by other EIPs' tests.

Risk and validation

Security, performance, boundary conditions, and cryptography that need validation.

Security risks
Introduces or modifies mechanisms that could compromise the security of the chain, users, validators, or other stakeholders, if not implemented properly.
Score anchors
0
No new mechanisms are introduced that could pose a security risk.
1
The introduced mechanisms are self-contained, can be validated in isolation, and do not alter existing invariants that could pose a security risk for any stakeholders.
2
The introduced mechanisms interact with a limited number of existing components, slightly altering their security assumptions and requiring a targeted security review or fuzzing.
3
The introduced mechanisms interact with multiple existing components, including critical ones, substantially altering their security assumptions and requiring an extensive security review and fuzzing.
Performance risks
Introduces or modifies mechanisms and requires performance validation.
Score anchors
0
No new mechanisms are introduced that require performance validation.
1
The introduced mechanisms can be benchmarked in isolation and do not affect existing performance behavior.
2
The introduced mechanisms cannot be fully benchmarked in isolation, but they only have a limited impact on the existing performance benchmarks.
3
The introduced mechanisms cannot be benchmarked in isolation and have a substantial impact on existing performance benchmarks or have complex interactions with existing mechanisms.
Edge/boundary conditions
Feature contains edge/boundary conditions.
Score anchors
0
No discernible edge cases or boundary conditions are introduced.
1
A single edge-case or boundary-condition prone mechanism is introduced.
2
Multiple edge-case or boundary-condition prone mechanisms are introduced, but none of them requires an elevated number of cases to test.
3
Multiple edge-case or boundary-condition prone mechanisms are introduced and at least one of them requires an elevated number of cases to test.
Cryptography
Introduces new cryptography mechanisms or modifies existing functionality that involves cryptography
Score anchors
0
No cryptography mechanisms are introduced.
1
A new cryptography mechanism is introduced but it is a well known mechanism that is known to have vast resources to aid on its testing.
2
Multiple new cryptography mechanisms are introduced that are well-known or a single but novel mechanism is introduced that is either untested or has limited resources.
3
Multiple new cryptography mechanisms are introduced and at least one of them is a novel mechanism.

Coordination

Cross-EIP interactions and behavior that clients must agree on before tests exist.

XEIP
Cross-EIP interactions
Introduces or modifies mechanisms that affect other EIPs in either the same or past forks.
Score anchors
0
Fully self-contained EIP that does not depend on, modify, or conflict with any other EIP.
1
The EIP interacts with one or more other EIPs in a non-critical and limited way but can be tested independently for the most part.
2
The EIP depends on or modifies one or more other EIPs such that coordinated testing and consideration is required, but interactions are limited in scope and not complex.
3
The EIP has strong interdependencies with multiple EIPs, requiring extensive coordinated cross-EIP testing as well as potential re-design of existing test vectors.
- +1 for every 3 additional interacting EIPs beyond the first 3, each of which requires its own coordinated test cases. List the EIPs in the rationale.
- This row is intentionally uncapped, unlike every other anchor: each interacting EIP is another axis of the test matrix, so a ceiling would make a 12-EIP product indistinguishable from a 3-EIP one.
UNSP
Unspecified behavior requiring cross-client consensus · Checklist revision 2 only
The EIP text does not determine the answer for cases a test can construct. Clients must agree on a previously unspecified detail before tests can be baselined. The cost here is coordination and re-baselining, not test writing.
Score anchors
0
The EIP text determines the answer for every case a test could construct.
1
A few details are unspecified but have an obvious intended reading.
2
Details require client agreement before tests can be written, but they are localized.
3
A previously unspecified *and previously unobservable* behavior becomes consensus-critical; expect tests to be re-baselined on each round of EIP amendment.
- Score this from the EIP's state at assessment time: whether it has client implementations, whether it has been through a devnet, and how many open questions remain on its discussion thread.