{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RRB7USGSSORWAPDUUFL5JWIZW3","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":"08232e3a831e2815337c12031a433209ec5629c5eec34c2633ceb02357884e88","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T22:38:55Z","title_canon_sha256":"192300af55cced99f61cae9f8da3d35a0f4ff8628c83cf2ec41a0faecd325326"},"schema_version":"1.0","source":{"id":"2502.18679","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18679","created_at":"2026-07-05T11:42:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18679v3","created_at":"2026-07-05T11:42:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18679","created_at":"2026-07-05T11:42:26Z"},{"alias_kind":"pith_short_12","alias_value":"RRB7USGSSORW","created_at":"2026-07-05T11:42:26Z"},{"alias_kind":"pith_short_16","alias_value":"RRB7USGSSORWAPDU","created_at":"2026-07-05T11:42:26Z"},{"alias_kind":"pith_short_8","alias_value":"RRB7USGS","created_at":"2026-07-05T11:42:26Z"}],"graph_snapshots":[{"event_id":"sha256:8edf5145491c5c9a2e944b8461b3d2300fd7abc3e050a5c4e272bc37dfa8e491","target":"graph","created_at":"2026-07-05T11:42:26Z","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/2502.18679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs) using supervised datasets of input-output pairs. However, despite being supervised, SFT is inherently limited by its generative training objective. To address its limitations, the existing common strategy is to follow SFT with a separate phase of preference optimization (PO), which relies on either human-labeled preference data or a strong reward model to guide the learning process. In this paper, we address the limitations of SFT by exploring one of the most successful techniques in con","authors_text":"Changlong Yu, Haoming Jiang, Ilgee Hong, Liang Qiu, Siqi Guo, Tianbao Yang, Tuo Zhao, Vicente Balmaseda, Xin Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T22:38:55Z","title":"Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18679","kind":"arxiv","version":3},"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":"sha256:7abcc3f0e3dbb2e68a92e82e87b237e24aa70243879aa150f46767de0acc6634","target":"record","created_at":"2026-07-05T11:42:26Z","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":"08232e3a831e2815337c12031a433209ec5629c5eec34c2633ceb02357884e88","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T22:38:55Z","title_canon_sha256":"192300af55cced99f61cae9f8da3d35a0f4ff8628c83cf2ec41a0faecd325326"},"schema_version":"1.0","source":{"id":"2502.18679","kind":"arxiv","version":3}},"canonical_sha256":"8c43fa48d293a3603c74a157d4d919b6ff17215420efb7a4f727607c20dfe57a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c43fa48d293a3603c74a157d4d919b6ff17215420efb7a4f727607c20dfe57a","first_computed_at":"2026-07-05T11:42:26.292691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:26.292691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nWjEWe0NcO4k/BnbFlOAtz+GZxPhoaH8DUTdM+Nj52K1BFbRLcmGvPHjZV6sgddFJ55b0kZWuM2myu/qBBYJBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:26.293162Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18679","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7abcc3f0e3dbb2e68a92e82e87b237e24aa70243879aa150f46767de0acc6634","sha256:8edf5145491c5c9a2e944b8461b3d2300fd7abc3e050a5c4e272bc37dfa8e491"],"state_sha256":"95cffcc3e9e85cb18d85712434617cacf46a7979a03d656f2c4047c77051a6a5"}