{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GK7TAAU4OSBHMR5C4OKK2GRKQQ","short_pith_number":"pith:GK7TAAU4","schema_version":"1.0","canonical_sha256":"32bf30029c74827647a2e394ad1a2a84272f0928738a558d3451e14972c18aa6","source":{"kind":"arxiv","id":"2102.07033","version":1},"attestation_state":"computed","paper":{"title":"PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aleksandra Piktus, Heinrich K\\\"uttler, Linqing Liu, Pasquale Minervini, Patrick Lewis, Pontus Stenetorp, Sebastian Riedel, Yuxiang WU","submitted_at":"2021-02-13T23:43:45Z","abstract_excerpt":"Open-domain Question Answering models which directly leverage question-answer (QA) pairs, such as closed-book QA (CBQA) models and QA-pair retrievers, show promise in terms of speed and memory compared to conventional models which retrieve and read from text corpora. QA-pair retrievers also offer interpretable answers, a high degree of control, and are trivial to update at test time with new knowledge. However, these models lack the accuracy of retrieve-and-read systems, as substantially less knowledge is covered by the available QA-pairs relative to text corpora like Wikipedia. To facilitate "},"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":"2102.07033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-13T23:43:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e556bc956185f654477aec4401d851549a87496ae2405eda16fae9ca74d99e21","abstract_canon_sha256":"df00b75e814206e9991a18ad120adac91f8ff693476bb0a4f67ee1cf49987976"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:00.754877Z","signature_b64":"kYnDBHzg8Bz4yJTXu+n6VI2qS9Zcy50hHHZyQdJ3BvRNMcLUWBWCsADsywmxJbC/5f8UskhpgG3+IpjTjOK9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32bf30029c74827647a2e394ad1a2a84272f0928738a558d3451e14972c18aa6","last_reissued_at":"2026-07-05T02:15:00.754350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:00.754350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aleksandra Piktus, Heinrich K\\\"uttler, Linqing Liu, Pasquale Minervini, Patrick Lewis, Pontus Stenetorp, Sebastian Riedel, Yuxiang WU","submitted_at":"2021-02-13T23:43:45Z","abstract_excerpt":"Open-domain Question Answering models which directly leverage question-answer (QA) pairs, such as closed-book QA (CBQA) models and QA-pair retrievers, show promise in terms of speed and memory compared to conventional models which retrieve and read from text corpora. QA-pair retrievers also offer interpretable answers, a high degree of control, and are trivial to update at test time with new knowledge. However, these models lack the accuracy of retrieve-and-read systems, as substantially less knowledge is covered by the available QA-pairs relative to text corpora like Wikipedia. To facilitate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07033","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/2102.07033/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":"2102.07033","created_at":"2026-07-05T02:15:00.754408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.07033v1","created_at":"2026-07-05T02:15:00.754408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07033","created_at":"2026-07-05T02:15:00.754408+00:00"},{"alias_kind":"pith_short_12","alias_value":"GK7TAAU4OSBH","created_at":"2026-07-05T02:15:00.754408+00:00"},{"alias_kind":"pith_short_16","alias_value":"GK7TAAU4OSBHMR5C","created_at":"2026-07-05T02:15:00.754408+00:00"},{"alias_kind":"pith_short_8","alias_value":"GK7TAAU4","created_at":"2026-07-05T02:15:00.754408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2303.09014","citing_title":"ART: Automatic multi-step reasoning and tool-use for large language models","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GK7TAAU4OSBHMR5C4OKK2GRKQQ","json":"https://pith.science/pith/GK7TAAU4OSBHMR5C4OKK2GRKQQ.json","graph_json":"https://pith.science/api/pith-number/GK7TAAU4OSBHMR5C4OKK2GRKQQ/graph.json","events_json":"https://pith.science/api/pith-number/GK7TAAU4OSBHMR5C4OKK2GRKQQ/events.json","paper":"https://pith.science/paper/GK7TAAU4"},"agent_actions":{"view_html":"https://pith.science/pith/GK7TAAU4OSBHMR5C4OKK2GRKQQ","download_json":"https://pith.science/pith/GK7TAAU4OSBHMR5C4OKK2GRKQQ.json","view_paper":"https://pith.science/paper/GK7TAAU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.07033&json=true","fetch_graph":"https://pith.science/api/pith-number/GK7TAAU4OSBHMR5C4OKK2GRKQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/GK7TAAU4OSBHMR5C4OKK2GRKQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GK7TAAU4OSBHMR5C4OKK2GRKQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GK7TAAU4OSBHMR5C4OKK2GRKQQ/action/storage_attestation","attest_author":"https://pith.science/pith/GK7TAAU4OSBHMR5C4OKK2GRKQQ/action/author_attestation","sign_citation":"https://pith.science/pith/GK7TAAU4OSBHMR5C4OKK2GRKQQ/action/citation_signature","submit_replication":"https://pith.science/pith/GK7TAAU4OSBHMR5C4OKK2GRKQQ/action/replication_record"}},"created_at":"2026-07-05T02:15:00.754408+00:00","updated_at":"2026-07-05T02:15:00.754408+00:00"}