{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MMMGG5QTOVSXVJGNVOJDQWSZ5R","short_pith_number":"pith:MMMGG5QT","canonical_record":{"source":{"id":"2502.15631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T17:59:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"25ce539691ad63d0aeff3754565bfc629a4fb643f6de292f623ff83dd9a916e6","abstract_canon_sha256":"ffad8c1fde741cf4acd576ec3bd99c33795dc317de2f02d12d24679594fa0935"},"schema_version":"1.0"},"canonical_sha256":"631863761375657aa4cdab92385a59ec7c995814868f97f1eb9fbfefbb949528","source":{"kind":"arxiv","id":"2502.15631","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15631","created_at":"2026-07-05T10:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15631v1","created_at":"2026-07-05T10:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15631","created_at":"2026-07-05T10:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"MMMGG5QTOVSX","created_at":"2026-07-05T10:18:04Z"},{"alias_kind":"pith_short_16","alias_value":"MMMGG5QTOVSXVJGN","created_at":"2026-07-05T10:18:04Z"},{"alias_kind":"pith_short_8","alias_value":"MMMGG5QT","created_at":"2026-07-05T10:18:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MMMGG5QTOVSXVJGNVOJDQWSZ5R","target":"record","payload":{"canonical_record":{"source":{"id":"2502.15631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T17:59:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"25ce539691ad63d0aeff3754565bfc629a4fb643f6de292f623ff83dd9a916e6","abstract_canon_sha256":"ffad8c1fde741cf4acd576ec3bd99c33795dc317de2f02d12d24679594fa0935"},"schema_version":"1.0"},"canonical_sha256":"631863761375657aa4cdab92385a59ec7c995814868f97f1eb9fbfefbb949528","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:04.866693Z","signature_b64":"9knTdyQtFOx6kWIsvvjTjFQO6lZrGUOooMCfeC/zI+guPJWf7JpD1jz0Yjahj+FMi08EUwvyMLy6B06SzgaEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"631863761375657aa4cdab92385a59ec7c995814868f97f1eb9fbfefbb949528","last_reissued_at":"2026-07-05T10:18:04.866245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:04.866245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.15631","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p59otLGCfIxrN3JFCg+xQ1+4C+nTSsaNvkvyYJbHHiq4MsjY+teXGJwY9lzfhkbxDi5K2p3FDPQ5ioU+1oAyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:50:05.712914Z"},"content_sha256":"ed335dcef2a93a86b45f9631b98267ee0ec8936159c993a1f3170a15474fb6e6","schema_version":"1.0","event_id":"sha256:ed335dcef2a93a86b45f9631b98267ee0ec8936159c993a1f3170a15474fb6e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MMMGG5QTOVSXVJGNVOJDQWSZ5R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Relationship Between Reasoning and Performance in Large Language Models -- o3 (mini) Thinks Harder, Not Longer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andres Algaba, Marthe Ballon, Vincent Ginis","submitted_at":"2025-02-21T17:59:13Z","abstract_excerpt":"Large language models have demonstrated remarkable progress in mathematical reasoning, leveraging chain-of-thought and test-time compute scaling. However, many open questions remain regarding the interplay between reasoning token usage and accuracy gains. In particular, when comparing models across generations, it is unclear whether improved performance results from longer reasoning chains or more efficient reasoning. We systematically analyze chain-of-thought length across o1-mini and o3-mini variants on the Omni-MATH benchmark, finding that o3-mini (m) achieves superior accuracy without requ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15631","kind":"arxiv","version":1},"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/2502.15631/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":"2026-07-05T10:18:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aEliduB5D+lVt0ZQ1xG3te+tqk10/hJm9fgpm5tvff6MVwGFyvL3WysJKCvGEJEmOHaNt38ydWEl6JfLmg8MDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:50:05.713510Z"},"content_sha256":"579fcb60661b4447bf18ff5c6543cc35fdf7af8b326082e9460a4c992937778a","schema_version":"1.0","event_id":"sha256:579fcb60661b4447bf18ff5c6543cc35fdf7af8b326082e9460a4c992937778a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MMMGG5QTOVSXVJGNVOJDQWSZ5R/bundle.json","state_url":"https://pith.science/pith/MMMGG5QTOVSXVJGNVOJDQWSZ5R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MMMGG5QTOVSXVJGNVOJDQWSZ5R/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":"2026-08-05T19:50:05Z","links":{"resolver":"https://pith.science/pith/MMMGG5QTOVSXVJGNVOJDQWSZ5R","bundle":"https://pith.science/pith/MMMGG5QTOVSXVJGNVOJDQWSZ5R/bundle.json","state":"https://pith.science/pith/MMMGG5QTOVSXVJGNVOJDQWSZ5R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MMMGG5QTOVSXVJGNVOJDQWSZ5R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MMMGG5QTOVSXVJGNVOJDQWSZ5R","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":"ffad8c1fde741cf4acd576ec3bd99c33795dc317de2f02d12d24679594fa0935","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T17:59:13Z","title_canon_sha256":"25ce539691ad63d0aeff3754565bfc629a4fb643f6de292f623ff83dd9a916e6"},"schema_version":"1.0","source":{"id":"2502.15631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15631","created_at":"2026-07-05T10:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15631v1","created_at":"2026-07-05T10:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15631","created_at":"2026-07-05T10:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"MMMGG5QTOVSX","created_at":"2026-07-05T10:18:04Z"},{"alias_kind":"pith_short_16","alias_value":"MMMGG5QTOVSXVJGN","created_at":"2026-07-05T10:18:04Z"},{"alias_kind":"pith_short_8","alias_value":"MMMGG5QT","created_at":"2026-07-05T10:18:04Z"}],"graph_snapshots":[{"event_id":"sha256:579fcb60661b4447bf18ff5c6543cc35fdf7af8b326082e9460a4c992937778a","target":"graph","created_at":"2026-07-05T10:18:04Z","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/2502.15631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have demonstrated remarkable progress in mathematical reasoning, leveraging chain-of-thought and test-time compute scaling. However, many open questions remain regarding the interplay between reasoning token usage and accuracy gains. In particular, when comparing models across generations, it is unclear whether improved performance results from longer reasoning chains or more efficient reasoning. We systematically analyze chain-of-thought length across o1-mini and o3-mini variants on the Omni-MATH benchmark, finding that o3-mini (m) achieves superior accuracy without requ","authors_text":"Andres Algaba, Marthe Ballon, Vincent Ginis","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T17:59:13Z","title":"The Relationship Between Reasoning and Performance in Large Language Models -- o3 (mini) Thinks Harder, Not Longer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15631","kind":"arxiv","version":1},"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:ed335dcef2a93a86b45f9631b98267ee0ec8936159c993a1f3170a15474fb6e6","target":"record","created_at":"2026-07-05T10:18:04Z","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":"ffad8c1fde741cf4acd576ec3bd99c33795dc317de2f02d12d24679594fa0935","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T17:59:13Z","title_canon_sha256":"25ce539691ad63d0aeff3754565bfc629a4fb643f6de292f623ff83dd9a916e6"},"schema_version":"1.0","source":{"id":"2502.15631","kind":"arxiv","version":1}},"canonical_sha256":"631863761375657aa4cdab92385a59ec7c995814868f97f1eb9fbfefbb949528","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"631863761375657aa4cdab92385a59ec7c995814868f97f1eb9fbfefbb949528","first_computed_at":"2026-07-05T10:18:04.866245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:04.866245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9knTdyQtFOx6kWIsvvjTjFQO6lZrGUOooMCfeC/zI+guPJWf7JpD1jz0Yjahj+FMi08EUwvyMLy6B06SzgaEDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:04.866693Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed335dcef2a93a86b45f9631b98267ee0ec8936159c993a1f3170a15474fb6e6","sha256:579fcb60661b4447bf18ff5c6543cc35fdf7af8b326082e9460a4c992937778a"],"state_sha256":"5cd9f4228c7ba7df6a9b19e7982bb311c483701aa9403fbd12246f22ccef7829"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KjPuGjfJg8YTzDg605xC830zb62+ZfJUm1Fj2Gs19d0oea1qWDSDz939TtuOUphCysvTyBprFC8F6PiJqZSwCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T19:50:05.718143Z","bundle_sha256":"d62c3fe997fc82fdb0dff0084bb86f431e63ba85ad18aaf1d4845a604bc36be6"}}