{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QYW44JPAOHLYS3Z5UF6RBL66ZU","short_pith_number":"pith:QYW44JPA","canonical_record":{"source":{"id":"2606.09932","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T17:58:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d513cffe39174c822af1141872cb6420dde423d5dbe0e545f0e9353b992c9cfd","abstract_canon_sha256":"effc05567b5e4034ad49d515f5c0c18c0816159165cbfbe91753ff56c3b0d39c"},"schema_version":"1.0"},"canonical_sha256":"862dce25e071d7896f3da17d10afdecd17823655c85820ef6dfd0d376272c0ae","source":{"kind":"arxiv","id":"2606.09932","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09932","created_at":"2026-06-10T00:08:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09932v1","created_at":"2026-06-10T00:08:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09932","created_at":"2026-06-10T00:08:33Z"},{"alias_kind":"pith_short_12","alias_value":"QYW44JPAOHLY","created_at":"2026-06-10T00:08:33Z"},{"alias_kind":"pith_short_16","alias_value":"QYW44JPAOHLYS3Z5","created_at":"2026-06-10T00:08:33Z"},{"alias_kind":"pith_short_8","alias_value":"QYW44JPA","created_at":"2026-06-10T00:08:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QYW44JPAOHLYS3Z5UF6RBL66ZU","target":"record","payload":{"canonical_record":{"source":{"id":"2606.09932","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T17:58:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d513cffe39174c822af1141872cb6420dde423d5dbe0e545f0e9353b992c9cfd","abstract_canon_sha256":"effc05567b5e4034ad49d515f5c0c18c0816159165cbfbe91753ff56c3b0d39c"},"schema_version":"1.0"},"canonical_sha256":"862dce25e071d7896f3da17d10afdecd17823655c85820ef6dfd0d376272c0ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:33.644061Z","signature_b64":"yMfpCfZBTq6MYQlGVNahneq1ER0IoXP3RWEFvYD5VTne4axFht9Q9e+aASArnAn3UhvrxN6xLUpgZ9QLMlT+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"862dce25e071d7896f3da17d10afdecd17823655c85820ef6dfd0d376272c0ae","last_reissued_at":"2026-06-10T00:08:33.643145Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:33.643145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.09932","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T00:08:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yjw1/Fw/OpJV3wTGGGaROajzCEC8w2a1H8OJDGb5DeeCSzl5xZp16jG2JcCuPgvIX0pv5g1egQChat3QHBl3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T15:45:15.096855Z"},"content_sha256":"91b04c5caa66c9f7b2dee34122cab95827ea4a0bc0d87073ac9a0ad9f6579ae3","schema_version":"1.0","event_id":"sha256:91b04c5caa66c9f7b2dee34122cab95827ea4a0bc0d87073ac9a0ad9f6579ae3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QYW44JPAOHLYS3Z5UF6RBL66ZU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiashun Liu, Ling Pan, Runze Liu, Xu Wan, Yuqian Fu","submitted_at":"2026-06-07T17:58:58Z","abstract_excerpt":"Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become a standard pipeline for Large Language Model (LLM) post-training. SFT is expected to provide a useful behavioral prior for RL to further enhance model capabilities. However, checkpoints with excessive SFT often show limited improvement during RL. We attribute this failure to the loss of model plasticity: the reduced ability of an SFT-initialized policy to be effectively reshaped by subsequent RL. To better understand this phenomenon, we conduct detailed analysis from multiple perspectives, including parameter chang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09932","kind":"arxiv","version":1},"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/2606.09932/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":"2026-06-10T00:08:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ippzXn3s+UcZuWlq+p1ihnDt4ti8HCPYCZldn74HWibGAyHJxbjyGspCl5emrfbHX09qJvflIr3YyINNENzkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T15:45:15.097466Z"},"content_sha256":"2a10cc6f26f10f6ce362534544de896fb2b71fc3406fbe4408cac76f36fd585d","schema_version":"1.0","event_id":"sha256:2a10cc6f26f10f6ce362534544de896fb2b71fc3406fbe4408cac76f36fd585d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QYW44JPAOHLYS3Z5UF6RBL66ZU/bundle.json","state_url":"https://pith.science/pith/QYW44JPAOHLYS3Z5UF6RBL66ZU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QYW44JPAOHLYS3Z5UF6RBL66ZU/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":"2026-06-10T15:45:15Z","links":{"resolver":"https://pith.science/pith/QYW44JPAOHLYS3Z5UF6RBL66ZU","bundle":"https://pith.science/pith/QYW44JPAOHLYS3Z5UF6RBL66ZU/bundle.json","state":"https://pith.science/pith/QYW44JPAOHLYS3Z5UF6RBL66ZU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QYW44JPAOHLYS3Z5UF6RBL66ZU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QYW44JPAOHLYS3Z5UF6RBL66ZU","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":"effc05567b5e4034ad49d515f5c0c18c0816159165cbfbe91753ff56c3b0d39c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T17:58:58Z","title_canon_sha256":"d513cffe39174c822af1141872cb6420dde423d5dbe0e545f0e9353b992c9cfd"},"schema_version":"1.0","source":{"id":"2606.09932","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09932","created_at":"2026-06-10T00:08:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09932v1","created_at":"2026-06-10T00:08:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09932","created_at":"2026-06-10T00:08:33Z"},{"alias_kind":"pith_short_12","alias_value":"QYW44JPAOHLY","created_at":"2026-06-10T00:08:33Z"},{"alias_kind":"pith_short_16","alias_value":"QYW44JPAOHLYS3Z5","created_at":"2026-06-10T00:08:33Z"},{"alias_kind":"pith_short_8","alias_value":"QYW44JPA","created_at":"2026-06-10T00:08:33Z"}],"graph_snapshots":[{"event_id":"sha256:2a10cc6f26f10f6ce362534544de896fb2b71fc3406fbe4408cac76f36fd585d","target":"graph","created_at":"2026-06-10T00:08:33Z","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/2606.09932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become a standard pipeline for Large Language Model (LLM) post-training. SFT is expected to provide a useful behavioral prior for RL to further enhance model capabilities. However, checkpoints with excessive SFT often show limited improvement during RL. We attribute this failure to the loss of model plasticity: the reduced ability of an SFT-initialized policy to be effectively reshaped by subsequent RL. To better understand this phenomenon, we conduct detailed analysis from multiple perspectives, including parameter chang","authors_text":"Jiashun Liu, Ling Pan, Runze Liu, Xu Wan, Yuqian Fu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T17:58:58Z","title":"When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09932","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":"sha256:91b04c5caa66c9f7b2dee34122cab95827ea4a0bc0d87073ac9a0ad9f6579ae3","target":"record","created_at":"2026-06-10T00:08:33Z","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":"effc05567b5e4034ad49d515f5c0c18c0816159165cbfbe91753ff56c3b0d39c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T17:58:58Z","title_canon_sha256":"d513cffe39174c822af1141872cb6420dde423d5dbe0e545f0e9353b992c9cfd"},"schema_version":"1.0","source":{"id":"2606.09932","kind":"arxiv","version":1}},"canonical_sha256":"862dce25e071d7896f3da17d10afdecd17823655c85820ef6dfd0d376272c0ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"862dce25e071d7896f3da17d10afdecd17823655c85820ef6dfd0d376272c0ae","first_computed_at":"2026-06-10T00:08:33.643145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T00:08:33.643145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yMfpCfZBTq6MYQlGVNahneq1ER0IoXP3RWEFvYD5VTne4axFht9Q9e+aASArnAn3UhvrxN6xLUpgZ9QLMlT+BA==","signature_status":"signed_v1","signed_at":"2026-06-10T00:08:33.644061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09932","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91b04c5caa66c9f7b2dee34122cab95827ea4a0bc0d87073ac9a0ad9f6579ae3","sha256:2a10cc6f26f10f6ce362534544de896fb2b71fc3406fbe4408cac76f36fd585d"],"state_sha256":"32e2479a4842facd5e7706c4c7729568f441057e554f7550dc8d3e2b87525b98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sfrix8G8qp3D6IAI8uN8rwuCLUxhD96fclpkCAGSVtCTxFypbgBiFmjVK4+fPWiz59cH98uMSvWkSxKJaESpDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T15:45:15.101270Z","bundle_sha256":"8465e180fbed82ede3c9866e39a0e1d02e0353dab751c948b14f181e02794a17"}}