{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4HLLBK5Z4FRDX4HK6KU6TXWXTO","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":"cba01f48da7c5546f4b6d1a76845004433400995c028357d97368dbcd90e1249","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T12:18:47Z","title_canon_sha256":"48e1eef21f2ac5a6b7c3b97ef423db18906b9a91218bfd5e5a9fbdab9d529357"},"schema_version":"1.0","source":{"id":"2605.18299","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18299","created_at":"2026-05-20T00:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18299v1","created_at":"2026-05-20T00:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18299","created_at":"2026-05-20T00:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"4HLLBK5Z4FRD","created_at":"2026-05-20T00:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"4HLLBK5Z4FRDX4HK","created_at":"2026-05-20T00:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"4HLLBK5Z","created_at":"2026-05-20T00:05:54Z"}],"graph_snapshots":[{"event_id":"sha256:4cfa58a194a552291b4c0b6f7109be3ceacd0ef314f3b3969edba4a6c6e380ef","target":"graph","created_at":"2026-05-20T00:05:54Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.213326Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.903210Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18299/integrity.json","findings":[],"snapshot_sha256":"3473efb3b6cedf2efe9069f140bcc8e725265afed62574014594851fe719a24f","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Search-augmented reasoning agents interleave internal reasoning with calls to an external retriever, and their performance relies on the quality of each issued query. However, under outcome-reward reinforcement learning, every search decision in a rollout shares the same trajectory-level reward, leaving individual queries without step-specific credit. Recent process-supervision approaches address this gap by drawing step-level signals from outside the policy, relying either on a much larger teacher model, or on sub-question annotations produced by a stronger external system. In contrast, we pr","authors_text":"Ben Chen, Chenyi Lei, Huangyu Dai, Lingtao Mao, Wenwu Ou, Xuxin Zhang, Yufei Ma, Zhipeng Qian, Zihan Liang","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T12:18:47Z","title":"SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18299","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:eda6fd46500983b6b3c0f778d3826af509e718958695cab18e8a36b4f2b57afd","target":"record","created_at":"2026-05-20T00:05:54Z","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":"cba01f48da7c5546f4b6d1a76845004433400995c028357d97368dbcd90e1249","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T12:18:47Z","title_canon_sha256":"48e1eef21f2ac5a6b7c3b97ef423db18906b9a91218bfd5e5a9fbdab9d529357"},"schema_version":"1.0","source":{"id":"2605.18299","kind":"arxiv","version":1}},"canonical_sha256":"e1d6b0abb9e1623bf0eaf2a9e9ded79bb6fc6bcaf694d88e7742a5044209f9eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1d6b0abb9e1623bf0eaf2a9e9ded79bb6fc6bcaf694d88e7742a5044209f9eb","first_computed_at":"2026-05-20T00:05:54.048744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:54.048744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JI5sqLB3n3oSq6agVwH3Jms5e7EWcosV6gE8xtewseWjWyas4UPnDinPXWeXVPp+t4H7STc5thP8rMXg7sA4Bw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:54.049422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18299","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eda6fd46500983b6b3c0f778d3826af509e718958695cab18e8a36b4f2b57afd","sha256:4cfa58a194a552291b4c0b6f7109be3ceacd0ef314f3b3969edba4a6c6e380ef"],"state_sha256":"7504bf95c4f069c447d81b23e680c292ea9deab602606e167c34ab038e328e29"}