{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MZJPPDUCYJIOGF3SN4OT7FMMLM","short_pith_number":"pith:MZJPPDUC","schema_version":"1.0","canonical_sha256":"6652f78e82c250e317726f1d3f958c5b2e0652c2234212e2ac807c2733438cda","source":{"kind":"arxiv","id":"2403.03888","version":3},"attestation_state":"computed","paper":{"title":"FaaF: Facts as a Function for the evaluation of generated text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gabor Barany, Vasileios Katranidis","submitted_at":"2024-03-06T17:48:06Z","abstract_excerpt":"The demand for accurate and efficient verification of information in texts generated by large language models (LMs) is at an all-time high, but remains unresolved. Recent efforts have focused on extracting and verifying atomic facts from these texts via prompting LM evaluators. However, we demonstrate that this method of prompting is unreliable when faced with incomplete or inaccurate reference information. We introduce Facts as a Function (FaaF), a new approach to the fact verification task that leverages the function-calling capabilities of LMs. FaaF significantly enhances the ability of LMs"},"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":"2403.03888","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T17:48:06Z","cross_cats_sorted":[],"title_canon_sha256":"903032afc2f9f5a3d5e6246d57b64572d7f73f3720b2eef4187a22202f7ef4f8","abstract_canon_sha256":"ef077a6cda2dd4f77446a770c67f40c2095b8493108bc9de3da09ab3035d8d20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:45.868080Z","signature_b64":"McmPO9Nt2UVBjCg5FdlVawx4hLa7g96tLGhKfPwpidCMYXsCQNolCcYTgOR6LZ3/saK2HJ+yvQjK9DlenMLSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6652f78e82c250e317726f1d3f958c5b2e0652c2234212e2ac807c2733438cda","last_reissued_at":"2026-07-05T09:10:45.867692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:45.867692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FaaF: Facts as a Function for the evaluation of generated text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gabor Barany, Vasileios Katranidis","submitted_at":"2024-03-06T17:48:06Z","abstract_excerpt":"The demand for accurate and efficient verification of information in texts generated by large language models (LMs) is at an all-time high, but remains unresolved. Recent efforts have focused on extracting and verifying atomic facts from these texts via prompting LM evaluators. However, we demonstrate that this method of prompting is unreliable when faced with incomplete or inaccurate reference information. We introduce Facts as a Function (FaaF), a new approach to the fact verification task that leverages the function-calling capabilities of LMs. FaaF significantly enhances the ability of LMs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03888","kind":"arxiv","version":3},"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/2403.03888/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":"2403.03888","created_at":"2026-07-05T09:10:45.867750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03888v3","created_at":"2026-07-05T09:10:45.867750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03888","created_at":"2026-07-05T09:10:45.867750+00:00"},{"alias_kind":"pith_short_12","alias_value":"MZJPPDUCYJIO","created_at":"2026-07-05T09:10:45.867750+00:00"},{"alias_kind":"pith_short_16","alias_value":"MZJPPDUCYJIOGF3S","created_at":"2026-07-05T09:10:45.867750+00:00"},{"alias_kind":"pith_short_8","alias_value":"MZJPPDUC","created_at":"2026-07-05T09:10:45.867750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.19710","citing_title":"Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systems","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MZJPPDUCYJIOGF3SN4OT7FMMLM","json":"https://pith.science/pith/MZJPPDUCYJIOGF3SN4OT7FMMLM.json","graph_json":"https://pith.science/api/pith-number/MZJPPDUCYJIOGF3SN4OT7FMMLM/graph.json","events_json":"https://pith.science/api/pith-number/MZJPPDUCYJIOGF3SN4OT7FMMLM/events.json","paper":"https://pith.science/paper/MZJPPDUC"},"agent_actions":{"view_html":"https://pith.science/pith/MZJPPDUCYJIOGF3SN4OT7FMMLM","download_json":"https://pith.science/pith/MZJPPDUCYJIOGF3SN4OT7FMMLM.json","view_paper":"https://pith.science/paper/MZJPPDUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03888&json=true","fetch_graph":"https://pith.science/api/pith-number/MZJPPDUCYJIOGF3SN4OT7FMMLM/graph.json","fetch_events":"https://pith.science/api/pith-number/MZJPPDUCYJIOGF3SN4OT7FMMLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MZJPPDUCYJIOGF3SN4OT7FMMLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MZJPPDUCYJIOGF3SN4OT7FMMLM/action/storage_attestation","attest_author":"https://pith.science/pith/MZJPPDUCYJIOGF3SN4OT7FMMLM/action/author_attestation","sign_citation":"https://pith.science/pith/MZJPPDUCYJIOGF3SN4OT7FMMLM/action/citation_signature","submit_replication":"https://pith.science/pith/MZJPPDUCYJIOGF3SN4OT7FMMLM/action/replication_record"}},"created_at":"2026-07-05T09:10:45.867750+00:00","updated_at":"2026-07-05T09:10:45.867750+00:00"}