{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5VMOKKOI46QIWOP3L7V7MCG47O","short_pith_number":"pith:5VMOKKOI","schema_version":"1.0","canonical_sha256":"ed58e529c8e7a08b39fb5febf608dcfb858947c0e953e2bf668f2f856ee91b9b","source":{"kind":"arxiv","id":"2301.13298","version":1},"attestation_state":"computed","paper":{"title":"LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Bailey Kuehl, Erin Bransom, Kalpesh Krishna, Kyle Lo, Mohit Iyyer, Pradeep Dasigi","submitted_at":"2023-01-30T21:31:48Z","abstract_excerpt":"While human evaluation remains best practice for accurately judging the faithfulness of automatically-generated summaries, few solutions exist to address the increased difficulty and workload when evaluating long-form summaries. Through a survey of 162 papers on long-form summarization, we first shed light on current human evaluation practices surrounding long-form summaries. We find that 73% of these papers do not perform any human evaluation on model-generated summaries, while other works face new difficulties that manifest when dealing with long documents (e.g., low inter-annotator agreemen"},"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":"2301.13298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-30T21:31:48Z","cross_cats_sorted":[],"title_canon_sha256":"1751a165310bdf6e146cca85f2e564c984e9d7e63a8f2f819a452cb9bac67977","abstract_canon_sha256":"29461409757b5fc0e08cce7f62293777f25e0cf687fc4d44069b63e3227b30f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:13.406676Z","signature_b64":"aTRbMSN6sSAqCUcOP0DSChwEo41mavk0aoldpD8VVvzxFo+KfxrFdgR6Gh9dvgIa759BdXkFTR6OZk8AycVMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed58e529c8e7a08b39fb5febf608dcfb858947c0e953e2bf668f2f856ee91b9b","last_reissued_at":"2026-07-05T05:37:13.406199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:13.406199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Bailey Kuehl, Erin Bransom, Kalpesh Krishna, Kyle Lo, Mohit Iyyer, Pradeep Dasigi","submitted_at":"2023-01-30T21:31:48Z","abstract_excerpt":"While human evaluation remains best practice for accurately judging the faithfulness of automatically-generated summaries, few solutions exist to address the increased difficulty and workload when evaluating long-form summaries. Through a survey of 162 papers on long-form summarization, we first shed light on current human evaluation practices surrounding long-form summaries. We find that 73% of these papers do not perform any human evaluation on model-generated summaries, while other works face new difficulties that manifest when dealing with long documents (e.g., low inter-annotator agreemen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13298","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/2301.13298/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":"2301.13298","created_at":"2026-07-05T05:37:13.406255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13298v1","created_at":"2026-07-05T05:37:13.406255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13298","created_at":"2026-07-05T05:37:13.406255+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VMOKKOI46QI","created_at":"2026-07-05T05:37:13.406255+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VMOKKOI46QIWOP3","created_at":"2026-07-05T05:37:13.406255+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VMOKKOI","created_at":"2026-07-05T05:37:13.406255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21734","citing_title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","ref_index":179,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22748","citing_title":"AI Fiction in the Wild","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20131","citing_title":"Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives","ref_index":169,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5VMOKKOI46QIWOP3L7V7MCG47O","json":"https://pith.science/pith/5VMOKKOI46QIWOP3L7V7MCG47O.json","graph_json":"https://pith.science/api/pith-number/5VMOKKOI46QIWOP3L7V7MCG47O/graph.json","events_json":"https://pith.science/api/pith-number/5VMOKKOI46QIWOP3L7V7MCG47O/events.json","paper":"https://pith.science/paper/5VMOKKOI"},"agent_actions":{"view_html":"https://pith.science/pith/5VMOKKOI46QIWOP3L7V7MCG47O","download_json":"https://pith.science/pith/5VMOKKOI46QIWOP3L7V7MCG47O.json","view_paper":"https://pith.science/paper/5VMOKKOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13298&json=true","fetch_graph":"https://pith.science/api/pith-number/5VMOKKOI46QIWOP3L7V7MCG47O/graph.json","fetch_events":"https://pith.science/api/pith-number/5VMOKKOI46QIWOP3L7V7MCG47O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VMOKKOI46QIWOP3L7V7MCG47O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VMOKKOI46QIWOP3L7V7MCG47O/action/storage_attestation","attest_author":"https://pith.science/pith/5VMOKKOI46QIWOP3L7V7MCG47O/action/author_attestation","sign_citation":"https://pith.science/pith/5VMOKKOI46QIWOP3L7V7MCG47O/action/citation_signature","submit_replication":"https://pith.science/pith/5VMOKKOI46QIWOP3L7V7MCG47O/action/replication_record"}},"created_at":"2026-07-05T05:37:13.406255+00:00","updated_at":"2026-07-05T05:37:13.406255+00:00"}