{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SLGXXKGEGKQKUMTPF6GO6MYSEQ","short_pith_number":"pith:SLGXXKGE","canonical_record":{"source":{"id":"2608.05080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T17:22:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7f0201203880cb19e44dab15879ff721bace1be4d3987d49014a9b102f9bf372","abstract_canon_sha256":"49e490a8a62f9e6c213977ceaaed056a325595211935bd3c8b521f730c0a4ee2"},"schema_version":"1.0"},"canonical_sha256":"92cd7ba8c432a0aa326f2f8cef3312243056b914ec9f3aa69630444a427dfced","source":{"kind":"arxiv","id":"2608.05080","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05080","created_at":"2026-08-06T01:49:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05080v1","created_at":"2026-08-06T01:49:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05080","created_at":"2026-08-06T01:49:00Z"},{"alias_kind":"pith_short_12","alias_value":"SLGXXKGEGKQK","created_at":"2026-08-06T01:49:00Z"},{"alias_kind":"pith_short_16","alias_value":"SLGXXKGEGKQKUMTP","created_at":"2026-08-06T01:49:00Z"},{"alias_kind":"pith_short_8","alias_value":"SLGXXKGE","created_at":"2026-08-06T01:49:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SLGXXKGEGKQKUMTPF6GO6MYSEQ","target":"record","payload":{"canonical_record":{"source":{"id":"2608.05080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T17:22:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7f0201203880cb19e44dab15879ff721bace1be4d3987d49014a9b102f9bf372","abstract_canon_sha256":"49e490a8a62f9e6c213977ceaaed056a325595211935bd3c8b521f730c0a4ee2"},"schema_version":"1.0"},"canonical_sha256":"92cd7ba8c432a0aa326f2f8cef3312243056b914ec9f3aa69630444a427dfced","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:49:00.096929Z","signature_b64":"qm9krio/xGKUjVySOvb+mr2qepF61xFXxCU9b5ZlGqU7b1K/ez3Ekn4330M6bR8AP9s9evlo8MqYx+nplIChBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92cd7ba8c432a0aa326f2f8cef3312243056b914ec9f3aa69630444a427dfced","last_reissued_at":"2026-08-06T01:49:00.095367Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:49:00.095367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.05080","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":"2026-08-06T01:49:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9K2bivMo+1QKnqfbCeSEGB+ScOQ8LNrvtOgG4GKiCqTYDY4ydU6fwNf7jfxMAI4qVl+sLxsDBGHUHpcJiafoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:34:13.319866Z"},"content_sha256":"2aed0fbb5a0f9bed79b626ad19d6b69d0809093ff700dc6c9564f23e9cecea60","schema_version":"1.0","event_id":"sha256:2aed0fbb5a0f9bed79b626ad19d6b69d0809093ff700dc6c9564f23e9cecea60"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SLGXXKGEGKQKUMTPF6GO6MYSEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hong Wang, James Feng, Jie Yuan, Manqing Mao, Nikki Lijing Kuang, Samson Koelle, Wei Niu, Yanfang Ye, Yanjun Lin, Zheyuan Zhang, Zhuoer Wang","submitted_at":"2026-08-05T17:22:02Z","abstract_excerpt":"Critic-free group-based reinforcement learning has become a scalable approach for post-training large language models. However, most existing methods allocate the same number of rollouts to every task and trajectory state, even though some rollouts provide much more useful learning signals than others. Recent work has started to treat rollout generation as an adaptive decision, but two important limitations remain. First, intervention strategies are often based on fixed heuristics and therefore cannot adjust as the policy changes during training. Second, these methods usually decide only how m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05080","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/2608.05080/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":"2026-08-06T01:49:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LfdA1DLPNXMuJnS3hE4nnSr6jYvE0wDzsOjK6BMA9Pvng1z0jNGrL7h4yp+6vdo8B2ybPrfaNP0I5B0ASXvtDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:34:13.320398Z"},"content_sha256":"c2fbc846334acfec4eb28a5181f83c7103c05b93231d018f91d85fa322c663d1","schema_version":"1.0","event_id":"sha256:c2fbc846334acfec4eb28a5181f83c7103c05b93231d018f91d85fa322c663d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SLGXXKGEGKQKUMTPF6GO6MYSEQ/bundle.json","state_url":"https://pith.science/pith/SLGXXKGEGKQKUMTPF6GO6MYSEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SLGXXKGEGKQKUMTPF6GO6MYSEQ/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":"2026-08-06T18:34:13Z","links":{"resolver":"https://pith.science/pith/SLGXXKGEGKQKUMTPF6GO6MYSEQ","bundle":"https://pith.science/pith/SLGXXKGEGKQKUMTPF6GO6MYSEQ/bundle.json","state":"https://pith.science/pith/SLGXXKGEGKQKUMTPF6GO6MYSEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SLGXXKGEGKQKUMTPF6GO6MYSEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SLGXXKGEGKQKUMTPF6GO6MYSEQ","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":"49e490a8a62f9e6c213977ceaaed056a325595211935bd3c8b521f730c0a4ee2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T17:22:02Z","title_canon_sha256":"7f0201203880cb19e44dab15879ff721bace1be4d3987d49014a9b102f9bf372"},"schema_version":"1.0","source":{"id":"2608.05080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05080","created_at":"2026-08-06T01:49:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05080v1","created_at":"2026-08-06T01:49:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05080","created_at":"2026-08-06T01:49:00Z"},{"alias_kind":"pith_short_12","alias_value":"SLGXXKGEGKQK","created_at":"2026-08-06T01:49:00Z"},{"alias_kind":"pith_short_16","alias_value":"SLGXXKGEGKQKUMTP","created_at":"2026-08-06T01:49:00Z"},{"alias_kind":"pith_short_8","alias_value":"SLGXXKGE","created_at":"2026-08-06T01:49:00Z"}],"graph_snapshots":[{"event_id":"sha256:c2fbc846334acfec4eb28a5181f83c7103c05b93231d018f91d85fa322c663d1","target":"graph","created_at":"2026-08-06T01:49:00Z","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/2608.05080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Critic-free group-based reinforcement learning has become a scalable approach for post-training large language models. However, most existing methods allocate the same number of rollouts to every task and trajectory state, even though some rollouts provide much more useful learning signals than others. Recent work has started to treat rollout generation as an adaptive decision, but two important limitations remain. First, intervention strategies are often based on fixed heuristics and therefore cannot adjust as the policy changes during training. Second, these methods usually decide only how m","authors_text":"Hong Wang, James Feng, Jie Yuan, Manqing Mao, Nikki Lijing Kuang, Samson Koelle, Wei Niu, Yanfang Ye, Yanjun Lin, Zheyuan Zhang, Zhuoer Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T17:22:02Z","title":"Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05080","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":"sha256:2aed0fbb5a0f9bed79b626ad19d6b69d0809093ff700dc6c9564f23e9cecea60","target":"record","created_at":"2026-08-06T01:49:00Z","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":"49e490a8a62f9e6c213977ceaaed056a325595211935bd3c8b521f730c0a4ee2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T17:22:02Z","title_canon_sha256":"7f0201203880cb19e44dab15879ff721bace1be4d3987d49014a9b102f9bf372"},"schema_version":"1.0","source":{"id":"2608.05080","kind":"arxiv","version":1}},"canonical_sha256":"92cd7ba8c432a0aa326f2f8cef3312243056b914ec9f3aa69630444a427dfced","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92cd7ba8c432a0aa326f2f8cef3312243056b914ec9f3aa69630444a427dfced","first_computed_at":"2026-08-06T01:49:00.095367Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:49:00.095367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qm9krio/xGKUjVySOvb+mr2qepF61xFXxCU9b5ZlGqU7b1K/ez3Ekn4330M6bR8AP9s9evlo8MqYx+nplIChBA==","signature_status":"signed_v1","signed_at":"2026-08-06T01:49:00.096929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2aed0fbb5a0f9bed79b626ad19d6b69d0809093ff700dc6c9564f23e9cecea60","sha256:c2fbc846334acfec4eb28a5181f83c7103c05b93231d018f91d85fa322c663d1"],"state_sha256":"9d2c5073df9e3464e6d780754c36792bfb0ed16a4a9acd81fdd658ea78c6e32f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ZBz7cvLf3TJsxRXCFlSRaGGA62LpN3sE4HFrW6qvwSVs8751PBT3/1pPYzg9thsf2WVO2hlKWhH2Rrbzd+eBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:34:13.324406Z","bundle_sha256":"8c3300f31ee7fa9d258370d2c8e00e65e55c9c716e9e9bab4fcda13c824d22ee"}}