{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KT7XV7FXQRWJBT6JYSNL64UXED","short_pith_number":"pith:KT7XV7FX","canonical_record":{"source":{"id":"2502.13723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T13:51:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d65228d766e31c008a9d08b8301abb277648b35892e817152a90009f25d17b5","abstract_canon_sha256":"6a1189bf203bef2a00df997bf93d0bc6bf72b98e3aaca413a5a6e8c65f870816"},"schema_version":"1.0"},"canonical_sha256":"54ff7afcb7846c90cfc9c49abf729720fd9c2e75d6a855d0dbc4359eb3e03895","source":{"kind":"arxiv","id":"2502.13723","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13723","created_at":"2026-07-05T10:16:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13723v1","created_at":"2026-07-05T10:16:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13723","created_at":"2026-07-05T10:16:51Z"},{"alias_kind":"pith_short_12","alias_value":"KT7XV7FXQRWJ","created_at":"2026-07-05T10:16:51Z"},{"alias_kind":"pith_short_16","alias_value":"KT7XV7FXQRWJBT6J","created_at":"2026-07-05T10:16:51Z"},{"alias_kind":"pith_short_8","alias_value":"KT7XV7FX","created_at":"2026-07-05T10:16:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KT7XV7FXQRWJBT6JYSNL64UXED","target":"record","payload":{"canonical_record":{"source":{"id":"2502.13723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T13:51:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d65228d766e31c008a9d08b8301abb277648b35892e817152a90009f25d17b5","abstract_canon_sha256":"6a1189bf203bef2a00df997bf93d0bc6bf72b98e3aaca413a5a6e8c65f870816"},"schema_version":"1.0"},"canonical_sha256":"54ff7afcb7846c90cfc9c49abf729720fd9c2e75d6a855d0dbc4359eb3e03895","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:51.903972Z","signature_b64":"yFuqLFAb5DBq9OwHhsv2fNYSgg3nW+VHVNE/XWhxeWl2+5LdMDv3nXr75LO0MIF2lANuqdBsiVBfT4F3uGTUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54ff7afcb7846c90cfc9c49abf729720fd9c2e75d6a855d0dbc4359eb3e03895","last_reissued_at":"2026-07-05T10:16:51.903455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:51.903455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.13723","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":"2026-07-05T10:16:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IW1KhXeBWm+Abdc0Ssp9ep84EdPcxAOVus76goJdi2Ujy6BCfMVDZbaNjz5NerNTfJQ/ADjLMjkn5qi4+pRyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:05:51.811612Z"},"content_sha256":"1c453f3cd3e9102cfbabe503a8b694a5b8a60bea2399b9dd2b3ab0785960f2b2","schema_version":"1.0","event_id":"sha256:1c453f3cd3e9102cfbabe503a8b694a5b8a60bea2399b9dd2b3ab0785960f2b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KT7XV7FXQRWJBT6JYSNL64UXED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangsheng Bao, Han Cui, Hongbo Zhang, Jun Wang, Linyi Yang, Yue Zhang","submitted_at":"2025-02-19T13:51:05Z","abstract_excerpt":"We introduce Direct Value Optimization (DVO), an innovative reinforcement learning framework for enhancing large language models in complex reasoning tasks. Unlike traditional methods relying on preference labels, DVO utilizes value signals at individual reasoning steps, optimizing models via a mean squared error loss. The key benefit of DVO lies in its fine-grained supervision, circumventing the need for labor-intensive human annotations. Target values within the DVO are estimated using either Monte Carlo Tree Search or an outcome value model. Our empirical analysis on both mathematical and c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13723","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/2502.13723/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":"2026-07-05T10:16:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KxPve3nrrzE44LVWoUYJOmeIV0dKnTmrCneazyUqZ6agCPI8g9jwdceJtJ+88qh3ckvzTSN2tr/JmWrl2h81AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:05:51.812093Z"},"content_sha256":"0b873916b5b63e65dd6fa35463fb3d5ced7b66ae146f0923a1c0bafac5ba6f3d","schema_version":"1.0","event_id":"sha256:0b873916b5b63e65dd6fa35463fb3d5ced7b66ae146f0923a1c0bafac5ba6f3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KT7XV7FXQRWJBT6JYSNL64UXED/bundle.json","state_url":"https://pith.science/pith/KT7XV7FXQRWJBT6JYSNL64UXED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KT7XV7FXQRWJBT6JYSNL64UXED/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":"2026-08-05T04:05:51Z","links":{"resolver":"https://pith.science/pith/KT7XV7FXQRWJBT6JYSNL64UXED","bundle":"https://pith.science/pith/KT7XV7FXQRWJBT6JYSNL64UXED/bundle.json","state":"https://pith.science/pith/KT7XV7FXQRWJBT6JYSNL64UXED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KT7XV7FXQRWJBT6JYSNL64UXED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KT7XV7FXQRWJBT6JYSNL64UXED","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":"6a1189bf203bef2a00df997bf93d0bc6bf72b98e3aaca413a5a6e8c65f870816","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T13:51:05Z","title_canon_sha256":"0d65228d766e31c008a9d08b8301abb277648b35892e817152a90009f25d17b5"},"schema_version":"1.0","source":{"id":"2502.13723","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13723","created_at":"2026-07-05T10:16:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13723v1","created_at":"2026-07-05T10:16:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13723","created_at":"2026-07-05T10:16:51Z"},{"alias_kind":"pith_short_12","alias_value":"KT7XV7FXQRWJ","created_at":"2026-07-05T10:16:51Z"},{"alias_kind":"pith_short_16","alias_value":"KT7XV7FXQRWJBT6J","created_at":"2026-07-05T10:16:51Z"},{"alias_kind":"pith_short_8","alias_value":"KT7XV7FX","created_at":"2026-07-05T10:16:51Z"}],"graph_snapshots":[{"event_id":"sha256:0b873916b5b63e65dd6fa35463fb3d5ced7b66ae146f0923a1c0bafac5ba6f3d","target":"graph","created_at":"2026-07-05T10:16:51Z","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/2502.13723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Direct Value Optimization (DVO), an innovative reinforcement learning framework for enhancing large language models in complex reasoning tasks. Unlike traditional methods relying on preference labels, DVO utilizes value signals at individual reasoning steps, optimizing models via a mean squared error loss. The key benefit of DVO lies in its fine-grained supervision, circumventing the need for labor-intensive human annotations. Target values within the DVO are estimated using either Monte Carlo Tree Search or an outcome value model. Our empirical analysis on both mathematical and c","authors_text":"Guangsheng Bao, Han Cui, Hongbo Zhang, Jun Wang, Linyi Yang, Yue Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T13:51:05Z","title":"Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13723","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":"sha256:1c453f3cd3e9102cfbabe503a8b694a5b8a60bea2399b9dd2b3ab0785960f2b2","target":"record","created_at":"2026-07-05T10:16:51Z","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":"6a1189bf203bef2a00df997bf93d0bc6bf72b98e3aaca413a5a6e8c65f870816","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T13:51:05Z","title_canon_sha256":"0d65228d766e31c008a9d08b8301abb277648b35892e817152a90009f25d17b5"},"schema_version":"1.0","source":{"id":"2502.13723","kind":"arxiv","version":1}},"canonical_sha256":"54ff7afcb7846c90cfc9c49abf729720fd9c2e75d6a855d0dbc4359eb3e03895","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54ff7afcb7846c90cfc9c49abf729720fd9c2e75d6a855d0dbc4359eb3e03895","first_computed_at":"2026-07-05T10:16:51.903455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:51.903455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yFuqLFAb5DBq9OwHhsv2fNYSgg3nW+VHVNE/XWhxeWl2+5LdMDv3nXr75LO0MIF2lANuqdBsiVBfT4F3uGTUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:51.903972Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13723","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c453f3cd3e9102cfbabe503a8b694a5b8a60bea2399b9dd2b3ab0785960f2b2","sha256:0b873916b5b63e65dd6fa35463fb3d5ced7b66ae146f0923a1c0bafac5ba6f3d"],"state_sha256":"c3b221a513453979ac8ff906753605b88e526baa056c9acd9143b1bd0ff094c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U8jPYxEfXsmnfAMu/RxL9qhzcKu7T7JZ4aeNnt7MLYtIZIIkrJ56f/x1lQ6Ft/TM/t/tX2juNIzXyYh/HBx3DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:05:51.815213Z","bundle_sha256":"21ee51d29b072d6de0af7df2d3b96677932234db98ce7f217497eb400f4c21c1"}}