{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Y42NP566HYMJRUZDTY55RYOPMS","short_pith_number":"pith:Y42NP566","canonical_record":{"source":{"id":"2307.13692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-25T17:55:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0faaa82bf56f8408e66cd5c5ca2fa2b1ac167d674d35812661823d4f4169ccf1","abstract_canon_sha256":"60a28acbd3f8c4fc58a8bec0121781f3005044307e407d71c8635923e71f197f"},"schema_version":"1.0"},"canonical_sha256":"c734d7f7de3e1898d3239e3bd8e1cf64b8ed80283930c80e0a7f30c03529a646","source":{"kind":"arxiv","id":"2307.13692","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.13692","created_at":"2026-07-05T06:35:29Z"},{"alias_kind":"arxiv_version","alias_value":"2307.13692v2","created_at":"2026-07-05T06:35:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13692","created_at":"2026-07-05T06:35:29Z"},{"alias_kind":"pith_short_12","alias_value":"Y42NP566HYMJ","created_at":"2026-07-05T06:35:29Z"},{"alias_kind":"pith_short_16","alias_value":"Y42NP566HYMJRUZD","created_at":"2026-07-05T06:35:29Z"},{"alias_kind":"pith_short_8","alias_value":"Y42NP566","created_at":"2026-07-05T06:35:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Y42NP566HYMJRUZDTY55RYOPMS","target":"record","payload":{"canonical_record":{"source":{"id":"2307.13692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-25T17:55:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0faaa82bf56f8408e66cd5c5ca2fa2b1ac167d674d35812661823d4f4169ccf1","abstract_canon_sha256":"60a28acbd3f8c4fc58a8bec0121781f3005044307e407d71c8635923e71f197f"},"schema_version":"1.0"},"canonical_sha256":"c734d7f7de3e1898d3239e3bd8e1cf64b8ed80283930c80e0a7f30c03529a646","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:29.257234Z","signature_b64":"slXOw6nSrp2sZTxCG56OWNUGGNiMStY6B19qxiwfEDNrxtLmHqG7fRaG8rpkYsoptTUl+AVqomYXpFBrGxWBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c734d7f7de3e1898d3239e3bd8e1cf64b8ed80283930c80e0a7f30c03529a646","last_reissued_at":"2026-07-05T06:35:29.256805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:29.256805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.13692","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":"2026-07-05T06:35:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R92SSrhhK2jHV6eb6IGrXOpjwR32yq9sf8quBrJ52/k66O3BsUxfCWg1okaztn1xabnBfNGcya0Qz555CsTrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T13:54:57.213535Z"},"content_sha256":"5e9300311c214de536e278db3ceaffe2735547bcc278b0ee834649fa8bc752cf","schema_version":"1.0","event_id":"sha256:5e9300311c214de536e278db3ceaffe2735547bcc278b0ee834649fa8bc752cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Y42NP566HYMJRUZDTY55RYOPMS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ARB: Advanced Reasoning Benchmark for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander Havrilla, Alexander Kranias, Aran Komatsuzaki, Daniel Paleka, John J. Nay, Kshitij Gupta, Paula Vidas, Pranav Tadepalli, Tomohiro Sawada","submitted_at":"2023-07-25T17:55:19Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable performance on various quantitative reasoning and knowledge benchmarks. However, many of these benchmarks are losing utility as LLMs get increasingly high scores, despite not yet reaching expert performance in these domains. We introduce ARB, a novel benchmark composed of advanced reasoning problems in multiple fields. ARB presents a more challenging test than prior benchmarks, featuring problems in mathematics, physics, biology, chemistry, and law. As a subset of ARB, we introduce a challenging set of math and physics problems which re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13692","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/2307.13692/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":"2026-07-05T06:35:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gPyAK6ucZ+5jtgoLOuQh/1Dzt/D21EUude3mmCGeHmbkQYW49aecEByMZu+MpEnXu0yISyH3I5y1pE8egtFDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T13:54:57.213957Z"},"content_sha256":"1da2dad4022d27d38a86794c27062da19faeff74f379866a8b76c3a30480a6be","schema_version":"1.0","event_id":"sha256:1da2dad4022d27d38a86794c27062da19faeff74f379866a8b76c3a30480a6be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y42NP566HYMJRUZDTY55RYOPMS/bundle.json","state_url":"https://pith.science/pith/Y42NP566HYMJRUZDTY55RYOPMS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y42NP566HYMJRUZDTY55RYOPMS/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":"2026-07-12T13:54:57Z","links":{"resolver":"https://pith.science/pith/Y42NP566HYMJRUZDTY55RYOPMS","bundle":"https://pith.science/pith/Y42NP566HYMJRUZDTY55RYOPMS/bundle.json","state":"https://pith.science/pith/Y42NP566HYMJRUZDTY55RYOPMS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y42NP566HYMJRUZDTY55RYOPMS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y42NP566HYMJRUZDTY55RYOPMS","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":"60a28acbd3f8c4fc58a8bec0121781f3005044307e407d71c8635923e71f197f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-25T17:55:19Z","title_canon_sha256":"0faaa82bf56f8408e66cd5c5ca2fa2b1ac167d674d35812661823d4f4169ccf1"},"schema_version":"1.0","source":{"id":"2307.13692","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.13692","created_at":"2026-07-05T06:35:29Z"},{"alias_kind":"arxiv_version","alias_value":"2307.13692v2","created_at":"2026-07-05T06:35:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13692","created_at":"2026-07-05T06:35:29Z"},{"alias_kind":"pith_short_12","alias_value":"Y42NP566HYMJ","created_at":"2026-07-05T06:35:29Z"},{"alias_kind":"pith_short_16","alias_value":"Y42NP566HYMJRUZD","created_at":"2026-07-05T06:35:29Z"},{"alias_kind":"pith_short_8","alias_value":"Y42NP566","created_at":"2026-07-05T06:35:29Z"}],"graph_snapshots":[{"event_id":"sha256:1da2dad4022d27d38a86794c27062da19faeff74f379866a8b76c3a30480a6be","target":"graph","created_at":"2026-07-05T06:35:29Z","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/2307.13692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable performance on various quantitative reasoning and knowledge benchmarks. However, many of these benchmarks are losing utility as LLMs get increasingly high scores, despite not yet reaching expert performance in these domains. We introduce ARB, a novel benchmark composed of advanced reasoning problems in multiple fields. ARB presents a more challenging test than prior benchmarks, featuring problems in mathematics, physics, biology, chemistry, and law. As a subset of ARB, we introduce a challenging set of math and physics problems which re","authors_text":"Alexander Havrilla, Alexander Kranias, Aran Komatsuzaki, Daniel Paleka, John J. Nay, Kshitij Gupta, Paula Vidas, Pranav Tadepalli, Tomohiro Sawada","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-25T17:55:19Z","title":"ARB: Advanced Reasoning Benchmark for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13692","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":"sha256:5e9300311c214de536e278db3ceaffe2735547bcc278b0ee834649fa8bc752cf","target":"record","created_at":"2026-07-05T06:35:29Z","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":"60a28acbd3f8c4fc58a8bec0121781f3005044307e407d71c8635923e71f197f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-25T17:55:19Z","title_canon_sha256":"0faaa82bf56f8408e66cd5c5ca2fa2b1ac167d674d35812661823d4f4169ccf1"},"schema_version":"1.0","source":{"id":"2307.13692","kind":"arxiv","version":2}},"canonical_sha256":"c734d7f7de3e1898d3239e3bd8e1cf64b8ed80283930c80e0a7f30c03529a646","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c734d7f7de3e1898d3239e3bd8e1cf64b8ed80283930c80e0a7f30c03529a646","first_computed_at":"2026-07-05T06:35:29.256805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:29.256805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"slXOw6nSrp2sZTxCG56OWNUGGNiMStY6B19qxiwfEDNrxtLmHqG7fRaG8rpkYsoptTUl+AVqomYXpFBrGxWBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:29.257234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.13692","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e9300311c214de536e278db3ceaffe2735547bcc278b0ee834649fa8bc752cf","sha256:1da2dad4022d27d38a86794c27062da19faeff74f379866a8b76c3a30480a6be"],"state_sha256":"e61b884b5d32d6b19e33fdead0b7d018cba96eb6f5049ab0cd383004e9e20c28"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PE+pEWzh6MmMJ/MIoDbYvMd+mPLv9VY92C9JPS/3CG06tA/I49lpsbzRBPh9mSdSwRB/9LkaRnEarQ7aQ0rdBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T13:54:57.216429Z","bundle_sha256":"1d502e169f9e896fb1ef187ed2fdc4654c44a8e17d446336af01d9e4a73baeaf"}}