{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WTCXU5CRVTKT7W5BYOBPZ7S6CI","short_pith_number":"pith:WTCXU5CR","canonical_record":{"source":{"id":"2505.17988","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T14:55:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"858c22a5087b6a0d69bba40ba79f90130883359f59b4a0c39c249d6e6e8885a9","abstract_canon_sha256":"d91a0b7d24722712901f4630944614e0f8e9b5e73385dec2c26067281c7618bb"},"schema_version":"1.0"},"canonical_sha256":"b4c57a7451acd53fdba1c382fcfe5e1237a0ffbe160203e9c3c6177b730027f0","source":{"kind":"arxiv","id":"2505.17988","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17988","created_at":"2026-07-05T11:48:49Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17988v3","created_at":"2026-07-05T11:48:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17988","created_at":"2026-07-05T11:48:49Z"},{"alias_kind":"pith_short_12","alias_value":"WTCXU5CRVTKT","created_at":"2026-07-05T11:48:49Z"},{"alias_kind":"pith_short_16","alias_value":"WTCXU5CRVTKT7W5B","created_at":"2026-07-05T11:48:49Z"},{"alias_kind":"pith_short_8","alias_value":"WTCXU5CR","created_at":"2026-07-05T11:48:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WTCXU5CRVTKT7W5BYOBPZ7S6CI","target":"record","payload":{"canonical_record":{"source":{"id":"2505.17988","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T14:55:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"858c22a5087b6a0d69bba40ba79f90130883359f59b4a0c39c249d6e6e8885a9","abstract_canon_sha256":"d91a0b7d24722712901f4630944614e0f8e9b5e73385dec2c26067281c7618bb"},"schema_version":"1.0"},"canonical_sha256":"b4c57a7451acd53fdba1c382fcfe5e1237a0ffbe160203e9c3c6177b730027f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:49.190497Z","signature_b64":"C078/kguGuFE5BgsOLq48ck4B0DXYfe1objJzfvvGC0DNbbNV4JIx4XMWQC8T2nTrlR7oecXCkYSWu9kpGMDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4c57a7451acd53fdba1c382fcfe5e1237a0ffbe160203e9c3c6177b730027f0","last_reissued_at":"2026-07-05T11:48:49.189880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:49.189880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.17988","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:48:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIn9WrSiGuMso11hjRMsH+Iw1PiBnSX03EU8R/q73hP4Vku++ARA8q4VWHmI2d/jNG/W/P0tiXfhuCQZjfpgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:52:34.079268Z"},"content_sha256":"8c589853ab4202aa669440939aa33477fed0a792343c2d154df2044c31ec3193","schema_version":"1.0","event_id":"sha256:8c589853ab4202aa669440939aa33477fed0a792343c2d154df2044c31ec3193"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WTCXU5CRVTKT7W5BYOBPZ7S6CI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiandong Gao, Ji Wu, Yutong Chen","submitted_at":"2025-05-23T14:55:22Z","abstract_excerpt":"R1-style Reinforcement Learning (RL) significantly enhances Large Language Models' reasoning capabilities, yet the mechanism behind rule-based RL remains unclear. We found that small-scale SFT has substantial influence on RL but shows poor efficiency. To explain our observations, we propose an analytical framework and compare the efficiency of SFT and RL by measuring \\textbf{sample effect}. Our hypothetical analysis shows the potential to improve SFT efficiency. Guided by our analysis, we propose \\textbf{Re-distillation}, a technique that aims to boost the effectiveness of small-scale distilla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17988","kind":"arxiv","version":3},"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/2505.17988/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":"2026-07-05T11:48:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t4pbFb0yxjiIvHMKh7s5FnFSyrUlvYKqACws88YrxbQKaIu0K4S/iHsoE5MOS1y4ajSLTKkKmQQjB1Kw1M8uAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:52:34.079801Z"},"content_sha256":"febcac7ce7383c42e43aaf77d600708fdc564d296b7340be8608c436d21292ca","schema_version":"1.0","event_id":"sha256:febcac7ce7383c42e43aaf77d600708fdc564d296b7340be8608c436d21292ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTCXU5CRVTKT7W5BYOBPZ7S6CI/bundle.json","state_url":"https://pith.science/pith/WTCXU5CRVTKT7W5BYOBPZ7S6CI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTCXU5CRVTKT7W5BYOBPZ7S6CI/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":"2026-08-06T10:52:34Z","links":{"resolver":"https://pith.science/pith/WTCXU5CRVTKT7W5BYOBPZ7S6CI","bundle":"https://pith.science/pith/WTCXU5CRVTKT7W5BYOBPZ7S6CI/bundle.json","state":"https://pith.science/pith/WTCXU5CRVTKT7W5BYOBPZ7S6CI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTCXU5CRVTKT7W5BYOBPZ7S6CI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WTCXU5CRVTKT7W5BYOBPZ7S6CI","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":"d91a0b7d24722712901f4630944614e0f8e9b5e73385dec2c26067281c7618bb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T14:55:22Z","title_canon_sha256":"858c22a5087b6a0d69bba40ba79f90130883359f59b4a0c39c249d6e6e8885a9"},"schema_version":"1.0","source":{"id":"2505.17988","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17988","created_at":"2026-07-05T11:48:49Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17988v3","created_at":"2026-07-05T11:48:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17988","created_at":"2026-07-05T11:48:49Z"},{"alias_kind":"pith_short_12","alias_value":"WTCXU5CRVTKT","created_at":"2026-07-05T11:48:49Z"},{"alias_kind":"pith_short_16","alias_value":"WTCXU5CRVTKT7W5B","created_at":"2026-07-05T11:48:49Z"},{"alias_kind":"pith_short_8","alias_value":"WTCXU5CR","created_at":"2026-07-05T11:48:49Z"}],"graph_snapshots":[{"event_id":"sha256:febcac7ce7383c42e43aaf77d600708fdc564d296b7340be8608c436d21292ca","target":"graph","created_at":"2026-07-05T11:48:49Z","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/2505.17988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"R1-style Reinforcement Learning (RL) significantly enhances Large Language Models' reasoning capabilities, yet the mechanism behind rule-based RL remains unclear. We found that small-scale SFT has substantial influence on RL but shows poor efficiency. To explain our observations, we propose an analytical framework and compare the efficiency of SFT and RL by measuring \\textbf{sample effect}. Our hypothetical analysis shows the potential to improve SFT efficiency. Guided by our analysis, we propose \\textbf{Re-distillation}, a technique that aims to boost the effectiveness of small-scale distilla","authors_text":"Jiandong Gao, Ji Wu, Yutong Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T14:55:22Z","title":"Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17988","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":"sha256:8c589853ab4202aa669440939aa33477fed0a792343c2d154df2044c31ec3193","target":"record","created_at":"2026-07-05T11:48:49Z","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":"d91a0b7d24722712901f4630944614e0f8e9b5e73385dec2c26067281c7618bb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T14:55:22Z","title_canon_sha256":"858c22a5087b6a0d69bba40ba79f90130883359f59b4a0c39c249d6e6e8885a9"},"schema_version":"1.0","source":{"id":"2505.17988","kind":"arxiv","version":3}},"canonical_sha256":"b4c57a7451acd53fdba1c382fcfe5e1237a0ffbe160203e9c3c6177b730027f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4c57a7451acd53fdba1c382fcfe5e1237a0ffbe160203e9c3c6177b730027f0","first_computed_at":"2026-07-05T11:48:49.189880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:49.189880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C078/kguGuFE5BgsOLq48ck4B0DXYfe1objJzfvvGC0DNbbNV4JIx4XMWQC8T2nTrlR7oecXCkYSWu9kpGMDDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:49.190497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17988","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c589853ab4202aa669440939aa33477fed0a792343c2d154df2044c31ec3193","sha256:febcac7ce7383c42e43aaf77d600708fdc564d296b7340be8608c436d21292ca"],"state_sha256":"5d0a85d37e653d460569107a63be2742697c0ece8d811e78109b8545667273d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PgcpNN3w/gnXlDHlfo83LScMdD++lddCWn0BCkKGWLIph585rQxPCUXgJ5Ef9Sz0wTohxCkSvxXw1jDWGAuACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T10:52:34.085413Z","bundle_sha256":"d94968b923a6b11daaa4fb7858336456892bb77140dfaaf128ba37f85ca5f090"}}