{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IEZ5OJNEY2ZJICGGTIZRW7U7HU","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":"2cc91d17cc70002345d94c61cc14ef1dd88b9f2471b409e6d021009d20980154","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T09:57:18Z","title_canon_sha256":"64400b432aaeb07013a85d00b8a995a78630690cc5fbdcab0449768dba15f440"},"schema_version":"1.0","source":{"id":"2607.14777","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14777","created_at":"2026-07-17T01:21:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14777v1","created_at":"2026-07-17T01:21:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14777","created_at":"2026-07-17T01:21:30Z"},{"alias_kind":"pith_short_12","alias_value":"IEZ5OJNEY2ZJ","created_at":"2026-07-17T01:21:30Z"},{"alias_kind":"pith_short_16","alias_value":"IEZ5OJNEY2ZJICGG","created_at":"2026-07-17T01:21:30Z"},{"alias_kind":"pith_short_8","alias_value":"IEZ5OJNE","created_at":"2026-07-17T01:21:30Z"}],"graph_snapshots":[{"event_id":"sha256:935f336f10a7982fed70a3091feab34a998d54a2b2493972bcef924752bed1db","target":"graph","created_at":"2026-07-17T01:21:30Z","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/2607.14777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limited guidance on intermediate decisions, leaving a supervision gap between episode-level outcomes and token-level policy learning. We propose SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills and dis","authors_text":"Fan Zhang, Haoran Luo, Jianhua Tao, Jinyang Wu, Lang Feng, Shuai Zhang, Shuo Yang, Yuhao Shen, Zheng Lian, Zhengqi Wen, Zhengxi Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T09:57:18Z","title":"SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14777","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":"sha256:755a0d41f19524c2ffa8fa97a1b33918707946186ddffd6b8b759c2307ad7d0e","target":"record","created_at":"2026-07-17T01:21:30Z","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":"2cc91d17cc70002345d94c61cc14ef1dd88b9f2471b409e6d021009d20980154","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T09:57:18Z","title_canon_sha256":"64400b432aaeb07013a85d00b8a995a78630690cc5fbdcab0449768dba15f440"},"schema_version":"1.0","source":{"id":"2607.14777","kind":"arxiv","version":1}},"canonical_sha256":"4133d725a4c6b29408c69a331b7e9f3d28d6a91d11577a4d8197cb42bbc76f30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4133d725a4c6b29408c69a331b7e9f3d28d6a91d11577a4d8197cb42bbc76f30","first_computed_at":"2026-07-17T01:21:30.518449Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:21:30.518449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K6mdS+O8auO2mXQ84arSXWX8bonWctBQTJx8T8S+vt4VqLsQOqS7fHUkgOSbIGUxlPugWw9oEXrclWVS7bq8Cw==","signature_status":"signed_v1","signed_at":"2026-07-17T01:21:30.519271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14777","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:755a0d41f19524c2ffa8fa97a1b33918707946186ddffd6b8b759c2307ad7d0e","sha256:935f336f10a7982fed70a3091feab34a998d54a2b2493972bcef924752bed1db"],"state_sha256":"50ce751489767f3227f193b439fb6eef82ae82300f3926e7b1b3f7b367bd9b06"}