{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BYEWVJHLLJSBAFBYZQHW53ZP4H","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":"483c37c13df48f095cdf2bd9dfe85105c2ba5890a677f231492782606ffc4753","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T03:13:18Z","title_canon_sha256":"0117130cc66b40fcaa32c9bc10da7fe09a7dad78f1b065dd32c9a15d01d44f97"},"schema_version":"1.0","source":{"id":"2608.12764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12764","created_at":"2026-08-14T00:47:38Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12764v1","created_at":"2026-08-14T00:47:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12764","created_at":"2026-08-14T00:47:38Z"},{"alias_kind":"pith_short_12","alias_value":"BYEWVJHLLJSB","created_at":"2026-08-14T00:47:38Z"},{"alias_kind":"pith_short_16","alias_value":"BYEWVJHLLJSBAFBY","created_at":"2026-08-14T00:47:38Z"},{"alias_kind":"pith_short_8","alias_value":"BYEWVJHL","created_at":"2026-08-14T00:47:38Z"}],"graph_snapshots":[{"event_id":"sha256:f3995fa44388b596e80e5cdc13bba010e5babab93d155437d604ec70b3a88bd6","target":"graph","created_at":"2026-08-14T00:47:38Z","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/2608.12764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment. On-policy self-distillation (OPSD) addresses this by using the model's own logits as dense token-level teachers, but extending it to search agents introduces a fundamental tension: the teacher, having access to privileged information such as the correct answer, produces a distribution that differs systematically from the student's exploration-based reasoning, and naive distillati","authors_text":"Chuqiao Kuang, Haoze Wu, Tianyi Zhuang, Xiaoguang Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T03:13:18Z","title":"Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12764","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:f04b7363345ef0bee6749e1a1e33a4f3ed7c97af75e02806b5fbb9f5adc5bb32","target":"record","created_at":"2026-08-14T00:47:38Z","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":"483c37c13df48f095cdf2bd9dfe85105c2ba5890a677f231492782606ffc4753","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T03:13:18Z","title_canon_sha256":"0117130cc66b40fcaa32c9bc10da7fe09a7dad78f1b065dd32c9a15d01d44f97"},"schema_version":"1.0","source":{"id":"2608.12764","kind":"arxiv","version":1}},"canonical_sha256":"0e096aa4eb5a64101438cc0f6eef2fe1c26117a5794fede18ec4e1bc1c79e23a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e096aa4eb5a64101438cc0f6eef2fe1c26117a5794fede18ec4e1bc1c79e23a","first_computed_at":"2026-08-14T00:47:38.315530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T00:47:38.315530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DK4bv6/3xaR89WO/SlhXsFeRB2g6wOslOtTmx7tspQULxdIYwhjtFGYnRl46BgFHu67rKnAbOd2u5EVqibpNCA==","signature_status":"signed_v1","signed_at":"2026-08-14T00:47:38.330906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f04b7363345ef0bee6749e1a1e33a4f3ed7c97af75e02806b5fbb9f5adc5bb32","sha256:f3995fa44388b596e80e5cdc13bba010e5babab93d155437d604ec70b3a88bd6"],"state_sha256":"799adb16cd1b6594df95717e56e2864b84fee1b6c6e808afa30170597e9274a1"}