{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KTNRXHVKNHZ5NXDXB4YRRAOEQ3","short_pith_number":"pith:KTNRXHVK","canonical_record":{"source":{"id":"2504.07080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T17:53:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f81e01b18a259f70f229f682f5514db2f4128213a5e5959201b8103e3c599c0c","abstract_canon_sha256":"e9f1824a53d1866c216844a88f1f99b09c7a58a287ff3e3ad6e26b41010f42bd"},"schema_version":"1.0"},"canonical_sha256":"54db1b9eaa69f3d6dc770f311881c486c9db9145ba37da0db41fc1258c76bb8d","source":{"kind":"arxiv","id":"2504.07080","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07080","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07080v1","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07080","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"pith_short_12","alias_value":"KTNRXHVKNHZ5","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"pith_short_16","alias_value":"KTNRXHVKNHZ5NXDX","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"pith_short_8","alias_value":"KTNRXHVK","created_at":"2026-07-05T10:46:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KTNRXHVKNHZ5NXDXB4YRRAOEQ3","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T17:53:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f81e01b18a259f70f229f682f5514db2f4128213a5e5959201b8103e3c599c0c","abstract_canon_sha256":"e9f1824a53d1866c216844a88f1f99b09c7a58a287ff3e3ad6e26b41010f42bd"},"schema_version":"1.0"},"canonical_sha256":"54db1b9eaa69f3d6dc770f311881c486c9db9145ba37da0db41fc1258c76bb8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:50.936407Z","signature_b64":"EmS8kHjDZ+WgRqTE2dcvKL+odVI+ijLuoYm739NP3yjp3F11xX8L/vF6UKVmuk7NW5HvQqXMIVLIQTC2It0WDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54db1b9eaa69f3d6dc770f311881c486c9db9145ba37da0db41fc1258c76bb8d","last_reissued_at":"2026-07-05T10:46:50.935864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:50.935864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07080","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":"2026-07-05T10:46:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aimBkyroRfvYfs+P6Q4Ifir7Ix4bnHyhGVOXVmTBypHRXJqbzooIg/78xYhavabdX/1wcs0vqO4277PQbLiyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:17:05.516732Z"},"content_sha256":"cd3c1013cf38602b81855662647e06d7437e55bc8e8aa6496a4548bd3dcda157","schema_version":"1.0","event_id":"sha256:cd3c1013cf38602b81855662647e06d7437e55bc8e8aa6496a4548bd3dcda157"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KTNRXHVKNHZ5NXDXB4YRRAOEQ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeduCE: Deductive Consistency as a Framework to Evaluate LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amit Sharma, Atharva Pandey, Kshitij Dubey, Rahul Sharma","submitted_at":"2025-04-09T17:53:55Z","abstract_excerpt":"Despite great performance on Olympiad-level reasoning problems, frontier large language models can still struggle on high school math when presented with novel problems outside standard benchmarks. Going beyond final accuracy, we propose a deductive consistency metric to analyze chain-of-thought output from language models (LMs).Formally, deductive reasoning involves two subtasks: understanding a set of input premises and inferring the conclusions that follow from them. The proposed metric studies LMs' performance on these subtasks, with the goal of explaining LMs' reasoning errors on novel pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07080","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/2504.07080/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":"2026-07-05T10:46:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XabF55U848dc+BPzeIdHLG3df0m/M3Mu8mHyKDOhH0f5nFhDKSrx90lqqk4dhi/IdrVSqlEICgAzYQdHuV8FBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:17:05.517236Z"},"content_sha256":"410bc269dff1856587b2114976f2fd9ffadcff54eccfb463b3c95e6550c3bff0","schema_version":"1.0","event_id":"sha256:410bc269dff1856587b2114976f2fd9ffadcff54eccfb463b3c95e6550c3bff0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KTNRXHVKNHZ5NXDXB4YRRAOEQ3/bundle.json","state_url":"https://pith.science/pith/KTNRXHVKNHZ5NXDXB4YRRAOEQ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KTNRXHVKNHZ5NXDXB4YRRAOEQ3/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":"2026-08-23T17:17:05Z","links":{"resolver":"https://pith.science/pith/KTNRXHVKNHZ5NXDXB4YRRAOEQ3","bundle":"https://pith.science/pith/KTNRXHVKNHZ5NXDXB4YRRAOEQ3/bundle.json","state":"https://pith.science/pith/KTNRXHVKNHZ5NXDXB4YRRAOEQ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KTNRXHVKNHZ5NXDXB4YRRAOEQ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KTNRXHVKNHZ5NXDXB4YRRAOEQ3","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":"e9f1824a53d1866c216844a88f1f99b09c7a58a287ff3e3ad6e26b41010f42bd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T17:53:55Z","title_canon_sha256":"f81e01b18a259f70f229f682f5514db2f4128213a5e5959201b8103e3c599c0c"},"schema_version":"1.0","source":{"id":"2504.07080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07080","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07080v1","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07080","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"pith_short_12","alias_value":"KTNRXHVKNHZ5","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"pith_short_16","alias_value":"KTNRXHVKNHZ5NXDX","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"pith_short_8","alias_value":"KTNRXHVK","created_at":"2026-07-05T10:46:50Z"}],"graph_snapshots":[{"event_id":"sha256:410bc269dff1856587b2114976f2fd9ffadcff54eccfb463b3c95e6550c3bff0","target":"graph","created_at":"2026-07-05T10:46:50Z","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/2504.07080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite great performance on Olympiad-level reasoning problems, frontier large language models can still struggle on high school math when presented with novel problems outside standard benchmarks. Going beyond final accuracy, we propose a deductive consistency metric to analyze chain-of-thought output from language models (LMs).Formally, deductive reasoning involves two subtasks: understanding a set of input premises and inferring the conclusions that follow from them. The proposed metric studies LMs' performance on these subtasks, with the goal of explaining LMs' reasoning errors on novel pr","authors_text":"Amit Sharma, Atharva Pandey, Kshitij Dubey, Rahul Sharma","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T17:53:55Z","title":"DeduCE: Deductive Consistency as a Framework to Evaluate LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07080","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:cd3c1013cf38602b81855662647e06d7437e55bc8e8aa6496a4548bd3dcda157","target":"record","created_at":"2026-07-05T10:46:50Z","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":"e9f1824a53d1866c216844a88f1f99b09c7a58a287ff3e3ad6e26b41010f42bd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T17:53:55Z","title_canon_sha256":"f81e01b18a259f70f229f682f5514db2f4128213a5e5959201b8103e3c599c0c"},"schema_version":"1.0","source":{"id":"2504.07080","kind":"arxiv","version":1}},"canonical_sha256":"54db1b9eaa69f3d6dc770f311881c486c9db9145ba37da0db41fc1258c76bb8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54db1b9eaa69f3d6dc770f311881c486c9db9145ba37da0db41fc1258c76bb8d","first_computed_at":"2026-07-05T10:46:50.935864Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:50.935864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EmS8kHjDZ+WgRqTE2dcvKL+odVI+ijLuoYm739NP3yjp3F11xX8L/vF6UKVmuk7NW5HvQqXMIVLIQTC2It0WDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:50.936407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd3c1013cf38602b81855662647e06d7437e55bc8e8aa6496a4548bd3dcda157","sha256:410bc269dff1856587b2114976f2fd9ffadcff54eccfb463b3c95e6550c3bff0"],"state_sha256":"04bda007faf94e56fd1ee9252a2c60ea4d26c709a20acdefe6e64a3a1b7f885c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DZ9pJNlnRCHHqiCPyxliX9mpWAJuA1atUGgBeNaIP4U2hfXNaF0IOm/e+Y25RwlalG3M4Jb3oPfbBtfjIAuVCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T17:17:05.520855Z","bundle_sha256":"373947984b1d7fbe0af79551e7452f4f84380d9f83252afe5860ae43870ea9e9"}}