{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DC2GMVHGT4GMDZF2E35QKOM5FA","short_pith_number":"pith:DC2GMVHG","schema_version":"1.0","canonical_sha256":"18b46654e69f0cc1e4ba26fb05399d2806cb5e34f1ff51469812af5cfedb251c","source":{"kind":"arxiv","id":"2205.11465","version":1},"attestation_state":"computed","paper":{"title":"SQuALITY: Building a Long-Document Summarization Dataset the Hard Way","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alex Wang, Angelica Chen, Jason Phang, Richard Yuanzhe Pang, Samuel R. Bowman","submitted_at":"2022-05-23T17:02:07Z","abstract_excerpt":"Summarization datasets are often assembled either by scraping naturally occurring public-domain summaries -- which are nearly always in difficult-to-work-with technical domains -- or by using approximate heuristics to extract them from everyday text -- which frequently yields unfaithful summaries. In this work, we turn to a slower but more straightforward approach to developing summarization benchmark data: We hire highly-qualified contractors to read stories and write original summaries from scratch. To amortize reading time, we collect five summaries per document, with the first giving an ov"},"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":"2205.11465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T17:02:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7d1e23092b1943c5017764bbb59377e699d8b52c904158dc8ca4375e1d08169d","abstract_canon_sha256":"e7b199e23c5e19ec3a52befb3fe06f0bd9aa258029a71e320acca35e3bd56c2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:37.525183Z","signature_b64":"NB8DAYSxVJW6//35Rdm+2XaZHkHjny5INu3wgPvDmzJzmFKHqZlb4UPVBIYc1fPnTH4zDIboFm+Q5JbE4tteBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18b46654e69f0cc1e4ba26fb05399d2806cb5e34f1ff51469812af5cfedb251c","last_reissued_at":"2026-07-05T04:25:37.524815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:37.524815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SQuALITY: Building a Long-Document Summarization Dataset the Hard Way","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alex Wang, Angelica Chen, Jason Phang, Richard Yuanzhe Pang, Samuel R. Bowman","submitted_at":"2022-05-23T17:02:07Z","abstract_excerpt":"Summarization datasets are often assembled either by scraping naturally occurring public-domain summaries -- which are nearly always in difficult-to-work-with technical domains -- or by using approximate heuristics to extract them from everyday text -- which frequently yields unfaithful summaries. In this work, we turn to a slower but more straightforward approach to developing summarization benchmark data: We hire highly-qualified contractors to read stories and write original summaries from scratch. To amortize reading time, we collect five summaries per document, with the first giving an ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11465","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/2205.11465/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":"2205.11465","created_at":"2026-07-05T04:25:37.524872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11465v1","created_at":"2026-07-05T04:25:37.524872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11465","created_at":"2026-07-05T04:25:37.524872+00:00"},{"alias_kind":"pith_short_12","alias_value":"DC2GMVHGT4GM","created_at":"2026-07-05T04:25:37.524872+00:00"},{"alias_kind":"pith_short_16","alias_value":"DC2GMVHGT4GMDZF2","created_at":"2026-07-05T04:25:37.524872+00:00"},{"alias_kind":"pith_short_8","alias_value":"DC2GMVHG","created_at":"2026-07-05T04:25:37.524872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.01743","citing_title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","ref_index":46,"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":121,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DC2GMVHGT4GMDZF2E35QKOM5FA","json":"https://pith.science/pith/DC2GMVHGT4GMDZF2E35QKOM5FA.json","graph_json":"https://pith.science/api/pith-number/DC2GMVHGT4GMDZF2E35QKOM5FA/graph.json","events_json":"https://pith.science/api/pith-number/DC2GMVHGT4GMDZF2E35QKOM5FA/events.json","paper":"https://pith.science/paper/DC2GMVHG"},"agent_actions":{"view_html":"https://pith.science/pith/DC2GMVHGT4GMDZF2E35QKOM5FA","download_json":"https://pith.science/pith/DC2GMVHGT4GMDZF2E35QKOM5FA.json","view_paper":"https://pith.science/paper/DC2GMVHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11465&json=true","fetch_graph":"https://pith.science/api/pith-number/DC2GMVHGT4GMDZF2E35QKOM5FA/graph.json","fetch_events":"https://pith.science/api/pith-number/DC2GMVHGT4GMDZF2E35QKOM5FA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DC2GMVHGT4GMDZF2E35QKOM5FA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DC2GMVHGT4GMDZF2E35QKOM5FA/action/storage_attestation","attest_author":"https://pith.science/pith/DC2GMVHGT4GMDZF2E35QKOM5FA/action/author_attestation","sign_citation":"https://pith.science/pith/DC2GMVHGT4GMDZF2E35QKOM5FA/action/citation_signature","submit_replication":"https://pith.science/pith/DC2GMVHGT4GMDZF2E35QKOM5FA/action/replication_record"}},"created_at":"2026-07-05T04:25:37.524872+00:00","updated_at":"2026-07-05T04:25:37.524872+00:00"}