{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DULSWRVDKDLO7NJUAW4WWB5Z65","short_pith_number":"pith:DULSWRVD","schema_version":"1.0","canonical_sha256":"1d172b46a350d6efb53405b96b07b9f7629fbe1e1b245e722aa019088a8d5598","source":{"kind":"arxiv","id":"2506.22356","version":1},"attestation_state":"computed","paper":{"title":"HLTCOE at LiveRAG: GPT-Researcher using ColBERT retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Dawn Lawrie, Eugene Yang, Kevin Duh, Orion Weller","submitted_at":"2025-06-27T16:08:39Z","abstract_excerpt":"The HLTCOE LiveRAG submission utilized the GPT-researcher framework for researching the context of the question, filtering the returned results, and generating the final answer. The retrieval system was a ColBERT bi-encoder architecture, which represents a passage with many dense tokens. Retrieval used a local, compressed index of the FineWeb10-BT collection created with PLAID-X, using a model fine-tuned for multilingual retrieval. Query generation from context was done with Qwen2.5-7B-Instruct, while filtering was accomplished with m2-bert-80M-8k-retrieval. Up to nine passages were used as co"},"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":"2506.22356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-27T16:08:39Z","cross_cats_sorted":[],"title_canon_sha256":"c98d0432307af2913c52805b788705636004bbc4b925496ff7210380099c9770","abstract_canon_sha256":"5430629577b1675b90bf98340a440f942c3c0b68b7fa9d8cd479e0dfb4c25b0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:25.762621Z","signature_b64":"X3caE0a/lCAPnPgk/SHJ0Im1VdwhTEffKzXavKpk8KhECJBp7B4cRfsNc+gUel1fj6/CbyOhAacl8w8HVBzzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d172b46a350d6efb53405b96b07b9f7629fbe1e1b245e722aa019088a8d5598","last_reissued_at":"2026-07-05T11:28:25.762118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:25.762118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HLTCOE at LiveRAG: GPT-Researcher using ColBERT retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Dawn Lawrie, Eugene Yang, Kevin Duh, Orion Weller","submitted_at":"2025-06-27T16:08:39Z","abstract_excerpt":"The HLTCOE LiveRAG submission utilized the GPT-researcher framework for researching the context of the question, filtering the returned results, and generating the final answer. The retrieval system was a ColBERT bi-encoder architecture, which represents a passage with many dense tokens. Retrieval used a local, compressed index of the FineWeb10-BT collection created with PLAID-X, using a model fine-tuned for multilingual retrieval. Query generation from context was done with Qwen2.5-7B-Instruct, while filtering was accomplished with m2-bert-80M-8k-retrieval. Up to nine passages were used as co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22356","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/2506.22356/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":"2506.22356","created_at":"2026-07-05T11:28:25.762185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22356v1","created_at":"2026-07-05T11:28:25.762185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22356","created_at":"2026-07-05T11:28:25.762185+00:00"},{"alias_kind":"pith_short_12","alias_value":"DULSWRVDKDLO","created_at":"2026-07-05T11:28:25.762185+00:00"},{"alias_kind":"pith_short_16","alias_value":"DULSWRVDKDLO7NJU","created_at":"2026-07-05T11:28:25.762185+00:00"},{"alias_kind":"pith_short_8","alias_value":"DULSWRVD","created_at":"2026-07-05T11:28:25.762185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.08819","citing_title":"Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DULSWRVDKDLO7NJUAW4WWB5Z65","json":"https://pith.science/pith/DULSWRVDKDLO7NJUAW4WWB5Z65.json","graph_json":"https://pith.science/api/pith-number/DULSWRVDKDLO7NJUAW4WWB5Z65/graph.json","events_json":"https://pith.science/api/pith-number/DULSWRVDKDLO7NJUAW4WWB5Z65/events.json","paper":"https://pith.science/paper/DULSWRVD"},"agent_actions":{"view_html":"https://pith.science/pith/DULSWRVDKDLO7NJUAW4WWB5Z65","download_json":"https://pith.science/pith/DULSWRVDKDLO7NJUAW4WWB5Z65.json","view_paper":"https://pith.science/paper/DULSWRVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22356&json=true","fetch_graph":"https://pith.science/api/pith-number/DULSWRVDKDLO7NJUAW4WWB5Z65/graph.json","fetch_events":"https://pith.science/api/pith-number/DULSWRVDKDLO7NJUAW4WWB5Z65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DULSWRVDKDLO7NJUAW4WWB5Z65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DULSWRVDKDLO7NJUAW4WWB5Z65/action/storage_attestation","attest_author":"https://pith.science/pith/DULSWRVDKDLO7NJUAW4WWB5Z65/action/author_attestation","sign_citation":"https://pith.science/pith/DULSWRVDKDLO7NJUAW4WWB5Z65/action/citation_signature","submit_replication":"https://pith.science/pith/DULSWRVDKDLO7NJUAW4WWB5Z65/action/replication_record"}},"created_at":"2026-07-05T11:28:25.762185+00:00","updated_at":"2026-07-05T11:28:25.762185+00:00"}