{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:37I6P3OYFCFSMKVYT4QEWIHKXJ","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":"83571253e79a41fa8046eca2c4a7fd5b7c053d7d0db4c60500a9bbbe54a90c74","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-22T00:38:43Z","title_canon_sha256":"2be2e0a131213221a17634eb3b2e2d755bd5ce2630eeaf003946191e42fbacad"},"schema_version":"1.0","source":{"id":"2511.17852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.17852","created_at":"2026-05-27T01:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2511.17852v2","created_at":"2026-05-27T01:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.17852","created_at":"2026-05-27T01:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"37I6P3OYFCFS","created_at":"2026-05-27T01:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"37I6P3OYFCFSMKVY","created_at":"2026-05-27T01:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"37I6P3OY","created_at":"2026-05-27T01:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:9c35a80c77867d3ddf9dca7aea79c57a1b774c832c03839ad5998600f47fb546","target":"graph","created_at":"2026-05-27T01:04:52Z","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/2511.17852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers can acquire Chain-of-Thought (CoT) capabilities to solve complex reasoning tasks through fine-tuning. Reinforcement learning (RL) and supervised fine-tuning (SFT) are two primary approaches to this end. In this work, we specifically examine RL with process rewards and SFT for learning $k$-sparse Boolean functions with a one-layer transformer through intermediate reasoning steps akin to CoT. In particular, we consider $k$-sparse Boolean functions that can be recursively decomposed into fixed 2-sparse Boolean functions. We first analyze the learning dynamics of RL fine-tuning with p","authors_text":"Bochen Lyu, Xiaohao Cai, Yiyang Jia, Zhanxing Zhu","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-22T00:38:43Z","title":"Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But Differently"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.17852","kind":"arxiv","version":2},"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":"sha256:370273c2bc66569986192580c141da41ee3b810e3e019e9c836b4f17c1d6ebac","target":"record","created_at":"2026-05-27T01:04:52Z","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":"83571253e79a41fa8046eca2c4a7fd5b7c053d7d0db4c60500a9bbbe54a90c74","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-22T00:38:43Z","title_canon_sha256":"2be2e0a131213221a17634eb3b2e2d755bd5ce2630eeaf003946191e42fbacad"},"schema_version":"1.0","source":{"id":"2511.17852","kind":"arxiv","version":2}},"canonical_sha256":"dfd1e7edd8288b262ab89f204b20eaba60b4be89fbb853c4414a201d6c3e11eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfd1e7edd8288b262ab89f204b20eaba60b4be89fbb853c4414a201d6c3e11eb","first_computed_at":"2026-05-27T01:04:52.701750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:04:52.701750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5kq7+tSpDNVMAzjMTHzxF0wd7TE3k2XFbtUEuAiTokFup1ZI8f/pKiN+zPdO/dD+rOODXw21sdmjOY7dZPUeAg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:04:52.702947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.17852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:370273c2bc66569986192580c141da41ee3b810e3e019e9c836b4f17c1d6ebac","sha256:9c35a80c77867d3ddf9dca7aea79c57a1b774c832c03839ad5998600f47fb546"],"state_sha256":"2b4b51fa9090ca91ddd13739e67b69eb206451d5f74dee85d120532ddba4069a"}