{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FZC6UQAIYRAZDRS4RTCXZB3W2V","short_pith_number":"pith:FZC6UQAI","schema_version":"1.0","canonical_sha256":"2e45ea4008c44191c65c8cc57c8776d57f46f084cd0e0bf8ab961af49d84df4f","source":{"kind":"arxiv","id":"2307.16883","version":1},"attestation_state":"computed","paper":{"title":"HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Aref Jafari, Ehsan Kamalloo, Jimmy Lin, Nandan Thakur, Xinyu Zhang","submitted_at":"2023-07-31T17:49:18Z","abstract_excerpt":"The rise of large language models (LLMs) had a transformative impact on search, ushering in a new era of search engines that are capable of generating search results in natural language text, imbued with citations for supporting sources. Building generative information-seeking models demands openly accessible datasets, which currently remain lacking. In this paper, we introduce a new dataset, HAGRID (Human-in-the-loop Attributable Generative Retrieval for Information-seeking Dataset) for building end-to-end generative information-seeking models that are capable of retrieving candidate quotes a"},"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":"2307.16883","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-31T17:49:18Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"d4b8031e705da93798b74f90472defdc8a1967c9c5daf15136dd2af805abbf61","abstract_canon_sha256":"690fae6688e11495c5cf650c00f90b9c89aab4d20716707be7534a48ee5e3a10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:09.333914Z","signature_b64":"Kqi3ggVNd9TOfpQpbx6riOv6nzDA0AB6slmPE4b+t7UqvVYgfRx9lOLkwPW4UvsIF7J8B8TzYhJRgdkulYqtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e45ea4008c44191c65c8cc57c8776d57f46f084cd0e0bf8ab961af49d84df4f","last_reissued_at":"2026-07-05T06:36:09.333441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:09.333441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Aref Jafari, Ehsan Kamalloo, Jimmy Lin, Nandan Thakur, Xinyu Zhang","submitted_at":"2023-07-31T17:49:18Z","abstract_excerpt":"The rise of large language models (LLMs) had a transformative impact on search, ushering in a new era of search engines that are capable of generating search results in natural language text, imbued with citations for supporting sources. Building generative information-seeking models demands openly accessible datasets, which currently remain lacking. In this paper, we introduce a new dataset, HAGRID (Human-in-the-loop Attributable Generative Retrieval for Information-seeking Dataset) for building end-to-end generative information-seeking models that are capable of retrieving candidate quotes a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16883","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/2307.16883/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":"2307.16883","created_at":"2026-07-05T06:36:09.333496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16883v1","created_at":"2026-07-05T06:36:09.333496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16883","created_at":"2026-07-05T06:36:09.333496+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZC6UQAIYRAZ","created_at":"2026-07-05T06:36:09.333496+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZC6UQAIYRAZDRS4","created_at":"2026-07-05T06:36:09.333496+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZC6UQAI","created_at":"2026-07-05T06:36:09.333496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23915","citing_title":"Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28615","citing_title":"What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2406.19741","citing_title":"ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2506.17585","citing_title":"Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZC6UQAIYRAZDRS4RTCXZB3W2V","json":"https://pith.science/pith/FZC6UQAIYRAZDRS4RTCXZB3W2V.json","graph_json":"https://pith.science/api/pith-number/FZC6UQAIYRAZDRS4RTCXZB3W2V/graph.json","events_json":"https://pith.science/api/pith-number/FZC6UQAIYRAZDRS4RTCXZB3W2V/events.json","paper":"https://pith.science/paper/FZC6UQAI"},"agent_actions":{"view_html":"https://pith.science/pith/FZC6UQAIYRAZDRS4RTCXZB3W2V","download_json":"https://pith.science/pith/FZC6UQAIYRAZDRS4RTCXZB3W2V.json","view_paper":"https://pith.science/paper/FZC6UQAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16883&json=true","fetch_graph":"https://pith.science/api/pith-number/FZC6UQAIYRAZDRS4RTCXZB3W2V/graph.json","fetch_events":"https://pith.science/api/pith-number/FZC6UQAIYRAZDRS4RTCXZB3W2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZC6UQAIYRAZDRS4RTCXZB3W2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZC6UQAIYRAZDRS4RTCXZB3W2V/action/storage_attestation","attest_author":"https://pith.science/pith/FZC6UQAIYRAZDRS4RTCXZB3W2V/action/author_attestation","sign_citation":"https://pith.science/pith/FZC6UQAIYRAZDRS4RTCXZB3W2V/action/citation_signature","submit_replication":"https://pith.science/pith/FZC6UQAIYRAZDRS4RTCXZB3W2V/action/replication_record"}},"created_at":"2026-07-05T06:36:09.333496+00:00","updated_at":"2026-07-05T06:36:09.333496+00:00"}