{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7MLYLL2RDXDWK63JH7EC2P6VA6","short_pith_number":"pith:7MLYLL2R","schema_version":"1.0","canonical_sha256":"fb1785af511dc7657b693fc82d3fd507ac68bcbf867591efaff4b413ab2d17ad","source":{"kind":"arxiv","id":"2403.05217","version":1},"attestation_state":"computed","paper":{"title":"Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Cheng Tai, Chengwei Wu, Haiyu Yan, Hongda Sun, Rui Yan, Shuo Shang, Xin Gao, Yuxuan Liu","submitted_at":"2024-03-08T11:09:13Z","abstract_excerpt":"Open-domain question answering (ODQA) has emerged as a pivotal research spotlight in information systems. Existing methods follow two main paradigms to collect evidence: (1) The \\textit{retrieve-then-read} paradigm retrieves pertinent documents from an external corpus; and (2) the \\textit{generate-then-read} paradigm employs large language models (LLMs) to generate relevant documents. However, neither can fully address multifaceted requirements for evidence. To this end, we propose LLMQA, a generalized framework that formulates the ODQA process into three basic steps: query expansion, document"},"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":"2403.05217","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-08T11:09:13Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"748367dc088eefd3fdc6dad9d9d6658d402b8a7ea486688e3b3913290f12e01e","abstract_canon_sha256":"1a4155b5ee07ff45b57c71de216cb9c2f7b19162b12b34212175a81a70fa0c83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:52.412830Z","signature_b64":"iUqmcvHPDJCZCSKnknQqLK/3pGAdSi1U4tAxTL26WRAZkmkYiQ3irtzxeX7E26Kk/lOKQjin1XkIwcx1Jsy2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb1785af511dc7657b693fc82d3fd507ac68bcbf867591efaff4b413ab2d17ad","last_reissued_at":"2026-07-05T07:53:52.412458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:52.412458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Cheng Tai, Chengwei Wu, Haiyu Yan, Hongda Sun, Rui Yan, Shuo Shang, Xin Gao, Yuxuan Liu","submitted_at":"2024-03-08T11:09:13Z","abstract_excerpt":"Open-domain question answering (ODQA) has emerged as a pivotal research spotlight in information systems. Existing methods follow two main paradigms to collect evidence: (1) The \\textit{retrieve-then-read} paradigm retrieves pertinent documents from an external corpus; and (2) the \\textit{generate-then-read} paradigm employs large language models (LLMs) to generate relevant documents. However, neither can fully address multifaceted requirements for evidence. To this end, we propose LLMQA, a generalized framework that formulates the ODQA process into three basic steps: query expansion, document"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05217","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/2403.05217/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":"2403.05217","created_at":"2026-07-05T07:53:52.412515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05217v1","created_at":"2026-07-05T07:53:52.412515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05217","created_at":"2026-07-05T07:53:52.412515+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MLYLL2RDXDW","created_at":"2026-07-05T07:53:52.412515+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MLYLL2RDXDWK63J","created_at":"2026-07-05T07:53:52.412515+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MLYLL2R","created_at":"2026-07-05T07:53:52.412515+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/7MLYLL2RDXDWK63JH7EC2P6VA6","json":"https://pith.science/pith/7MLYLL2RDXDWK63JH7EC2P6VA6.json","graph_json":"https://pith.science/api/pith-number/7MLYLL2RDXDWK63JH7EC2P6VA6/graph.json","events_json":"https://pith.science/api/pith-number/7MLYLL2RDXDWK63JH7EC2P6VA6/events.json","paper":"https://pith.science/paper/7MLYLL2R"},"agent_actions":{"view_html":"https://pith.science/pith/7MLYLL2RDXDWK63JH7EC2P6VA6","download_json":"https://pith.science/pith/7MLYLL2RDXDWK63JH7EC2P6VA6.json","view_paper":"https://pith.science/paper/7MLYLL2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05217&json=true","fetch_graph":"https://pith.science/api/pith-number/7MLYLL2RDXDWK63JH7EC2P6VA6/graph.json","fetch_events":"https://pith.science/api/pith-number/7MLYLL2RDXDWK63JH7EC2P6VA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MLYLL2RDXDWK63JH7EC2P6VA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MLYLL2RDXDWK63JH7EC2P6VA6/action/storage_attestation","attest_author":"https://pith.science/pith/7MLYLL2RDXDWK63JH7EC2P6VA6/action/author_attestation","sign_citation":"https://pith.science/pith/7MLYLL2RDXDWK63JH7EC2P6VA6/action/citation_signature","submit_replication":"https://pith.science/pith/7MLYLL2RDXDWK63JH7EC2P6VA6/action/replication_record"}},"created_at":"2026-07-05T07:53:52.412515+00:00","updated_at":"2026-07-05T07:53:52.412515+00:00"}