{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YWUK3M67DWTBXBDXAZD6LADQA2","short_pith_number":"pith:YWUK3M67","schema_version":"1.0","canonical_sha256":"c5a8adb3df1da61b84770647e58070068bfffd7b94402fab36f0dba1648494bd","source":{"kind":"arxiv","id":"2605.27710","version":1},"attestation_state":"computed","paper":{"title":"DeepSciVerify: Verifying Scientific Claim--Citation Alignment via LLM-Driven Evidence Escalation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Tessier, Khashayar Khajavi, Rise Adhikari, Shaghayegh Sadeghi","submitted_at":"2026-05-26T21:33:29Z","abstract_excerpt":"Misalignment between claims and their cited evidence is a common failure mode in reports generated by large language models, limiting their reliability in scientific and other high-stakes settings. We present DeepSciVerify, a two-stage pipeline for scientific claim-citation verification that combines abstract-level reasoning with selective escalation to passage-level evidence. The system first verifies claims using the abstract and defers uncertain cases, retrieving and analyzing full-text passages only when necessary. This design leverages complementary behaviors across LLMs, as some models a"},"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":"2605.27710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T21:33:29Z","cross_cats_sorted":[],"title_canon_sha256":"9336f6be837f447eddc285123ba53ea8b2ae7857c8ead11009ac0a123549dd9b","abstract_canon_sha256":"ac5c93ffd1695951abf82319ec8c7e74781ff986ef54412bed64b1dd59361e57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:46.893047Z","signature_b64":"yeATOQF1HI6GCpAHZ5JHAy8OuF3S/8wO1cceu1SU1Cyih7pQo7h7S+GFZ1LRKIIK0AamXmD/UMBbe7eu0dHNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5a8adb3df1da61b84770647e58070068bfffd7b94402fab36f0dba1648494bd","last_reissued_at":"2026-05-28T01:04:46.892629Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:46.892629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepSciVerify: Verifying Scientific Claim--Citation Alignment via LLM-Driven Evidence Escalation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Tessier, Khashayar Khajavi, Rise Adhikari, Shaghayegh Sadeghi","submitted_at":"2026-05-26T21:33:29Z","abstract_excerpt":"Misalignment between claims and their cited evidence is a common failure mode in reports generated by large language models, limiting their reliability in scientific and other high-stakes settings. We present DeepSciVerify, a two-stage pipeline for scientific claim-citation verification that combines abstract-level reasoning with selective escalation to passage-level evidence. The system first verifies claims using the abstract and defers uncertain cases, retrieving and analyzing full-text passages only when necessary. This design leverages complementary behaviors across LLMs, as some models a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27710","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/2605.27710/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":"2605.27710","created_at":"2026-05-28T01:04:46.892693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27710v1","created_at":"2026-05-28T01:04:46.892693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27710","created_at":"2026-05-28T01:04:46.892693+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWUK3M67DWTB","created_at":"2026-05-28T01:04:46.892693+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWUK3M67DWTBXBDX","created_at":"2026-05-28T01:04:46.892693+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWUK3M67","created_at":"2026-05-28T01:04:46.892693+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/YWUK3M67DWTBXBDXAZD6LADQA2","json":"https://pith.science/pith/YWUK3M67DWTBXBDXAZD6LADQA2.json","graph_json":"https://pith.science/api/pith-number/YWUK3M67DWTBXBDXAZD6LADQA2/graph.json","events_json":"https://pith.science/api/pith-number/YWUK3M67DWTBXBDXAZD6LADQA2/events.json","paper":"https://pith.science/paper/YWUK3M67"},"agent_actions":{"view_html":"https://pith.science/pith/YWUK3M67DWTBXBDXAZD6LADQA2","download_json":"https://pith.science/pith/YWUK3M67DWTBXBDXAZD6LADQA2.json","view_paper":"https://pith.science/paper/YWUK3M67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27710&json=true","fetch_graph":"https://pith.science/api/pith-number/YWUK3M67DWTBXBDXAZD6LADQA2/graph.json","fetch_events":"https://pith.science/api/pith-number/YWUK3M67DWTBXBDXAZD6LADQA2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWUK3M67DWTBXBDXAZD6LADQA2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWUK3M67DWTBXBDXAZD6LADQA2/action/storage_attestation","attest_author":"https://pith.science/pith/YWUK3M67DWTBXBDXAZD6LADQA2/action/author_attestation","sign_citation":"https://pith.science/pith/YWUK3M67DWTBXBDXAZD6LADQA2/action/citation_signature","submit_replication":"https://pith.science/pith/YWUK3M67DWTBXBDXAZD6LADQA2/action/replication_record"}},"created_at":"2026-05-28T01:04:46.892693+00:00","updated_at":"2026-05-28T01:04:46.892693+00:00"}