{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WZ2422MT3ALW4N2KPOQ5YQSWGW","short_pith_number":"pith:WZ2422MT","schema_version":"1.0","canonical_sha256":"b675cd6993d8176e374a7ba1dc425635b42d57e36dfed9f57d43f89397aaac87","source":{"kind":"arxiv","id":"2010.00490","version":3},"attestation_state":"computed","paper":{"title":"Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Deutsch, Dan Roth, Tania Bedrax-Weiss","submitted_at":"2020-10-01T15:33:09Z","abstract_excerpt":"A desirable property of a reference-based evaluation metric that measures the content quality of a summary is that it should estimate how much information that summary has in common with a reference. Traditional text overlap based metrics such as ROUGE fail to achieve this because they are limited to matching tokens, either lexically or via embeddings. In this work, we propose a metric to evaluate the content quality of a summary using question-answering (QA). QA-based methods directly measure a summary's information overlap with a reference, making them fundamentally different than text overl"},"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":"2010.00490","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-01T15:33:09Z","cross_cats_sorted":[],"title_canon_sha256":"e874303967a8225f847fe8a321ef7e4480b9eaeb80cc6a76ae171a9588f17ac0","abstract_canon_sha256":"f2e093409ac0663f44b8e01c0a4a919ab97d3cc66de5e2ad4d0d619cf34319f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:46.435963Z","signature_b64":"Drr68tze11weMikTa8WDENsQFUueqpfxaytKvoecrEBqvaZryu/XbfrMCIakbcSx0G9iVF7QWANvly0JJ6CFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b675cd6993d8176e374a7ba1dc425635b42d57e36dfed9f57d43f89397aaac87","last_reissued_at":"2026-07-05T03:00:46.435517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:46.435517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Deutsch, Dan Roth, Tania Bedrax-Weiss","submitted_at":"2020-10-01T15:33:09Z","abstract_excerpt":"A desirable property of a reference-based evaluation metric that measures the content quality of a summary is that it should estimate how much information that summary has in common with a reference. Traditional text overlap based metrics such as ROUGE fail to achieve this because they are limited to matching tokens, either lexically or via embeddings. In this work, we propose a metric to evaluate the content quality of a summary using question-answering (QA). QA-based methods directly measure a summary's information overlap with a reference, making them fundamentally different than text overl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.00490","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/2010.00490/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":"2010.00490","created_at":"2026-07-05T03:00:46.435574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.00490v3","created_at":"2026-07-05T03:00:46.435574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.00490","created_at":"2026-07-05T03:00:46.435574+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZ2422MT3ALW","created_at":"2026-07-05T03:00:46.435574+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZ2422MT3ALW4N2K","created_at":"2026-07-05T03:00:46.435574+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZ2422MT","created_at":"2026-07-05T03:00:46.435574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14905","citing_title":"Measuring and Mitigating Hallucinations in Vision-Language Dataset Generation for Remote Sensing","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZ2422MT3ALW4N2KPOQ5YQSWGW","json":"https://pith.science/pith/WZ2422MT3ALW4N2KPOQ5YQSWGW.json","graph_json":"https://pith.science/api/pith-number/WZ2422MT3ALW4N2KPOQ5YQSWGW/graph.json","events_json":"https://pith.science/api/pith-number/WZ2422MT3ALW4N2KPOQ5YQSWGW/events.json","paper":"https://pith.science/paper/WZ2422MT"},"agent_actions":{"view_html":"https://pith.science/pith/WZ2422MT3ALW4N2KPOQ5YQSWGW","download_json":"https://pith.science/pith/WZ2422MT3ALW4N2KPOQ5YQSWGW.json","view_paper":"https://pith.science/paper/WZ2422MT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.00490&json=true","fetch_graph":"https://pith.science/api/pith-number/WZ2422MT3ALW4N2KPOQ5YQSWGW/graph.json","fetch_events":"https://pith.science/api/pith-number/WZ2422MT3ALW4N2KPOQ5YQSWGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZ2422MT3ALW4N2KPOQ5YQSWGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZ2422MT3ALW4N2KPOQ5YQSWGW/action/storage_attestation","attest_author":"https://pith.science/pith/WZ2422MT3ALW4N2KPOQ5YQSWGW/action/author_attestation","sign_citation":"https://pith.science/pith/WZ2422MT3ALW4N2KPOQ5YQSWGW/action/citation_signature","submit_replication":"https://pith.science/pith/WZ2422MT3ALW4N2KPOQ5YQSWGW/action/replication_record"}},"created_at":"2026-07-05T03:00:46.435574+00:00","updated_at":"2026-07-05T03:00:46.435574+00:00"}