{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MILJ6LRTAEX6642J5LVM6R4HMP","short_pith_number":"pith:MILJ6LRT","schema_version":"1.0","canonical_sha256":"62169f2e33012fef7349eaeacf478763e8c4e8fad53e5dde838ebd0faa9aedff","source":{"kind":"arxiv","id":"2406.15264","version":2},"attestation_state":"computed","paper":{"title":"Towards Fine-Grained Citation Evaluation in Generated Text: A Comparative Analysis of Faithfulness Metrics","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Evangelos Kanoulas, Jia-Hong Huang, Jiahuan Pei, Mohammad Aliannejadi, Weijia Zhang, Yifei Yuan","submitted_at":"2024-06-21T15:57:24Z","abstract_excerpt":"Large language models (LLMs) often produce unsupported or unverifiable content, known as \"hallucinations.\" To mitigate this, retrieval-augmented LLMs incorporate citations, grounding the content in verifiable sources. Despite such developments, manually assessing how well a citation supports the associated statement remains a major challenge. Previous studies use faithfulness metrics to estimate citation support automatically but are limited to binary classification, overlooking fine-grained citation support in practical scenarios. To investigate the effectiveness of faithfulness metrics in fi"},"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":"2406.15264","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-21T15:57:24Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"988ba63bc8ccc5178938b611a5917bdd45601b8c1e0e90e7dc92fc4599588693","abstract_canon_sha256":"968051448637c3e8dcca56147e749c11e3d2afdf35bc160de68ea3587c9c6e39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:24.925587Z","signature_b64":"5Q2rZkYHUY6BN6vpZWp69G1ZO9ahwVwo9ELeoNeIQeMbPh2PyBmo9ZmMLNfqYnInzXAomAw0kRqt1jNqJnOACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62169f2e33012fef7349eaeacf478763e8c4e8fad53e5dde838ebd0faa9aedff","last_reissued_at":"2026-07-05T08:58:24.925129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:24.925129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Fine-Grained Citation Evaluation in Generated Text: A Comparative Analysis of Faithfulness Metrics","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Evangelos Kanoulas, Jia-Hong Huang, Jiahuan Pei, Mohammad Aliannejadi, Weijia Zhang, Yifei Yuan","submitted_at":"2024-06-21T15:57:24Z","abstract_excerpt":"Large language models (LLMs) often produce unsupported or unverifiable content, known as \"hallucinations.\" To mitigate this, retrieval-augmented LLMs incorporate citations, grounding the content in verifiable sources. Despite such developments, manually assessing how well a citation supports the associated statement remains a major challenge. Previous studies use faithfulness metrics to estimate citation support automatically but are limited to binary classification, overlooking fine-grained citation support in practical scenarios. To investigate the effectiveness of faithfulness metrics in fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15264","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/2406.15264/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":"2406.15264","created_at":"2026-07-05T08:58:24.925187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15264v2","created_at":"2026-07-05T08:58:24.925187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15264","created_at":"2026-07-05T08:58:24.925187+00:00"},{"alias_kind":"pith_short_12","alias_value":"MILJ6LRTAEX6","created_at":"2026-07-05T08:58:24.925187+00:00"},{"alias_kind":"pith_short_16","alias_value":"MILJ6LRTAEX6642J","created_at":"2026-07-05T08:58:24.925187+00:00"},{"alias_kind":"pith_short_8","alias_value":"MILJ6LRT","created_at":"2026-07-05T08:58:24.925187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.21090","citing_title":"Training Large Language Models for Self-Explanation Faithfulness","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MILJ6LRTAEX6642J5LVM6R4HMP","json":"https://pith.science/pith/MILJ6LRTAEX6642J5LVM6R4HMP.json","graph_json":"https://pith.science/api/pith-number/MILJ6LRTAEX6642J5LVM6R4HMP/graph.json","events_json":"https://pith.science/api/pith-number/MILJ6LRTAEX6642J5LVM6R4HMP/events.json","paper":"https://pith.science/paper/MILJ6LRT"},"agent_actions":{"view_html":"https://pith.science/pith/MILJ6LRTAEX6642J5LVM6R4HMP","download_json":"https://pith.science/pith/MILJ6LRTAEX6642J5LVM6R4HMP.json","view_paper":"https://pith.science/paper/MILJ6LRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15264&json=true","fetch_graph":"https://pith.science/api/pith-number/MILJ6LRTAEX6642J5LVM6R4HMP/graph.json","fetch_events":"https://pith.science/api/pith-number/MILJ6LRTAEX6642J5LVM6R4HMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MILJ6LRTAEX6642J5LVM6R4HMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MILJ6LRTAEX6642J5LVM6R4HMP/action/storage_attestation","attest_author":"https://pith.science/pith/MILJ6LRTAEX6642J5LVM6R4HMP/action/author_attestation","sign_citation":"https://pith.science/pith/MILJ6LRTAEX6642J5LVM6R4HMP/action/citation_signature","submit_replication":"https://pith.science/pith/MILJ6LRTAEX6642J5LVM6R4HMP/action/replication_record"}},"created_at":"2026-07-05T08:58:24.925187+00:00","updated_at":"2026-07-05T08:58:24.925187+00:00"}