{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4FN4IO3EOT2CE4ROBHS6YHNOT6","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":"cc6a132c0e6b248cc9a9dd856a43b29898d29fe1bc53ccbf1bbc82fa82676a16","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-18T15:38:03Z","title_canon_sha256":"7aa4125a22ee05ccfb0bb2de1662cffa1b9dcf419d481d280fab8209660071e6"},"schema_version":"1.0","source":{"id":"2501.10799","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10799","created_at":"2026-07-05T10:02:33Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10799v1","created_at":"2026-07-05T10:02:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10799","created_at":"2026-07-05T10:02:33Z"},{"alias_kind":"pith_short_12","alias_value":"4FN4IO3EOT2C","created_at":"2026-07-05T10:02:33Z"},{"alias_kind":"pith_short_16","alias_value":"4FN4IO3EOT2CE4RO","created_at":"2026-07-05T10:02:33Z"},{"alias_kind":"pith_short_8","alias_value":"4FN4IO3E","created_at":"2026-07-05T10:02:33Z"}],"graph_snapshots":[{"event_id":"sha256:6269a4594c7c47dfaf3c1fd17dafa3e8288a5ef889181f0a9a5e568ac7fd17f4","target":"graph","created_at":"2026-07-05T10:02:33Z","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/2501.10799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have recently demonstrated remarkable success in mathematical reasoning. Despite progress in methods like chain-of-thought prompting and self-consistency sampling, these advances often focus on final correctness without ensuring that the underlying reasoning process is coherent and reliable. This paper introduces Step-KTO, a training framework that combines process-level and outcome-level binary feedback to guide LLMs toward more trustworthy reasoning trajectories. By providing binary evaluations for both the intermediate reasoning steps and the final answer, Step-","authors_text":"Arash Rahnama, Chen Zhu, Di Jin, Han Fang, Hao Ma, Jason Weston, Sainbayar Sukhbaatar, Sinong Wang, Tengyu Xu, Tianhao Wu, Yen-Ting Lin, Yuandong Tian, Yun He, Yun-Nung Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-18T15:38:03Z","title":"Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10799","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:f9d0b4150d89b81913fd52acf430309aebdab2c4ed4c3039303b96764416c49e","target":"record","created_at":"2026-07-05T10:02:33Z","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":"cc6a132c0e6b248cc9a9dd856a43b29898d29fe1bc53ccbf1bbc82fa82676a16","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-18T15:38:03Z","title_canon_sha256":"7aa4125a22ee05ccfb0bb2de1662cffa1b9dcf419d481d280fab8209660071e6"},"schema_version":"1.0","source":{"id":"2501.10799","kind":"arxiv","version":1}},"canonical_sha256":"e15bc43b6474f422722e09e5ec1dae9f9f2ffb4c22b42ef2e5a7467bd8b7b4f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e15bc43b6474f422722e09e5ec1dae9f9f2ffb4c22b42ef2e5a7467bd8b7b4f6","first_computed_at":"2026-07-05T10:02:33.463715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:33.463715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qPuvQ1DUk4ZkJdAgPl2RLL7gc0P/8cFaUtgk6nPBeG4aKEUiz+cte640lEoCfkEC/1sDyLeso8nr1S1SMExfAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:33.464156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.10799","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9d0b4150d89b81913fd52acf430309aebdab2c4ed4c3039303b96764416c49e","sha256:6269a4594c7c47dfaf3c1fd17dafa3e8288a5ef889181f0a9a5e568ac7fd17f4"],"state_sha256":"af37725c5054f5d56179c87ce24f22d7ca6b5feb4bca4e8f9c0d9e00b87f747e"}