{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2X6LUKKG5A6QG3TVAXYMGCTOGA","short_pith_number":"pith:2X6LUKKG","schema_version":"1.0","canonical_sha256":"d5fcba2946e83d036e7505f0c30a6e300bf0573006442aa680b9318aeaaec936","source":{"kind":"arxiv","id":"2605.05138","version":2},"attestation_state":"computed","paper":{"title":"Executable World Models for ARC-AGI-3 in the Era of Coding Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A coding-agent system using executable Python world models solves 7 of 25 public ARC-AGI-3 games with no game-specific code.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Sergey Rodionov","submitted_at":"2026-05-06T17:12:36Z","abstract_excerpt":"We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executable Python world model, verifies it against previous observations, refactors it toward simpler abstractions as a practical proxy for an MDL-like simplicity bias, and plans through the model before acting. The system is intentionally direct: it uses a scripted controller, predefined world-model interfaces, verifier programs, and a plan executor, but no hand-coded game-specific logic. The agent-facing prompts, workspace, and controller contain no game-specific code, game-specific prompts, hand-coded h"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.05138","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-06T17:12:36Z","cross_cats_sorted":[],"title_canon_sha256":"9a6614e5b4848633f82450c5d093edf98cd4bcbc64ac279d5308faf2d5b4d6ff","abstract_canon_sha256":"751e8135997294981010355d4f00d6dca27dfc7ab4ac696b11d14aaa1d2ac278"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:18.779126Z","signature_b64":"bW5ecRLqnY6qoOBzYGfABvfoeuNOeX56AGQizDfmbs6MW3bsrijeSunb9BrNcsuTaD5xttGTuGyUaTGtOJgADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5fcba2946e83d036e7505f0c30a6e300bf0573006442aa680b9318aeaaec936","last_reissued_at":"2026-06-09T01:05:18.778679Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:18.778679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Executable World Models for ARC-AGI-3 in the Era of Coding Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A coding-agent system using executable Python world models solves 7 of 25 public ARC-AGI-3 games with no game-specific code.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Sergey Rodionov","submitted_at":"2026-05-06T17:12:36Z","abstract_excerpt":"We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executable Python world model, verifies it against previous observations, refactors it toward simpler abstractions as a practical proxy for an MDL-like simplicity bias, and plans through the model before acting. The system is intentionally direct: it uses a scripted controller, predefined world-model interfaces, verifier programs, and a plan executor, but no hand-coded game-specific logic. The agent-facing prompts, workspace, and controller contain no game-specific code, game-specific prompts, hand-coded h"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The agent fully solved 7 games, achieved a Relative Human Action Efficiency greater than 75% on 6 games, and obtained a mean per-game RHAE of 32.58%. Because the system uses no game-specific code, it can serve as a game-general baseline for ARC-AGI-3.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That verifier-driven executable Python world models with refactoring as a proxy for MDL-like simplicity bias will generalize to the private validation set and other unseen tasks without requiring game-specific logic.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Executable world model agents solve 7 of 25 ARC-AGI-3 public games with 32.58% mean RHAE as a game-general baseline.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A coding-agent system using executable Python world models solves 7 of 25 public ARC-AGI-3 games with no game-specific code.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"426f977406652b2afb7c45b63ad52800054bc592b9032df3c33ba6337a8ee8de"},"source":{"id":"2605.05138","kind":"arxiv","version":2},"verdict":{"id":"31eb2c2b-de04-4a80-8766-f4325fc7de51","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T17:47:48.925371Z","strongest_claim":"The agent fully solved 7 games, achieved a Relative Human Action Efficiency greater than 75% on 6 games, and obtained a mean per-game RHAE of 32.58%. Because the system uses no game-specific code, it can serve as a game-general baseline for ARC-AGI-3.","one_line_summary":"Executable world model agents solve 7 of 25 ARC-AGI-3 public games with 32.58% mean RHAE as a game-general baseline.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That verifier-driven executable Python world models with refactoring as a proxy for MDL-like simplicity bias will generalize to the private validation set and other unseen tasks without requiring game-specific logic.","pith_extraction_headline":"A coding-agent system using executable Python world models solves 7 of 25 public ARC-AGI-3 games with no game-specific code."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.05138/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T10:36:11.066307Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.495118Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T13:49:11.916293Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3d1d61b9a383e85d57f48259e5bf87e31c3bdb46e8dca951986c81180fb60fb2"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a53259f1c6684c514591e6d48aada392657918e04854f0d9e3a5e60677618326"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.05138","created_at":"2026-06-09T01:05:18.778749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.05138v2","created_at":"2026-06-09T01:05:18.778749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05138","created_at":"2026-06-09T01:05:18.778749+00:00"},{"alias_kind":"pith_short_12","alias_value":"2X6LUKKG5A6Q","created_at":"2026-06-09T01:05:18.778749+00:00"},{"alias_kind":"pith_short_16","alias_value":"2X6LUKKG5A6QG3TV","created_at":"2026-06-09T01:05:18.778749+00:00"},{"alias_kind":"pith_short_8","alias_value":"2X6LUKKG","created_at":"2026-06-09T01:05:18.778749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA","json":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA.json","graph_json":"https://pith.science/api/pith-number/2X6LUKKG5A6QG3TVAXYMGCTOGA/graph.json","events_json":"https://pith.science/api/pith-number/2X6LUKKG5A6QG3TVAXYMGCTOGA/events.json","paper":"https://pith.science/paper/2X6LUKKG"},"agent_actions":{"view_html":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA","download_json":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA.json","view_paper":"https://pith.science/paper/2X6LUKKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.05138&json=true","fetch_graph":"https://pith.science/api/pith-number/2X6LUKKG5A6QG3TVAXYMGCTOGA/graph.json","fetch_events":"https://pith.science/api/pith-number/2X6LUKKG5A6QG3TVAXYMGCTOGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA/action/storage_attestation","attest_author":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA/action/author_attestation","sign_citation":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA/action/citation_signature","submit_replication":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA/action/replication_record"}},"created_at":"2026-06-09T01:05:18.778749+00:00","updated_at":"2026-06-09T01:05:18.778749+00:00"}