{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LQW767VY77V7TOPOFMUMGQ6ULR","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":"c0c21e016c52089a2a56695542990c68781619d23f52ae58a2d315feebab34df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T07:00:55Z","title_canon_sha256":"064fc313e376ab50a2074477019b163f6c1986810ed2e6282a0f9b9597ff7d35"},"schema_version":"1.0","source":{"id":"2605.19447","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19447","created_at":"2026-05-20T01:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19447v1","created_at":"2026-05-20T01:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19447","created_at":"2026-05-20T01:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"LQW767VY77V7","created_at":"2026-05-20T01:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"LQW767VY77V7TOPO","created_at":"2026-05-20T01:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"LQW767VY","created_at":"2026-05-20T01:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:567e4549ae217b57ac36f858dca4cf1d7f5eb8d47d150ac5cf998f1e15acbe1f","target":"graph","created_at":"2026-05-20T01:05:46Z","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/2605.19447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failure signal must be distributed across many actions. Existing methods rely on trajectory-level rewards or proxy signals, without fully leveraging per-step environmental feedback. Multi-turn agent settings are underexplored, where feedback can include error messages, page changes, observations, or reference trajectories. We systematically study five feedback sources and two insertion granularities and introduce SERL, a selective environment-reweigh","authors_text":"Dahua Lin, Kai Chen, Linyang Li, Peiji Li, Qipeng Guo, Tianyi Lyu, Xiaozhe Li, Yang Li, Yichuan Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T07:00:55Z","title":"What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19447","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:d273770307693e7187f60a4b8d201a4462172bf873f0262e9701c52600e298ed","target":"record","created_at":"2026-05-20T01:05:46Z","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":"c0c21e016c52089a2a56695542990c68781619d23f52ae58a2d315feebab34df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T07:00:55Z","title_canon_sha256":"064fc313e376ab50a2074477019b163f6c1986810ed2e6282a0f9b9597ff7d35"},"schema_version":"1.0","source":{"id":"2605.19447","kind":"arxiv","version":1}},"canonical_sha256":"5c2dff7eb8ffebf9b9ee2b28c343d45c412813e4b5759b0bc22dbab6229eb087","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c2dff7eb8ffebf9b9ee2b28c343d45c412813e4b5759b0bc22dbab6229eb087","first_computed_at":"2026-05-20T01:05:46.353563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:46.353563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+VTT35KK2sGAOXsQEWsexr+4WXEtzwxXbS8SXHf9ku6Q997Z4z2Hhto9oV+1BNuFFQ5e92B7oK7565BGDjeADw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:46.354417Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19447","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d273770307693e7187f60a4b8d201a4462172bf873f0262e9701c52600e298ed","sha256:567e4549ae217b57ac36f858dca4cf1d7f5eb8d47d150ac5cf998f1e15acbe1f"],"state_sha256":"ec106e8b31f9827634c9df8abcac6c29cd0c54858e357da156ecd8a6535ebd28"}