{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZM5E6BUMYNEWUJIWWPAZIJSJZO","short_pith_number":"pith:ZM5E6BUM","canonical_record":{"source":{"id":"2410.01748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T17:01:10Z","cross_cats_sorted":[],"title_canon_sha256":"2df591f0425718e826a699f24559ea9c364bbd7ab4a60fb7c222003d413658ff","abstract_canon_sha256":"afa6d9cdf884772caa05f62f72b959ccbe74225357f638c4543449e9fe9fb34d"},"schema_version":"1.0"},"canonical_sha256":"cb3a4f068cc3496a2516b3c1942649cba6063f36c780c525e56d3ed495ee8bef","source":{"kind":"arxiv","id":"2410.01748","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01748","created_at":"2026-07-05T09:14:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01748v1","created_at":"2026-07-05T09:14:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01748","created_at":"2026-07-05T09:14:51Z"},{"alias_kind":"pith_short_12","alias_value":"ZM5E6BUMYNEW","created_at":"2026-07-05T09:14:51Z"},{"alias_kind":"pith_short_16","alias_value":"ZM5E6BUMYNEWUJIW","created_at":"2026-07-05T09:14:51Z"},{"alias_kind":"pith_short_8","alias_value":"ZM5E6BUM","created_at":"2026-07-05T09:14:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZM5E6BUMYNEWUJIWWPAZIJSJZO","target":"record","payload":{"canonical_record":{"source":{"id":"2410.01748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T17:01:10Z","cross_cats_sorted":[],"title_canon_sha256":"2df591f0425718e826a699f24559ea9c364bbd7ab4a60fb7c222003d413658ff","abstract_canon_sha256":"afa6d9cdf884772caa05f62f72b959ccbe74225357f638c4543449e9fe9fb34d"},"schema_version":"1.0"},"canonical_sha256":"cb3a4f068cc3496a2516b3c1942649cba6063f36c780c525e56d3ed495ee8bef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:51.464678Z","signature_b64":"QJxbqbUpkFFZzsewXror6Gu2Mekk0hQfpLB/633s+OD7Lr1GyBy7yOHaY7SEDJvcpO+wjCLYeWW/eRL/9TzTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb3a4f068cc3496a2516b3c1942649cba6063f36c780c525e56d3ed495ee8bef","last_reissued_at":"2026-07-05T09:14:51.464194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:51.464194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.01748","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":"2026-07-05T09:14:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jG2CkHDGzm7HPNx4X7poch6LI7/dsl8nIWAWSZVJO1fiN6yO2kx/6t08AyD5PqXbOp2Hl2cZFU6QdUxAt3RsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:10:18.589350Z"},"content_sha256":"03664d9efd3e4c104f668c6721ee11e1ddcbc49fada63baf97ce3ec522d6d34c","schema_version":"1.0","event_id":"sha256:03664d9efd3e4c104f668c6721ee11e1ddcbc49fada63baf97ce3ec522d6d34c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZM5E6BUMYNEWUJIWWPAZIJSJZO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Not All LLM Reasoners Are Created Equal","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Alessandro Sordoni, Arian Hosseini, Daniel Toyama, Rishabh Agarwal","submitted_at":"2024-10-02T17:01:10Z","abstract_excerpt":"We study the depth of grade-school math (GSM) problem-solving capabilities of LLMs. To this end, we evaluate their performance on pairs of existing math word problems together so that the answer to the second problem depends on correctly answering the first problem. Our findings reveal a significant reasoning gap in most LLMs, that is performance difference between solving the compositional pairs and solving each question independently. This gap is more pronounced in smaller, more cost-efficient, and math-specialized models. Moreover, instruction-tuning recipes and code generation have varying"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01748","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/2410.01748/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":"2026-07-05T09:14:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6bEwRySq6VVefahEN9kkEKIY0nvt7P8gpyVbvzcDzh541It7mG3LQUEBnMe6kznwwZwgMPF1nYvavghnB75zCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:10:18.589763Z"},"content_sha256":"f9c60be88cd8c5cf7d4cf7799c734e3e011613802516491e048964ba12fb0567","schema_version":"1.0","event_id":"sha256:f9c60be88cd8c5cf7d4cf7799c734e3e011613802516491e048964ba12fb0567"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZM5E6BUMYNEWUJIWWPAZIJSJZO/bundle.json","state_url":"https://pith.science/pith/ZM5E6BUMYNEWUJIWWPAZIJSJZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZM5E6BUMYNEWUJIWWPAZIJSJZO/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":"2026-07-07T07:10:18Z","links":{"resolver":"https://pith.science/pith/ZM5E6BUMYNEWUJIWWPAZIJSJZO","bundle":"https://pith.science/pith/ZM5E6BUMYNEWUJIWWPAZIJSJZO/bundle.json","state":"https://pith.science/pith/ZM5E6BUMYNEWUJIWWPAZIJSJZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZM5E6BUMYNEWUJIWWPAZIJSJZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZM5E6BUMYNEWUJIWWPAZIJSJZO","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":"afa6d9cdf884772caa05f62f72b959ccbe74225357f638c4543449e9fe9fb34d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T17:01:10Z","title_canon_sha256":"2df591f0425718e826a699f24559ea9c364bbd7ab4a60fb7c222003d413658ff"},"schema_version":"1.0","source":{"id":"2410.01748","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01748","created_at":"2026-07-05T09:14:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01748v1","created_at":"2026-07-05T09:14:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01748","created_at":"2026-07-05T09:14:51Z"},{"alias_kind":"pith_short_12","alias_value":"ZM5E6BUMYNEW","created_at":"2026-07-05T09:14:51Z"},{"alias_kind":"pith_short_16","alias_value":"ZM5E6BUMYNEWUJIW","created_at":"2026-07-05T09:14:51Z"},{"alias_kind":"pith_short_8","alias_value":"ZM5E6BUM","created_at":"2026-07-05T09:14:51Z"}],"graph_snapshots":[{"event_id":"sha256:f9c60be88cd8c5cf7d4cf7799c734e3e011613802516491e048964ba12fb0567","target":"graph","created_at":"2026-07-05T09:14:51Z","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/2410.01748/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the depth of grade-school math (GSM) problem-solving capabilities of LLMs. To this end, we evaluate their performance on pairs of existing math word problems together so that the answer to the second problem depends on correctly answering the first problem. Our findings reveal a significant reasoning gap in most LLMs, that is performance difference between solving the compositional pairs and solving each question independently. This gap is more pronounced in smaller, more cost-efficient, and math-specialized models. Moreover, instruction-tuning recipes and code generation have varying","authors_text":"Aaron Courville, Alessandro Sordoni, Arian Hosseini, Daniel Toyama, Rishabh Agarwal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T17:01:10Z","title":"Not All LLM Reasoners Are Created Equal"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01748","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":"sha256:03664d9efd3e4c104f668c6721ee11e1ddcbc49fada63baf97ce3ec522d6d34c","target":"record","created_at":"2026-07-05T09:14:51Z","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":"afa6d9cdf884772caa05f62f72b959ccbe74225357f638c4543449e9fe9fb34d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T17:01:10Z","title_canon_sha256":"2df591f0425718e826a699f24559ea9c364bbd7ab4a60fb7c222003d413658ff"},"schema_version":"1.0","source":{"id":"2410.01748","kind":"arxiv","version":1}},"canonical_sha256":"cb3a4f068cc3496a2516b3c1942649cba6063f36c780c525e56d3ed495ee8bef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb3a4f068cc3496a2516b3c1942649cba6063f36c780c525e56d3ed495ee8bef","first_computed_at":"2026-07-05T09:14:51.464194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:51.464194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QJxbqbUpkFFZzsewXror6Gu2Mekk0hQfpLB/633s+OD7Lr1GyBy7yOHaY7SEDJvcpO+wjCLYeWW/eRL/9TzTBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:51.464678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01748","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03664d9efd3e4c104f668c6721ee11e1ddcbc49fada63baf97ce3ec522d6d34c","sha256:f9c60be88cd8c5cf7d4cf7799c734e3e011613802516491e048964ba12fb0567"],"state_sha256":"c42a2bfb06a4dd646479d3122f178ef424b5f790b8ed129b75842c89a8dcbd3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9vgxcL+qSfIHumbWaup4uB5A2cfGf73HNeOspdM+QZCW11Nry4lLHZ7+wpT78zBs+bCKvkW3s1Gp0u1IG32EBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:10:18.592025Z","bundle_sha256":"5b8009b0d6979cef26f9f9b28c3c2d48e0454f5826118c34a4edd880f2fd66d0"}}