{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4EXZA6A32OVRRPG3XB2YOZ7PS7","short_pith_number":"pith:4EXZA6A3","schema_version":"1.0","canonical_sha256":"e12f90781bd3ab18bcdbb8758767ef97fbfc55736b24d044778ff5f71764779c","source":{"kind":"arxiv","id":"2407.00390","version":1},"attestation_state":"computed","paper":{"title":"Advancing Process Verification for Large Language Models via Tree-Based Preference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mingqian He, Weiming Lu, Wenqi Zhang, Yongliang Shen, Zeqi Tan","submitted_at":"2024-06-29T10:09:49Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable potential in handling complex reasoning tasks by generating step-by-step rationales.Some methods have proven effective in boosting accuracy by introducing extra verifiers to assess these paths. However, existing verifiers, typically trained on binary-labeled reasoning paths, fail to fully utilize the relative merits of intermediate steps, thereby limiting the effectiveness of the feedback provided. To overcome this limitation, we propose Tree-based Preference Learning Verifier (Tree-PLV), a novel approach that constructs reasoning trees"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.00390","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T10:09:49Z","cross_cats_sorted":[],"title_canon_sha256":"e94e4379d6cf556515a66ddc7045353e3e0a064a9e14e5da04d881f21f86061f","abstract_canon_sha256":"131279d3b74e965f9db6e81b694ba7bc929bf9292c704a72a4305fd4dda6e846"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:19.136478Z","signature_b64":"RErAc36yRB4tWw10CF+CuXkKpSNmBOzgDTvfWL2ijkRXsa9OsTdtz4/yHyIzTooO13uVlguceEhyJe+ZkpHBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e12f90781bd3ab18bcdbb8758767ef97fbfc55736b24d044778ff5f71764779c","last_reissued_at":"2026-07-05T08:38:19.135761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:19.135761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Process Verification for Large Language Models via Tree-Based Preference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mingqian He, Weiming Lu, Wenqi Zhang, Yongliang Shen, Zeqi Tan","submitted_at":"2024-06-29T10:09:49Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable potential in handling complex reasoning tasks by generating step-by-step rationales.Some methods have proven effective in boosting accuracy by introducing extra verifiers to assess these paths. However, existing verifiers, typically trained on binary-labeled reasoning paths, fail to fully utilize the relative merits of intermediate steps, thereby limiting the effectiveness of the feedback provided. To overcome this limitation, we propose Tree-based Preference Learning Verifier (Tree-PLV), a novel approach that constructs reasoning trees"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00390","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/2407.00390/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.00390","created_at":"2026-07-05T08:38:19.135842+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00390v1","created_at":"2026-07-05T08:38:19.135842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00390","created_at":"2026-07-05T08:38:19.135842+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EXZA6A32OVR","created_at":"2026-07-05T08:38:19.135842+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EXZA6A32OVRRPG3","created_at":"2026-07-05T08:38:19.135842+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EXZA6A3","created_at":"2026-07-05T08:38:19.135842+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15118","citing_title":"Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4EXZA6A32OVRRPG3XB2YOZ7PS7","json":"https://pith.science/pith/4EXZA6A32OVRRPG3XB2YOZ7PS7.json","graph_json":"https://pith.science/api/pith-number/4EXZA6A32OVRRPG3XB2YOZ7PS7/graph.json","events_json":"https://pith.science/api/pith-number/4EXZA6A32OVRRPG3XB2YOZ7PS7/events.json","paper":"https://pith.science/paper/4EXZA6A3"},"agent_actions":{"view_html":"https://pith.science/pith/4EXZA6A32OVRRPG3XB2YOZ7PS7","download_json":"https://pith.science/pith/4EXZA6A32OVRRPG3XB2YOZ7PS7.json","view_paper":"https://pith.science/paper/4EXZA6A3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00390&json=true","fetch_graph":"https://pith.science/api/pith-number/4EXZA6A32OVRRPG3XB2YOZ7PS7/graph.json","fetch_events":"https://pith.science/api/pith-number/4EXZA6A32OVRRPG3XB2YOZ7PS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EXZA6A32OVRRPG3XB2YOZ7PS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EXZA6A32OVRRPG3XB2YOZ7PS7/action/storage_attestation","attest_author":"https://pith.science/pith/4EXZA6A32OVRRPG3XB2YOZ7PS7/action/author_attestation","sign_citation":"https://pith.science/pith/4EXZA6A32OVRRPG3XB2YOZ7PS7/action/citation_signature","submit_replication":"https://pith.science/pith/4EXZA6A32OVRRPG3XB2YOZ7PS7/action/replication_record"}},"created_at":"2026-07-05T08:38:19.135842+00:00","updated_at":"2026-07-05T08:38:19.135842+00:00"}