{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5XOEISCUBKSN7UB6RXGT4N6WTM","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":"d2bb25d46cfb2c2ab4b2c08895c49c2fc907da3d90d9529147608e56b9abb433","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-19T02:59:42Z","title_canon_sha256":"64cb6917ed6a313c42e666355fcafd0792ea8babbb8fb4a841255ce27a0437df"},"schema_version":"1.0","source":{"id":"2502.13389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13389","created_at":"2026-07-05T10:16:46Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13389v1","created_at":"2026-07-05T10:16:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13389","created_at":"2026-07-05T10:16:46Z"},{"alias_kind":"pith_short_12","alias_value":"5XOEISCUBKSN","created_at":"2026-07-05T10:16:46Z"},{"alias_kind":"pith_short_16","alias_value":"5XOEISCUBKSN7UB6","created_at":"2026-07-05T10:16:46Z"},{"alias_kind":"pith_short_8","alias_value":"5XOEISCU","created_at":"2026-07-05T10:16:46Z"}],"graph_snapshots":[{"event_id":"sha256:770a2b3256090577de096fef0b6b45ac944edbc0139facfaba573b18f2865509","target":"graph","created_at":"2026-07-05T10:16:46Z","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/2502.13389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we propose Reinforced Functional Token Tuning (RFTT), a novel reinforced fine-tuning framework that empowers Large Language Models (LLMs) with self-play learn-to-reason capabilities. Unlike prior prompt-driven reasoning efforts, RFTT embeds a rich set of learnable functional tokens (e.g., <analyze>, <verify>, <refine>) directly into the model vocabulary, enabling chain-of-thought construction with diverse human-like reasoning behaviors. Specifically, RFTT comprises two phases: (1) supervised fine-tuning performs prompt-driven tree search to obtain self-generated training data ann","authors_text":"Baisheng Lai, Dacheng Tao, Jiaxing Huang, Kongcheng Zhang, Mingli Song, Qi Yao, Shunyu Liu, Wenkai Fang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-19T02:59:42Z","title":"Reasoning with Reinforced Functional Token Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13389","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":"sha256:0180bbf082115b0595fdedf103d54bd8a4378fcc2f29fe252ac7916e74e90a86","target":"record","created_at":"2026-07-05T10:16:46Z","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":"d2bb25d46cfb2c2ab4b2c08895c49c2fc907da3d90d9529147608e56b9abb433","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-19T02:59:42Z","title_canon_sha256":"64cb6917ed6a313c42e666355fcafd0792ea8babbb8fb4a841255ce27a0437df"},"schema_version":"1.0","source":{"id":"2502.13389","kind":"arxiv","version":1}},"canonical_sha256":"eddc4448540aa4dfd03e8dcd3e37d69b14dd1fca19d33e722ca51e537d15d06d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eddc4448540aa4dfd03e8dcd3e37d69b14dd1fca19d33e722ca51e537d15d06d","first_computed_at":"2026-07-05T10:16:46.472293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:46.472293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PoVBMbCLbAEWzVA2bM5AW4bFl30dK568cKvUDaRT2z95YS+f88Zoh0GNHE7Etlk7V7QV+m3p/74F9U6gIu5rAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:46.472764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0180bbf082115b0595fdedf103d54bd8a4378fcc2f29fe252ac7916e74e90a86","sha256:770a2b3256090577de096fef0b6b45ac944edbc0139facfaba573b18f2865509"],"state_sha256":"18699c66f5cc2960cf0b06df05ea240135fdcf39b106cbf51b078c23a2b03457"}