{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XYDQUKQZ5LADC4CR2KZS7ZYVPZ","short_pith_number":"pith:XYDQUKQZ","canonical_record":{"source":{"id":"2608.01359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:22:27Z","cross_cats_sorted":[],"title_canon_sha256":"e8d49999c447c9f4e2232cb7843327ffa916ef9564e5a0f72717982c1481f323","abstract_canon_sha256":"5b4e874ede7fdbd187ab6658b1574bcafc2f313671ea08354953dfb0eb9d5654"},"schema_version":"1.0"},"canonical_sha256":"be070a2a19eac0317051d2b32fe7157e73ba2e94073cc1ff520564a7052695ec","source":{"kind":"arxiv","id":"2608.01359","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01359","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01359v1","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01359","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"XYDQUKQZ5LAD","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"XYDQUKQZ5LADC4CR","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"XYDQUKQZ","created_at":"2026-08-04T02:04:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XYDQUKQZ5LADC4CR2KZS7ZYVPZ","target":"record","payload":{"canonical_record":{"source":{"id":"2608.01359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:22:27Z","cross_cats_sorted":[],"title_canon_sha256":"e8d49999c447c9f4e2232cb7843327ffa916ef9564e5a0f72717982c1481f323","abstract_canon_sha256":"5b4e874ede7fdbd187ab6658b1574bcafc2f313671ea08354953dfb0eb9d5654"},"schema_version":"1.0"},"canonical_sha256":"be070a2a19eac0317051d2b32fe7157e73ba2e94073cc1ff520564a7052695ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:04:52.638844Z","signature_b64":"XJKTzrjpitAR//R8dVnA88rJF9+VOaJtNMcS0ieejWsSixcwF4SMJ3dn6Evc+cdPebOljtca8sJjHV8rT+1kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be070a2a19eac0317051d2b32fe7157e73ba2e94073cc1ff520564a7052695ec","last_reissued_at":"2026-08-04T02:04:52.637342Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:04:52.637342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.01359","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":"2026-08-04T02:04:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pKGY0Dbr5fH+9JKQ7nRyvxSxghzPvGWplozdyiEc1lBjW23bWHlPx+G7lNmWKwsF6w9ijd5vAcFXNj9+/upXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:24:30.471950Z"},"content_sha256":"0ceca6fbf72832b0aac429957069c29a02c5e601efaabbb5c43965dd689b00fb","schema_version":"1.0","event_id":"sha256:0ceca6fbf72832b0aac429957069c29a02c5e601efaabbb5c43965dd689b00fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XYDQUKQZ5LADC4CR2KZS7ZYVPZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EviSD: Evidence-Conditioned Self-Distillation for Search-Augmented Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Song, Jianan Xie, Liang Wang, Shu Wu, Xing Zheng, Xin Sun, Zhongqi Chen","submitted_at":"2026-08-02T16:22:27Z","abstract_excerpt":"Outcome-based reinforcement learning enables search-augmented language agents to learn from verifiable final answers, but its trajectory-level credit cannot distinguish the contributions of individual actions in a multi-turn search process. We propose EviSD, an evidence-conditioned self-distillation framework that uses instance-level supporting evidence as privileged information for search actions and golden answers as complementary privilege for answer actions. During training, the student samples actions from the original context, while the same model re-scores them as a privileged teacher u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01359","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/2608.01359/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":"2026-08-04T02:04:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IrEt5Dh1PsKExmLFf60oVzi4ozfWdQLcPy3bBgSZqDpuQcvxnM9lZjqgBQkfiZazEPWuX9chwPwOHIK9B9AxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:24:30.472813Z"},"content_sha256":"3d8689913aa68f54b980991b76290a653aeeadd2389435a65b68cded558b6362","schema_version":"1.0","event_id":"sha256:3d8689913aa68f54b980991b76290a653aeeadd2389435a65b68cded558b6362"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XYDQUKQZ5LADC4CR2KZS7ZYVPZ/bundle.json","state_url":"https://pith.science/pith/XYDQUKQZ5LADC4CR2KZS7ZYVPZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XYDQUKQZ5LADC4CR2KZS7ZYVPZ/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":"2026-08-06T17:24:30Z","links":{"resolver":"https://pith.science/pith/XYDQUKQZ5LADC4CR2KZS7ZYVPZ","bundle":"https://pith.science/pith/XYDQUKQZ5LADC4CR2KZS7ZYVPZ/bundle.json","state":"https://pith.science/pith/XYDQUKQZ5LADC4CR2KZS7ZYVPZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XYDQUKQZ5LADC4CR2KZS7ZYVPZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XYDQUKQZ5LADC4CR2KZS7ZYVPZ","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":"5b4e874ede7fdbd187ab6658b1574bcafc2f313671ea08354953dfb0eb9d5654","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:22:27Z","title_canon_sha256":"e8d49999c447c9f4e2232cb7843327ffa916ef9564e5a0f72717982c1481f323"},"schema_version":"1.0","source":{"id":"2608.01359","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01359","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01359v1","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01359","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"XYDQUKQZ5LAD","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"XYDQUKQZ5LADC4CR","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"XYDQUKQZ","created_at":"2026-08-04T02:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:3d8689913aa68f54b980991b76290a653aeeadd2389435a65b68cded558b6362","target":"graph","created_at":"2026-08-04T02:04:52Z","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/2608.01359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Outcome-based reinforcement learning enables search-augmented language agents to learn from verifiable final answers, but its trajectory-level credit cannot distinguish the contributions of individual actions in a multi-turn search process. We propose EviSD, an evidence-conditioned self-distillation framework that uses instance-level supporting evidence as privileged information for search actions and golden answers as complementary privilege for answer actions. During training, the student samples actions from the original context, while the same model re-scores them as a privileged teacher u","authors_text":"Bowen Song, Jianan Xie, Liang Wang, Shu Wu, Xing Zheng, Xin Sun, Zhongqi Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:22:27Z","title":"EviSD: Evidence-Conditioned Self-Distillation for Search-Augmented Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01359","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":"sha256:0ceca6fbf72832b0aac429957069c29a02c5e601efaabbb5c43965dd689b00fb","target":"record","created_at":"2026-08-04T02:04:52Z","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":"5b4e874ede7fdbd187ab6658b1574bcafc2f313671ea08354953dfb0eb9d5654","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:22:27Z","title_canon_sha256":"e8d49999c447c9f4e2232cb7843327ffa916ef9564e5a0f72717982c1481f323"},"schema_version":"1.0","source":{"id":"2608.01359","kind":"arxiv","version":1}},"canonical_sha256":"be070a2a19eac0317051d2b32fe7157e73ba2e94073cc1ff520564a7052695ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be070a2a19eac0317051d2b32fe7157e73ba2e94073cc1ff520564a7052695ec","first_computed_at":"2026-08-04T02:04:52.637342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:04:52.637342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XJKTzrjpitAR//R8dVnA88rJF9+VOaJtNMcS0ieejWsSixcwF4SMJ3dn6Evc+cdPebOljtca8sJjHV8rT+1kCA==","signature_status":"signed_v1","signed_at":"2026-08-04T02:04:52.638844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01359","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ceca6fbf72832b0aac429957069c29a02c5e601efaabbb5c43965dd689b00fb","sha256:3d8689913aa68f54b980991b76290a653aeeadd2389435a65b68cded558b6362"],"state_sha256":"3eb9c1a397fa14510cc5ea981dab2861525150eaeca9a9a59416fabf22a7f24e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mnou1LyvN86KGEki0/T4aoMb6dN+tvGO7hab6sPgljKhO4TSZcfPXpv5pEDfkimq9g1cA5t7SUXw03VBT6zsBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:24:30.490564Z","bundle_sha256":"ce0f61e12a5b1b2d3bf26000dd47751d653d7d8a2b1d20a203032a31ea55013b"}}