{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KIGGXE2WS5UTX5J7ZDIFOTMBH5","short_pith_number":"pith:KIGGXE2W","canonical_record":{"source":{"id":"2304.10703","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-21T02:19:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0df571846e81aff6ab51116115a7476ec86ad8b4322728db23655c850cfdc640","abstract_canon_sha256":"11f23fce1a240c761a8f038ac99d4aee4598c4c88fda4d05b76d51f1b36f0742"},"schema_version":"1.0"},"canonical_sha256":"520c6b935697693bf53fc8d0574d813f426adede1cb8e373692fc0a160c184ee","source":{"kind":"arxiv","id":"2304.10703","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.10703","created_at":"2026-07-05T07:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"2304.10703v2","created_at":"2026-07-05T07:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10703","created_at":"2026-07-05T07:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"KIGGXE2WS5UT","created_at":"2026-07-05T07:18:57Z"},{"alias_kind":"pith_short_16","alias_value":"KIGGXE2WS5UTX5J7","created_at":"2026-07-05T07:18:57Z"},{"alias_kind":"pith_short_8","alias_value":"KIGGXE2W","created_at":"2026-07-05T07:18:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KIGGXE2WS5UTX5J7ZDIFOTMBH5","target":"record","payload":{"canonical_record":{"source":{"id":"2304.10703","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-21T02:19:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0df571846e81aff6ab51116115a7476ec86ad8b4322728db23655c850cfdc640","abstract_canon_sha256":"11f23fce1a240c761a8f038ac99d4aee4598c4c88fda4d05b76d51f1b36f0742"},"schema_version":"1.0"},"canonical_sha256":"520c6b935697693bf53fc8d0574d813f426adede1cb8e373692fc0a160c184ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:57.327340Z","signature_b64":"B4TRG3z9TOYHR0iu0uUiU13J+0n+m2MnjUX5NoV4l0UKMCz6isaGuWFtgGU0RoLzRc2UbOikvBL41JvAz+9OCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"520c6b935697693bf53fc8d0574d813f426adede1cb8e373692fc0a160c184ee","last_reissued_at":"2026-07-05T07:18:57.326841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:57.326841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.10703","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":"2026-07-05T07:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iNRINQX1qUaU/JEZ5QU9+bQZ5r81w+AKWF6MDrYHsay80v73crgqDV+sXRbGt9lQ+AuuRG/ZLZ90GJ9TEQvrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:34:42.601217Z"},"content_sha256":"41afad16bf06fe660fe1b465f431948aad4a9190bd6dc4161077f38a7a5541f1","schema_version":"1.0","event_id":"sha256:41afad16bf06fe660fe1b465f431948aad4a9190bd6dc4161077f38a7a5541f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KIGGXE2WS5UTX5J7ZDIFOTMBH5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Archiki Prasad, Mohit Bansal, Swarnadeep Saha, Xiang Zhou","submitted_at":"2023-04-21T02:19:06Z","abstract_excerpt":"Multi-step reasoning ability is fundamental to many natural language tasks, yet it is unclear what constitutes a good reasoning chain and how to evaluate them. Most existing methods focus solely on whether the reasoning chain leads to the correct conclusion, but this answer-oriented view may confound reasoning quality with other spurious shortcuts to predict the answer. To bridge this gap, we evaluate reasoning chains by viewing them as informal proofs that derive the final answer. Specifically, we propose ReCEval (Reasoning Chain Evaluation), a framework that evaluates reasoning chains via tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10703","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/2304.10703/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":"2026-07-05T07:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v6/9cQ9qY93hESxZ+bRi6sC3AlUx+ey+0N9dxkTUMaGdO92UmFED6bOLPdv3Ec3NKffGbBmB27CQ2rcgOatUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:34:42.601795Z"},"content_sha256":"79c054f675f732fb57ab3b12504df284e1eec9c6347a3cf2c402c6ff74037524","schema_version":"1.0","event_id":"sha256:79c054f675f732fb57ab3b12504df284e1eec9c6347a3cf2c402c6ff74037524"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KIGGXE2WS5UTX5J7ZDIFOTMBH5/bundle.json","state_url":"https://pith.science/pith/KIGGXE2WS5UTX5J7ZDIFOTMBH5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KIGGXE2WS5UTX5J7ZDIFOTMBH5/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":"2026-08-08T09:34:42Z","links":{"resolver":"https://pith.science/pith/KIGGXE2WS5UTX5J7ZDIFOTMBH5","bundle":"https://pith.science/pith/KIGGXE2WS5UTX5J7ZDIFOTMBH5/bundle.json","state":"https://pith.science/pith/KIGGXE2WS5UTX5J7ZDIFOTMBH5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KIGGXE2WS5UTX5J7ZDIFOTMBH5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KIGGXE2WS5UTX5J7ZDIFOTMBH5","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":"11f23fce1a240c761a8f038ac99d4aee4598c4c88fda4d05b76d51f1b36f0742","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-21T02:19:06Z","title_canon_sha256":"0df571846e81aff6ab51116115a7476ec86ad8b4322728db23655c850cfdc640"},"schema_version":"1.0","source":{"id":"2304.10703","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.10703","created_at":"2026-07-05T07:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"2304.10703v2","created_at":"2026-07-05T07:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10703","created_at":"2026-07-05T07:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"KIGGXE2WS5UT","created_at":"2026-07-05T07:18:57Z"},{"alias_kind":"pith_short_16","alias_value":"KIGGXE2WS5UTX5J7","created_at":"2026-07-05T07:18:57Z"},{"alias_kind":"pith_short_8","alias_value":"KIGGXE2W","created_at":"2026-07-05T07:18:57Z"}],"graph_snapshots":[{"event_id":"sha256:79c054f675f732fb57ab3b12504df284e1eec9c6347a3cf2c402c6ff74037524","target":"graph","created_at":"2026-07-05T07:18:57Z","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/2304.10703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-step reasoning ability is fundamental to many natural language tasks, yet it is unclear what constitutes a good reasoning chain and how to evaluate them. Most existing methods focus solely on whether the reasoning chain leads to the correct conclusion, but this answer-oriented view may confound reasoning quality with other spurious shortcuts to predict the answer. To bridge this gap, we evaluate reasoning chains by viewing them as informal proofs that derive the final answer. Specifically, we propose ReCEval (Reasoning Chain Evaluation), a framework that evaluates reasoning chains via tw","authors_text":"Archiki Prasad, Mohit Bansal, Swarnadeep Saha, Xiang Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-21T02:19:06Z","title":"ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10703","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":"sha256:41afad16bf06fe660fe1b465f431948aad4a9190bd6dc4161077f38a7a5541f1","target":"record","created_at":"2026-07-05T07:18:57Z","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":"11f23fce1a240c761a8f038ac99d4aee4598c4c88fda4d05b76d51f1b36f0742","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-21T02:19:06Z","title_canon_sha256":"0df571846e81aff6ab51116115a7476ec86ad8b4322728db23655c850cfdc640"},"schema_version":"1.0","source":{"id":"2304.10703","kind":"arxiv","version":2}},"canonical_sha256":"520c6b935697693bf53fc8d0574d813f426adede1cb8e373692fc0a160c184ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"520c6b935697693bf53fc8d0574d813f426adede1cb8e373692fc0a160c184ee","first_computed_at":"2026-07-05T07:18:57.326841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:57.326841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B4TRG3z9TOYHR0iu0uUiU13J+0n+m2MnjUX5NoV4l0UKMCz6isaGuWFtgGU0RoLzRc2UbOikvBL41JvAz+9OCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:57.327340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.10703","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41afad16bf06fe660fe1b465f431948aad4a9190bd6dc4161077f38a7a5541f1","sha256:79c054f675f732fb57ab3b12504df284e1eec9c6347a3cf2c402c6ff74037524"],"state_sha256":"46a54833dc8b25f3baa62f172722473b6ab369a8f2ee4ae9938ec82c65509299"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GSHM5AE65mBAG+wDWpBeqlhX66mo10+m4ZgEMinMBFOXh5ge35m6oor8wBPd3t/ImUHg/s68yIta2gHKptU2Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:34:42.606901Z","bundle_sha256":"074d1dda0020f813867aa3ff1f8634b33915e37b9328a22aacbfe8f0ac26e604"}}