{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BWZNSL7IYIAMFUS2WHTGLZKNMI","short_pith_number":"pith:BWZNSL7I","schema_version":"1.0","canonical_sha256":"0db2d92fe8c200c2d25ab1e665e54d621b3250d3f902c6a6800d1fa8b4615fe6","source":{"kind":"arxiv","id":"2606.11127","version":1},"attestation_state":"computed","paper":{"title":"Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Karun Sharma, Pratinav Seth, Soham Bhattacharjee, Vinay Kumar Sankarapu","submitted_at":"2026-06-09T17:24:27Z","abstract_excerpt":"Synthetic post-training pipelines commonly filter generated samples with reward models or holistic LLM judges, yet two practices remain rarely examined together: whether the filtering signal is grounded in the source evidence that induced each generation, and whether rejected samples can be systematically recovered rather than permanently discarded. We present a controlled study of both questions across gate configurations, recovery strategies, and generator scales, using adversarially injected corpora to provide ground-truth failure labels. We find that exact source provenance improves faithf"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.11127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T17:24:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d2b772ea463a5f57174064e73fc52e4a7866f552f754e6ccb414ff8b0c871251","abstract_canon_sha256":"07aa312b86ef945e3d358407393879d9eb6a45d6075463f75f3b6913be5a4a66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:11:12.542262Z","signature_b64":"QB2hO5qWmms+RpTvg7oEEY+XMnAoa+uChztFum074pQZdc71bIxv4JUkByaNI9844RlsoOLp2haHsQl1xOyIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0db2d92fe8c200c2d25ab1e665e54d621b3250d3f902c6a6800d1fa8b4615fe6","last_reissued_at":"2026-06-10T01:11:12.541470Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:11:12.541470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Karun Sharma, Pratinav Seth, Soham Bhattacharjee, Vinay Kumar Sankarapu","submitted_at":"2026-06-09T17:24:27Z","abstract_excerpt":"Synthetic post-training pipelines commonly filter generated samples with reward models or holistic LLM judges, yet two practices remain rarely examined together: whether the filtering signal is grounded in the source evidence that induced each generation, and whether rejected samples can be systematically recovered rather than permanently discarded. We present a controlled study of both questions across gate configurations, recovery strategies, and generator scales, using adversarially injected corpora to provide ground-truth failure labels. We find that exact source provenance improves faithf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11127","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/2606.11127/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.11127","created_at":"2026-06-10T01:11:12.541595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11127v1","created_at":"2026-06-10T01:11:12.541595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11127","created_at":"2026-06-10T01:11:12.541595+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWZNSL7IYIAM","created_at":"2026-06-10T01:11:12.541595+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWZNSL7IYIAMFUS2","created_at":"2026-06-10T01:11:12.541595+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWZNSL7I","created_at":"2026-06-10T01:11:12.541595+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BWZNSL7IYIAMFUS2WHTGLZKNMI","json":"https://pith.science/pith/BWZNSL7IYIAMFUS2WHTGLZKNMI.json","graph_json":"https://pith.science/api/pith-number/BWZNSL7IYIAMFUS2WHTGLZKNMI/graph.json","events_json":"https://pith.science/api/pith-number/BWZNSL7IYIAMFUS2WHTGLZKNMI/events.json","paper":"https://pith.science/paper/BWZNSL7I"},"agent_actions":{"view_html":"https://pith.science/pith/BWZNSL7IYIAMFUS2WHTGLZKNMI","download_json":"https://pith.science/pith/BWZNSL7IYIAMFUS2WHTGLZKNMI.json","view_paper":"https://pith.science/paper/BWZNSL7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11127&json=true","fetch_graph":"https://pith.science/api/pith-number/BWZNSL7IYIAMFUS2WHTGLZKNMI/graph.json","fetch_events":"https://pith.science/api/pith-number/BWZNSL7IYIAMFUS2WHTGLZKNMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWZNSL7IYIAMFUS2WHTGLZKNMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWZNSL7IYIAMFUS2WHTGLZKNMI/action/storage_attestation","attest_author":"https://pith.science/pith/BWZNSL7IYIAMFUS2WHTGLZKNMI/action/author_attestation","sign_citation":"https://pith.science/pith/BWZNSL7IYIAMFUS2WHTGLZKNMI/action/citation_signature","submit_replication":"https://pith.science/pith/BWZNSL7IYIAMFUS2WHTGLZKNMI/action/replication_record"}},"created_at":"2026-06-10T01:11:12.541595+00:00","updated_at":"2026-06-10T01:11:12.541595+00:00"}