{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S2BBTGYBR2PI7BGWCAQHPYW2Y2","short_pith_number":"pith:S2BBTGYB","schema_version":"1.0","canonical_sha256":"9682199b018e9e8f84d6102077e2dac6a0eda69d5c507c3abe977073eabd3e09","source":{"kind":"arxiv","id":"2411.05375","version":2},"attestation_state":"computed","paper":{"title":"Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andreas Vlachos, Michael Schlichtkrull, Mubashara Akhtar","submitted_at":"2024-11-08T07:05:06Z","abstract_excerpt":"Current automated fact-checking (AFC) approaches typically evaluate evidence either implicitly via the predicted verdicts or through exact matches with predefined closed knowledge sources, such as Wikipedia. However, these methods are limited due to their reliance on evaluation metrics originally designed for other purposes and constraints from closed knowledge sources. In this work, we introduce \\textbf{\\textcolor{skyblue}{Ev\\textsuperscript{2}}\\textcolor{orangebrown}{R}} which combines the strengths of reference-based evaluation and verdict-level proxy scoring. Ev\\textsuperscript{2}R jointly"},"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":"2411.05375","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-08T07:05:06Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"9921a3bbf911da0b17690d1f83370db190deed8b051ef956095fbad051b7db2b","abstract_canon_sha256":"56add7c53d38662aaa1c00a4821f9b9ca7faec5677d1c5cc446500bf58329bbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:45.441206Z","signature_b64":"hwBknwVmFVNE5pEMz2n6JlptsD1f6gkLsQBd5+XxF74mnj3JBUs2Mdz2dB5dqc3Scl+ik9mQGQpJKteMstlVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9682199b018e9e8f84d6102077e2dac6a0eda69d5c507c3abe977073eabd3e09","last_reissued_at":"2026-07-05T11:39:45.440597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:45.440597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andreas Vlachos, Michael Schlichtkrull, Mubashara Akhtar","submitted_at":"2024-11-08T07:05:06Z","abstract_excerpt":"Current automated fact-checking (AFC) approaches typically evaluate evidence either implicitly via the predicted verdicts or through exact matches with predefined closed knowledge sources, such as Wikipedia. However, these methods are limited due to their reliance on evaluation metrics originally designed for other purposes and constraints from closed knowledge sources. In this work, we introduce \\textbf{\\textcolor{skyblue}{Ev\\textsuperscript{2}}\\textcolor{orangebrown}{R}} which combines the strengths of reference-based evaluation and verdict-level proxy scoring. Ev\\textsuperscript{2}R jointly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05375","kind":"arxiv","version":2},"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/2411.05375/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":"2411.05375","created_at":"2026-07-05T11:39:45.440657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05375v2","created_at":"2026-07-05T11:39:45.440657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05375","created_at":"2026-07-05T11:39:45.440657+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2BBTGYBR2PI","created_at":"2026-07-05T11:39:45.440657+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2BBTGYBR2PI7BGW","created_at":"2026-07-05T11:39:45.440657+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2BBTGYB","created_at":"2026-07-05T11:39:45.440657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07101","citing_title":"CANote: Empowering Fact-checking Note Writing Through Scaffolded and Provenance-based Human-AI Collaboration","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01101","citing_title":"TSVer: A Benchmark for Fact Verification Against Time-Series Evidence","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S2BBTGYBR2PI7BGWCAQHPYW2Y2","json":"https://pith.science/pith/S2BBTGYBR2PI7BGWCAQHPYW2Y2.json","graph_json":"https://pith.science/api/pith-number/S2BBTGYBR2PI7BGWCAQHPYW2Y2/graph.json","events_json":"https://pith.science/api/pith-number/S2BBTGYBR2PI7BGWCAQHPYW2Y2/events.json","paper":"https://pith.science/paper/S2BBTGYB"},"agent_actions":{"view_html":"https://pith.science/pith/S2BBTGYBR2PI7BGWCAQHPYW2Y2","download_json":"https://pith.science/pith/S2BBTGYBR2PI7BGWCAQHPYW2Y2.json","view_paper":"https://pith.science/paper/S2BBTGYB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05375&json=true","fetch_graph":"https://pith.science/api/pith-number/S2BBTGYBR2PI7BGWCAQHPYW2Y2/graph.json","fetch_events":"https://pith.science/api/pith-number/S2BBTGYBR2PI7BGWCAQHPYW2Y2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2BBTGYBR2PI7BGWCAQHPYW2Y2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2BBTGYBR2PI7BGWCAQHPYW2Y2/action/storage_attestation","attest_author":"https://pith.science/pith/S2BBTGYBR2PI7BGWCAQHPYW2Y2/action/author_attestation","sign_citation":"https://pith.science/pith/S2BBTGYBR2PI7BGWCAQHPYW2Y2/action/citation_signature","submit_replication":"https://pith.science/pith/S2BBTGYBR2PI7BGWCAQHPYW2Y2/action/replication_record"}},"created_at":"2026-07-05T11:39:45.440657+00:00","updated_at":"2026-07-05T11:39:45.440657+00:00"}