{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:53GCAVSVT7JPJJSHHE6OHPDEPX","short_pith_number":"pith:53GCAVSV","schema_version":"1.0","canonical_sha256":"eecc2056559fd2f4a647393ce3bc647dcf2bb9bb8dd7db0e90fec0f8a0062f64","source":{"kind":"arxiv","id":"2608.01409","version":1},"attestation_state":"computed","paper":{"title":"When Retrieval Helps and Distracts: Evaluating Evidence-Generating LLMs for Biomedical Claim Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Prabhjot Singh, Pritam Deka","submitted_at":"2026-08-02T17:43:28Z","abstract_excerpt":"Biomedical fact-checking systems must do more than predict whether a claim is supported, contradicted, or unaddressed: they should also produce evidence that is faithful, complete, and useful for verification. We study this evidence-generation setting on CARE-XAI, a unified benchmark spanning five biomedical and health fact-checking sources. We compare base instruction LLMs, PubMed retrieval-augmented LLMs, fine-tuned LLMs, label-only LLMs, and biomedical encoder classifiers under a shared evaluation protocol. Biomedical classifiers remain strongest for verdict-only prediction, while fine-tune"},"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":"2608.01409","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T17:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"7392c8d2d0d14878ef89f39578f58c3f3763e76e15292c1ca1514bf4568b3a65","abstract_canon_sha256":"1c7f7446a75fce88a63b6adfa920acd9ab192f4dc29c4696eff0c31a9160d8de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:05:10.323581Z","signature_b64":"nEimXFIpa4gfIlneYPxgoPx0VSVgfS3PabmWWNNIE5Jmr7oLjzM1oO+2QYnxvOUfQMgs2k1jIXhxDOYGPE2NCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eecc2056559fd2f4a647393ce3bc647dcf2bb9bb8dd7db0e90fec0f8a0062f64","last_reissued_at":"2026-08-04T02:05:10.321991Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:05:10.321991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Retrieval Helps and Distracts: Evaluating Evidence-Generating LLMs for Biomedical Claim Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Prabhjot Singh, Pritam Deka","submitted_at":"2026-08-02T17:43:28Z","abstract_excerpt":"Biomedical fact-checking systems must do more than predict whether a claim is supported, contradicted, or unaddressed: they should also produce evidence that is faithful, complete, and useful for verification. We study this evidence-generation setting on CARE-XAI, a unified benchmark spanning five biomedical and health fact-checking sources. We compare base instruction LLMs, PubMed retrieval-augmented LLMs, fine-tuned LLMs, label-only LLMs, and biomedical encoder classifiers under a shared evaluation protocol. Biomedical classifiers remain strongest for verdict-only prediction, while fine-tune"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01409","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/2608.01409/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":"2608.01409","created_at":"2026-08-04T02:05:10.323414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01409v1","created_at":"2026-08-04T02:05:10.323414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01409","created_at":"2026-08-04T02:05:10.323414+00:00"},{"alias_kind":"pith_short_12","alias_value":"53GCAVSVT7JP","created_at":"2026-08-04T02:05:10.323414+00:00"},{"alias_kind":"pith_short_16","alias_value":"53GCAVSVT7JPJJSH","created_at":"2026-08-04T02:05:10.323414+00:00"},{"alias_kind":"pith_short_8","alias_value":"53GCAVSV","created_at":"2026-08-04T02:05:10.323414+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/53GCAVSVT7JPJJSHHE6OHPDEPX","json":"https://pith.science/pith/53GCAVSVT7JPJJSHHE6OHPDEPX.json","graph_json":"https://pith.science/api/pith-number/53GCAVSVT7JPJJSHHE6OHPDEPX/graph.json","events_json":"https://pith.science/api/pith-number/53GCAVSVT7JPJJSHHE6OHPDEPX/events.json","paper":"https://pith.science/paper/53GCAVSV"},"agent_actions":{"view_html":"https://pith.science/pith/53GCAVSVT7JPJJSHHE6OHPDEPX","download_json":"https://pith.science/pith/53GCAVSVT7JPJJSHHE6OHPDEPX.json","view_paper":"https://pith.science/paper/53GCAVSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01409&json=true","fetch_graph":"https://pith.science/api/pith-number/53GCAVSVT7JPJJSHHE6OHPDEPX/graph.json","fetch_events":"https://pith.science/api/pith-number/53GCAVSVT7JPJJSHHE6OHPDEPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53GCAVSVT7JPJJSHHE6OHPDEPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53GCAVSVT7JPJJSHHE6OHPDEPX/action/storage_attestation","attest_author":"https://pith.science/pith/53GCAVSVT7JPJJSHHE6OHPDEPX/action/author_attestation","sign_citation":"https://pith.science/pith/53GCAVSVT7JPJJSHHE6OHPDEPX/action/citation_signature","submit_replication":"https://pith.science/pith/53GCAVSVT7JPJJSHHE6OHPDEPX/action/replication_record"}},"created_at":"2026-08-04T02:05:10.323414+00:00","updated_at":"2026-08-04T02:05:10.323414+00:00"}