{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZHIT4CRQBENNHMFUHHASST3YGH","short_pith_number":"pith:ZHIT4CRQ","canonical_record":{"source":{"id":"2509.21128","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-25T13:18:57Z","cross_cats_sorted":[],"title_canon_sha256":"c8254ca837dad65a9e2446188454fb13e985b67294beb6fd7c9a4f24092a0495","abstract_canon_sha256":"637ca2d069157c3799d74ddb9c46057e66d1bd63915e349a1fa72e25519b9e46"},"schema_version":"1.0"},"canonical_sha256":"c9d13e0a30091ad3b0b439c1294f7831f543d752e6e03acee3e73109bfb98569","source":{"kind":"arxiv","id":"2509.21128","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.21128","created_at":"2026-05-28T01:04:30Z"},{"alias_kind":"arxiv_version","alias_value":"2509.21128v2","created_at":"2026-05-28T01:04:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.21128","created_at":"2026-05-28T01:04:30Z"},{"alias_kind":"pith_short_12","alias_value":"ZHIT4CRQBENN","created_at":"2026-05-28T01:04:30Z"},{"alias_kind":"pith_short_16","alias_value":"ZHIT4CRQBENNHMFU","created_at":"2026-05-28T01:04:30Z"},{"alias_kind":"pith_short_8","alias_value":"ZHIT4CRQ","created_at":"2026-05-28T01:04:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZHIT4CRQBENNHMFUHHASST3YGH","target":"record","payload":{"canonical_record":{"source":{"id":"2509.21128","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-25T13:18:57Z","cross_cats_sorted":[],"title_canon_sha256":"c8254ca837dad65a9e2446188454fb13e985b67294beb6fd7c9a4f24092a0495","abstract_canon_sha256":"637ca2d069157c3799d74ddb9c46057e66d1bd63915e349a1fa72e25519b9e46"},"schema_version":"1.0"},"canonical_sha256":"c9d13e0a30091ad3b0b439c1294f7831f543d752e6e03acee3e73109bfb98569","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:30.716116Z","signature_b64":"N5Fo1vl184H/COOrGU0Bqm5CGmjUjqMCr+kFwyZQfxgt1B8bjdDeoz0iKPA2Wm7N45DG9gPcvwO/XAJfzSoVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9d13e0a30091ad3b0b439c1294f7831f543d752e6e03acee3e73109bfb98569","last_reissued_at":"2026-05-28T01:04:30.715572Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:30.715572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.21128","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fkG1JWrXMv0EE1wQ+xalDyrn7yDa0134zkJiseUMfJP5jn16CwTE6rEsQU2xp1NbDyEKYCP99eiIZBZsQtCVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:19:42.854268Z"},"content_sha256":"2680a543fc0d5c1badfea24cdbb6a9650cd13365dd596d3942fd28e52b6be1b9","schema_version":"1.0","event_id":"sha256:2680a543fc0d5c1badfea24cdbb6a9650cd13365dd596d3942fd28e52b6be1b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZHIT4CRQBENNHMFUHHASST3YGH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gouki Minegishi, Kohsei Matsutani, Shota Takashiro, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo","submitted_at":"2025-09-25T13:18:57Z","abstract_excerpt":"Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable rewards (RLVR) and supervised fine-tuning (SFT) on reasoning traces to improve their reasoning abilities. However, how these methods shape reasoning capabilities remains largely elusive. Going beyond an accuracy-based investigation of how these two components sculpt the reasoning process, this paper introduces a novel analysis framework that quantifies reasoning paths and captures their qualitative changes under each training process (with models of 1.5B, 7B, and 14B parameters on mathematical dom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.21128","kind":"arxiv","version":2},"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/2509.21128/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c8+1v7lBAQzvba2oNhi3wLFLGC1OBQ7HQU9WhSLHXEFWWzKNn0Gx+WXIDEgfvOhgXu4BX18rQ3DgottiyMWWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:19:42.854851Z"},"content_sha256":"3f75b6d7cc1e63db7117a9480ff52952fe0e5b499850ac4c58e6b663093ba051","schema_version":"1.0","event_id":"sha256:3f75b6d7cc1e63db7117a9480ff52952fe0e5b499850ac4c58e6b663093ba051"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZHIT4CRQBENNHMFUHHASST3YGH/bundle.json","state_url":"https://pith.science/pith/ZHIT4CRQBENNHMFUHHASST3YGH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZHIT4CRQBENNHMFUHHASST3YGH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T05:19:42Z","links":{"resolver":"https://pith.science/pith/ZHIT4CRQBENNHMFUHHASST3YGH","bundle":"https://pith.science/pith/ZHIT4CRQBENNHMFUHHASST3YGH/bundle.json","state":"https://pith.science/pith/ZHIT4CRQBENNHMFUHHASST3YGH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZHIT4CRQBENNHMFUHHASST3YGH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZHIT4CRQBENNHMFUHHASST3YGH","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":"637ca2d069157c3799d74ddb9c46057e66d1bd63915e349a1fa72e25519b9e46","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-25T13:18:57Z","title_canon_sha256":"c8254ca837dad65a9e2446188454fb13e985b67294beb6fd7c9a4f24092a0495"},"schema_version":"1.0","source":{"id":"2509.21128","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.21128","created_at":"2026-05-28T01:04:30Z"},{"alias_kind":"arxiv_version","alias_value":"2509.21128v2","created_at":"2026-05-28T01:04:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.21128","created_at":"2026-05-28T01:04:30Z"},{"alias_kind":"pith_short_12","alias_value":"ZHIT4CRQBENN","created_at":"2026-05-28T01:04:30Z"},{"alias_kind":"pith_short_16","alias_value":"ZHIT4CRQBENNHMFU","created_at":"2026-05-28T01:04:30Z"},{"alias_kind":"pith_short_8","alias_value":"ZHIT4CRQ","created_at":"2026-05-28T01:04:30Z"}],"graph_snapshots":[{"event_id":"sha256:3f75b6d7cc1e63db7117a9480ff52952fe0e5b499850ac4c58e6b663093ba051","target":"graph","created_at":"2026-05-28T01:04:30Z","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/2509.21128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable rewards (RLVR) and supervised fine-tuning (SFT) on reasoning traces to improve their reasoning abilities. However, how these methods shape reasoning capabilities remains largely elusive. Going beyond an accuracy-based investigation of how these two components sculpt the reasoning process, this paper introduces a novel analysis framework that quantifies reasoning paths and captures their qualitative changes under each training process (with models of 1.5B, 7B, and 14B parameters on mathematical dom","authors_text":"Gouki Minegishi, Kohsei Matsutani, Shota Takashiro, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-25T13:18:57Z","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.21128","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":"sha256:2680a543fc0d5c1badfea24cdbb6a9650cd13365dd596d3942fd28e52b6be1b9","target":"record","created_at":"2026-05-28T01:04:30Z","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":"637ca2d069157c3799d74ddb9c46057e66d1bd63915e349a1fa72e25519b9e46","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-25T13:18:57Z","title_canon_sha256":"c8254ca837dad65a9e2446188454fb13e985b67294beb6fd7c9a4f24092a0495"},"schema_version":"1.0","source":{"id":"2509.21128","kind":"arxiv","version":2}},"canonical_sha256":"c9d13e0a30091ad3b0b439c1294f7831f543d752e6e03acee3e73109bfb98569","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9d13e0a30091ad3b0b439c1294f7831f543d752e6e03acee3e73109bfb98569","first_computed_at":"2026-05-28T01:04:30.715572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:30.715572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N5Fo1vl184H/COOrGU0Bqm5CGmjUjqMCr+kFwyZQfxgt1B8bjdDeoz0iKPA2Wm7N45DG9gPcvwO/XAJfzSoVDg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:30.716116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.21128","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2680a543fc0d5c1badfea24cdbb6a9650cd13365dd596d3942fd28e52b6be1b9","sha256:3f75b6d7cc1e63db7117a9480ff52952fe0e5b499850ac4c58e6b663093ba051"],"state_sha256":"4b7ba3606f8aa69bb19e06eb06ccd1e4f4db38cabb1119421d9532109e5f381f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PwPthyqyf21FwnlFGQeafiRbZkmUOGQEW2XIN9S+Q8iJyTzKUrPLTHlGU3aEIQHdLR1atBEGIiLPvX1k+W68DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T05:19:42.858866Z","bundle_sha256":"21d3f6f751790ea6f513f95e4191f0f332229071ad2f15820b146b1ab4db0a31"}}