{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4AJCLYU6L3EZKMLICK3CX4EVXT","short_pith_number":"pith:4AJCLYU6","canonical_record":{"source":{"id":"2407.13729","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T17:30:48Z","cross_cats_sorted":[],"title_canon_sha256":"b0fbddf3f47648b81158a700cbc32eeb8f37a3c3ef464031dcdd8264211da1a7","abstract_canon_sha256":"b213d48e4b0c5115aa4c74e7ce69cb681743acc38f13d936b4880ff83b5fae98"},"schema_version":"1.0"},"canonical_sha256":"e01225e29e5ec995316812b62bf095bcda148032213886805aae7cfa13aafb84","source":{"kind":"arxiv","id":"2407.13729","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13729","created_at":"2026-07-05T12:07:54Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13729v2","created_at":"2026-07-05T12:07:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13729","created_at":"2026-07-05T12:07:54Z"},{"alias_kind":"pith_short_12","alias_value":"4AJCLYU6L3EZ","created_at":"2026-07-05T12:07:54Z"},{"alias_kind":"pith_short_16","alias_value":"4AJCLYU6L3EZKMLI","created_at":"2026-07-05T12:07:54Z"},{"alias_kind":"pith_short_8","alias_value":"4AJCLYU6","created_at":"2026-07-05T12:07:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4AJCLYU6L3EZKMLICK3CX4EVXT","target":"record","payload":{"canonical_record":{"source":{"id":"2407.13729","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T17:30:48Z","cross_cats_sorted":[],"title_canon_sha256":"b0fbddf3f47648b81158a700cbc32eeb8f37a3c3ef464031dcdd8264211da1a7","abstract_canon_sha256":"b213d48e4b0c5115aa4c74e7ce69cb681743acc38f13d936b4880ff83b5fae98"},"schema_version":"1.0"},"canonical_sha256":"e01225e29e5ec995316812b62bf095bcda148032213886805aae7cfa13aafb84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:54.134120Z","signature_b64":"Q68KikAFX1633EqlUrsj2i4xMS5FucjtRhIcKHDPLWkI1AKTffXTzePit0fTHwbCW3VIvltB4TUNFnjmXldRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e01225e29e5ec995316812b62bf095bcda148032213886805aae7cfa13aafb84","last_reissued_at":"2026-07-05T12:07:54.133522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:54.133522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.13729","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":"2026-07-05T12:07:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ew4TiUyopYd0CBQBf/kVEdEjD84Ch3ZW7OlMNJ7USWSNaSpcJ7Gzgfj67biyUDPc5cXaexx1WqaQDd9Cg3+oCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T14:12:18.257002Z"},"content_sha256":"0ca3881fbb6064fa3352b13e558f5915bdec2a1b8e4d8484e43ed42d050fc1a3","schema_version":"1.0","event_id":"sha256:0ca3881fbb6064fa3352b13e558f5915bdec2a1b8e4d8484e43ed42d050fc1a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4AJCLYU6L3EZKMLICK3CX4EVXT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Baba Is AI: Break the Rules to Beat the Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrei Barbu, Christopher J. Cueva, Ignacio Cases, Meagan Jens, Michelangelo Naim, Nathan Cloos, Yen-Ling Kuo","submitted_at":"2024-07-18T17:30:48Z","abstract_excerpt":"Humans solve problems by following existing rules and procedures, and also by leaps of creativity to redefine those rules and objectives. To probe these abilities, we developed a new benchmark based on the game Baba Is You where an agent manipulates both objects in the environment and rules, represented by movable tiles with words written on them, to reach a specified goal and win the game. We test three state-of-the-art multi-modal large language models (OpenAI GPT-4o, Google Gemini-1.5-Pro and Gemini-1.5-Flash) and find that they fail dramatically when generalization requires that the rules "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13729","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.13729/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:07:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Gt/8thF7nofP4iyMEFgg59PAXjkJQNwEMvzK530dn1epU0Rtp/dIKW2AuolKkYnu4tN9WWq1nS4vk19NnOrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T14:12:18.257396Z"},"content_sha256":"a11eb09d909e5a500094a97d31e44b3e49b2877adcfd2f398929119fe3ee1683","schema_version":"1.0","event_id":"sha256:a11eb09d909e5a500094a97d31e44b3e49b2877adcfd2f398929119fe3ee1683"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4AJCLYU6L3EZKMLICK3CX4EVXT/bundle.json","state_url":"https://pith.science/pith/4AJCLYU6L3EZKMLICK3CX4EVXT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4AJCLYU6L3EZKMLICK3CX4EVXT/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":"2026-07-11T14:12:18Z","links":{"resolver":"https://pith.science/pith/4AJCLYU6L3EZKMLICK3CX4EVXT","bundle":"https://pith.science/pith/4AJCLYU6L3EZKMLICK3CX4EVXT/bundle.json","state":"https://pith.science/pith/4AJCLYU6L3EZKMLICK3CX4EVXT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4AJCLYU6L3EZKMLICK3CX4EVXT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4AJCLYU6L3EZKMLICK3CX4EVXT","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":"b213d48e4b0c5115aa4c74e7ce69cb681743acc38f13d936b4880ff83b5fae98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T17:30:48Z","title_canon_sha256":"b0fbddf3f47648b81158a700cbc32eeb8f37a3c3ef464031dcdd8264211da1a7"},"schema_version":"1.0","source":{"id":"2407.13729","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13729","created_at":"2026-07-05T12:07:54Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13729v2","created_at":"2026-07-05T12:07:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13729","created_at":"2026-07-05T12:07:54Z"},{"alias_kind":"pith_short_12","alias_value":"4AJCLYU6L3EZ","created_at":"2026-07-05T12:07:54Z"},{"alias_kind":"pith_short_16","alias_value":"4AJCLYU6L3EZKMLI","created_at":"2026-07-05T12:07:54Z"},{"alias_kind":"pith_short_8","alias_value":"4AJCLYU6","created_at":"2026-07-05T12:07:54Z"}],"graph_snapshots":[{"event_id":"sha256:a11eb09d909e5a500094a97d31e44b3e49b2877adcfd2f398929119fe3ee1683","target":"graph","created_at":"2026-07-05T12:07:54Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.13729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans solve problems by following existing rules and procedures, and also by leaps of creativity to redefine those rules and objectives. To probe these abilities, we developed a new benchmark based on the game Baba Is You where an agent manipulates both objects in the environment and rules, represented by movable tiles with words written on them, to reach a specified goal and win the game. We test three state-of-the-art multi-modal large language models (OpenAI GPT-4o, Google Gemini-1.5-Pro and Gemini-1.5-Flash) and find that they fail dramatically when generalization requires that the rules ","authors_text":"Andrei Barbu, Christopher J. Cueva, Ignacio Cases, Meagan Jens, Michelangelo Naim, Nathan Cloos, Yen-Ling Kuo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T17:30:48Z","title":"Baba Is AI: Break the Rules to Beat the Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13729","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0ca3881fbb6064fa3352b13e558f5915bdec2a1b8e4d8484e43ed42d050fc1a3","target":"record","created_at":"2026-07-05T12:07:54Z","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":"b213d48e4b0c5115aa4c74e7ce69cb681743acc38f13d936b4880ff83b5fae98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T17:30:48Z","title_canon_sha256":"b0fbddf3f47648b81158a700cbc32eeb8f37a3c3ef464031dcdd8264211da1a7"},"schema_version":"1.0","source":{"id":"2407.13729","kind":"arxiv","version":2}},"canonical_sha256":"e01225e29e5ec995316812b62bf095bcda148032213886805aae7cfa13aafb84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e01225e29e5ec995316812b62bf095bcda148032213886805aae7cfa13aafb84","first_computed_at":"2026-07-05T12:07:54.133522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:54.133522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q68KikAFX1633EqlUrsj2i4xMS5FucjtRhIcKHDPLWkI1AKTffXTzePit0fTHwbCW3VIvltB4TUNFnjmXldRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:54.134120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13729","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ca3881fbb6064fa3352b13e558f5915bdec2a1b8e4d8484e43ed42d050fc1a3","sha256:a11eb09d909e5a500094a97d31e44b3e49b2877adcfd2f398929119fe3ee1683"],"state_sha256":"1344f77b9535cfe54c0a363b7de1144b8f93943bc6e7fb1fd1d38fe88e2e30e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2gnQS+i3/keszl3EoC8QunNalN5U+NbDaVC1GJppKOvSts8c70I/qkrFWPR9f6sNbI4bSY0ao4UeLjmdeQedCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T14:12:18.259533Z","bundle_sha256":"61ba64d2363ea095c0b35975d0e90ed85b1b6af461954e91388becb2fb361fb6"}}