{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2X6LUKKG5A6QG3TVAXYMGCTOGA","short_pith_number":"pith:2X6LUKKG","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"},"canonical_sha256":"d5fcba2946e83d036e7505f0c30a6e300bf0573006442aa680b9318aeaaec936","source":{"kind":"arxiv","id":"2605.05138","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.05138","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.05138v2","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05138","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"2X6LUKKG5A6Q","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"2X6LUKKG5A6QG3TV","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"2X6LUKKG","created_at":"2026-06-09T01:05:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2X6LUKKG5A6QG3TVAXYMGCTOGA","target":"record","payload":{"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"},"canonical_sha256":"d5fcba2946e83d036e7505f0c30a6e300bf0573006442aa680b9318aeaaec936","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"},"source_kind":"arxiv","source_id":"2605.05138","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:05:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7LzztD0lK12DRofCOcwMp1AxIRj8scDDiZ1ewlRcFo1AOkcm09+D7aeCcbuWCJSiu9S5jrZgtQRoRt4WWHnGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T21:18:22.320771Z"},"content_sha256":"382318c16a5e24981aa6bfc42a92adea108507273ae2e9fd7aa5a8afecd2a467","schema_version":"1.0","event_id":"sha256:382318c16a5e24981aa6bfc42a92adea108507273ae2e9fd7aa5a8afecd2a467"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2X6LUKKG5A6QG3TVAXYMGCTOGA","target":"graph","payload":{"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"},"verdict_id":"31eb2c2b-de04-4a80-8766-f4325fc7de51"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:05:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"82J5EXrANtVcHy6s8HiNzqU0QXK7ysmrrhHdkji//I4j2vQNa3K23bv5QfY1XxACKL6YQH9CDI1tQwSxUshwAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T21:18:22.321670Z"},"content_sha256":"efda2a70b3538ebbf3a1594b2ffc039c5994002fa3edffa082525668064ae9ef","schema_version":"1.0","event_id":"sha256:efda2a70b3538ebbf3a1594b2ffc039c5994002fa3edffa082525668064ae9ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA/bundle.json","state_url":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T21:18:22Z","links":{"resolver":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA","bundle":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA/bundle.json","state":"https://pith.science/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2X6LUKKG5A6QG3TVAXYMGCTOGA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2X6LUKKG5A6QG3TVAXYMGCTOGA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"751e8135997294981010355d4f00d6dca27dfc7ab4ac696b11d14aaa1d2ac278","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-06T17:12:36Z","title_canon_sha256":"9a6614e5b4848633f82450c5d093edf98cd4bcbc64ac279d5308faf2d5b4d6ff"},"schema_version":"1.0","source":{"id":"2605.05138","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.05138","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.05138v2","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05138","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"2X6LUKKG5A6Q","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"2X6LUKKG5A6QG3TV","created_at":"2026-06-09T01:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"2X6LUKKG","created_at":"2026-06-09T01:05:18Z"}],"graph_snapshots":[{"event_id":"sha256:efda2a70b3538ebbf3a1594b2ffc039c5994002fa3edffa082525668064ae9ef","target":"graph","created_at":"2026-06-09T01:05:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Executable world model agents solve 7 of 25 ARC-AGI-3 public games with 32.58% mean RHAE as a game-general baseline."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A coding-agent system using executable Python world models solves 7 of 25 public ARC-AGI-3 games with no game-specific code."}],"snapshot_sha256":"426f977406652b2afb7c45b63ad52800054bc592b9032df3c33ba6337a8ee8de"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a53259f1c6684c514591e6d48aada392657918e04854f0d9e3a5e60677618326"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.05138/integrity.json","findings":[],"snapshot_sha256":"3d1d61b9a383e85d57f48259e5bf87e31c3bdb46e8dca951986c81180fb60fb2","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Sergey Rodionov","cross_cats":[],"headline":"A coding-agent system using executable Python world models solves 7 of 25 public ARC-AGI-3 games with no game-specific code.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-06T17:12:36Z","title":"Executable World Models for ARC-AGI-3 in the Era of Coding Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.05138","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T17:47:48.925371Z","id":"31eb2c2b-de04-4a80-8766-f4325fc7de51","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"31eb2c2b-de04-4a80-8766-f4325fc7de51"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:382318c16a5e24981aa6bfc42a92adea108507273ae2e9fd7aa5a8afecd2a467","target":"record","created_at":"2026-06-09T01:05:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"751e8135997294981010355d4f00d6dca27dfc7ab4ac696b11d14aaa1d2ac278","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-06T17:12:36Z","title_canon_sha256":"9a6614e5b4848633f82450c5d093edf98cd4bcbc64ac279d5308faf2d5b4d6ff"},"schema_version":"1.0","source":{"id":"2605.05138","kind":"arxiv","version":2}},"canonical_sha256":"d5fcba2946e83d036e7505f0c30a6e300bf0573006442aa680b9318aeaaec936","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5fcba2946e83d036e7505f0c30a6e300bf0573006442aa680b9318aeaaec936","first_computed_at":"2026-06-09T01:05:18.778679Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:18.778679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bW5ecRLqnY6qoOBzYGfABvfoeuNOeX56AGQizDfmbs6MW3bsrijeSunb9BrNcsuTaD5xttGTuGyUaTGtOJgADg==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:18.779126Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.05138","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:382318c16a5e24981aa6bfc42a92adea108507273ae2e9fd7aa5a8afecd2a467","sha256:efda2a70b3538ebbf3a1594b2ffc039c5994002fa3edffa082525668064ae9ef"],"state_sha256":"c6523d9a53792f0c2cffa30fce6238ef6368e920c1daf712f89192b6f98bdc66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4iwmZpYe8lFpS7Ufr6HLJmCiVQCThlFzmYn6Ft3wjLzaMPTywOg/3EqOe12BbSuJK3diKO8OiCpCBc4go5npBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T21:18:22.324593Z","bundle_sha256":"69fcdfaa6d7ee7ae271214c130e2cb7a4957232d30c709de1dac0329e0316d46"}}