{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VEHWVNRVIY4QSCWR64SCYQH42Q","short_pith_number":"pith:VEHWVNRV","schema_version":"1.0","canonical_sha256":"a90f6ab6354639090ad1f7242c40fcd43eab540c4cfe196d4982ada9834331df","source":{"kind":"arxiv","id":"2401.04695","version":2},"attestation_state":"computed","paper":{"title":"Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gal Yona, Mor Geva, Roee Aharoni","submitted_at":"2024-01-09T17:44:36Z","abstract_excerpt":"Factual questions typically can be answered correctly at different levels of granularity. For example, both ``August 4, 1961'' and ``1961'' are correct answers to the question ``When was Barack Obama born?''. Standard question answering (QA) evaluation protocols, however, do not explicitly take this into account and compare a predicted answer against answers of a single granularity level. In this work, we propose GRANOLA QA, a novel evaluation setting where a predicted answer is evaluated in terms of accuracy and informativeness against a set of multi-granularity answers. We present a simple m"},"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":"2401.04695","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-09T17:44:36Z","cross_cats_sorted":[],"title_canon_sha256":"7d403fdf90e99090e1ab67d36ec9fd7defd653d62e37628854029fc41e3480b9","abstract_canon_sha256":"3fb26afe98d6f19cab9441da9c9675b8c4d7a96934bca4654806ef3a9b0c5f1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:53.270385Z","signature_b64":"R3jigBEaCuijxwY4+mPdiSUDz9263uySYKa2+4IyCl7rS+V/I1JpWkVsIjCYnqi1Io9LaH60NGsBiDM8Xv12Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a90f6ab6354639090ad1f7242c40fcd43eab540c4cfe196d4982ada9834331df","last_reissued_at":"2026-07-05T08:50:53.269862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:53.269862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gal Yona, Mor Geva, Roee Aharoni","submitted_at":"2024-01-09T17:44:36Z","abstract_excerpt":"Factual questions typically can be answered correctly at different levels of granularity. For example, both ``August 4, 1961'' and ``1961'' are correct answers to the question ``When was Barack Obama born?''. Standard question answering (QA) evaluation protocols, however, do not explicitly take this into account and compare a predicted answer against answers of a single granularity level. In this work, we propose GRANOLA QA, a novel evaluation setting where a predicted answer is evaluated in terms of accuracy and informativeness against a set of multi-granularity answers. We present a simple m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04695","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/2401.04695/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":"2401.04695","created_at":"2026-07-05T08:50:53.269916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04695v2","created_at":"2026-07-05T08:50:53.269916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04695","created_at":"2026-07-05T08:50:53.269916+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEHWVNRVIY4Q","created_at":"2026-07-05T08:50:53.269916+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEHWVNRVIY4QSCWR","created_at":"2026-07-05T08:50:53.269916+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEHWVNRV","created_at":"2026-07-05T08:50:53.269916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEHWVNRVIY4QSCWR64SCYQH42Q","json":"https://pith.science/pith/VEHWVNRVIY4QSCWR64SCYQH42Q.json","graph_json":"https://pith.science/api/pith-number/VEHWVNRVIY4QSCWR64SCYQH42Q/graph.json","events_json":"https://pith.science/api/pith-number/VEHWVNRVIY4QSCWR64SCYQH42Q/events.json","paper":"https://pith.science/paper/VEHWVNRV"},"agent_actions":{"view_html":"https://pith.science/pith/VEHWVNRVIY4QSCWR64SCYQH42Q","download_json":"https://pith.science/pith/VEHWVNRVIY4QSCWR64SCYQH42Q.json","view_paper":"https://pith.science/paper/VEHWVNRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04695&json=true","fetch_graph":"https://pith.science/api/pith-number/VEHWVNRVIY4QSCWR64SCYQH42Q/graph.json","fetch_events":"https://pith.science/api/pith-number/VEHWVNRVIY4QSCWR64SCYQH42Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEHWVNRVIY4QSCWR64SCYQH42Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEHWVNRVIY4QSCWR64SCYQH42Q/action/storage_attestation","attest_author":"https://pith.science/pith/VEHWVNRVIY4QSCWR64SCYQH42Q/action/author_attestation","sign_citation":"https://pith.science/pith/VEHWVNRVIY4QSCWR64SCYQH42Q/action/citation_signature","submit_replication":"https://pith.science/pith/VEHWVNRVIY4QSCWR64SCYQH42Q/action/replication_record"}},"created_at":"2026-07-05T08:50:53.269916+00:00","updated_at":"2026-07-05T08:50:53.269916+00:00"}