{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XOOIOQNX4QG7CUKIN4HNR3IHAY","short_pith_number":"pith:XOOIOQNX","schema_version":"1.0","canonical_sha256":"bb9c8741b7e40df151486f0ed8ed07063c1bc47a8b5c1ea7c2d4fd793f9748a6","source":{"kind":"arxiv","id":"2108.04026","version":1},"attestation_state":"computed","paper":{"title":"IntenT5: Search Result Diversification using Causal Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Craig Macdonald, Iadh Ounis, Roderick Murray-Smith, Sean MacAvaney","submitted_at":"2021-08-09T13:29:24Z","abstract_excerpt":"Search result diversification is a beneficial approach to overcome under-specified queries, such as those that are ambiguous or multi-faceted. Existing approaches often rely on massive query logs and interaction data to generate a variety of possible query intents, which then can be used to re-rank documents. However, relying on user interaction data is problematic because one first needs a massive user base to build a sufficient log; public query logs are insufficient on their own. Given the recent success of causal language models (such as the Text-To-Text Transformer (T5) model) at text gen"},"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":"2108.04026","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-08-09T13:29:24Z","cross_cats_sorted":[],"title_canon_sha256":"bc8b202d286b0d4038496dd0910a441ab8eabee17f4cdd2d0546b2ccbe65ff4a","abstract_canon_sha256":"1602270fecd94fd93ce39684ce2a03ae7f60b5d894b07cda26804f8e1c00d8c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:12.163997Z","signature_b64":"40E7RSPHlXp9fKZJVGH5kBTG/YMPveSf/A40Y35QuXSpHdWtyNqXrcBA5Sa6Rak2oCdTJHZ9DWSVpf/HU1xbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb9c8741b7e40df151486f0ed8ed07063c1bc47a8b5c1ea7c2d4fd793f9748a6","last_reissued_at":"2026-07-05T03:04:12.163532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:12.163532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IntenT5: Search Result Diversification using Causal Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Craig Macdonald, Iadh Ounis, Roderick Murray-Smith, Sean MacAvaney","submitted_at":"2021-08-09T13:29:24Z","abstract_excerpt":"Search result diversification is a beneficial approach to overcome under-specified queries, such as those that are ambiguous or multi-faceted. Existing approaches often rely on massive query logs and interaction data to generate a variety of possible query intents, which then can be used to re-rank documents. However, relying on user interaction data is problematic because one first needs a massive user base to build a sufficient log; public query logs are insufficient on their own. Given the recent success of causal language models (such as the Text-To-Text Transformer (T5) model) at text gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04026","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/2108.04026/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":"2108.04026","created_at":"2026-07-05T03:04:12.163593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.04026v1","created_at":"2026-07-05T03:04:12.163593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04026","created_at":"2026-07-05T03:04:12.163593+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOOIOQNX4QG7","created_at":"2026-07-05T03:04:12.163593+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOOIOQNX4QG7CUKI","created_at":"2026-07-05T03:04:12.163593+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOOIOQNX","created_at":"2026-07-05T03:04:12.163593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16692","citing_title":"Generating Search Explanations using Large Language Models","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOOIOQNX4QG7CUKIN4HNR3IHAY","json":"https://pith.science/pith/XOOIOQNX4QG7CUKIN4HNR3IHAY.json","graph_json":"https://pith.science/api/pith-number/XOOIOQNX4QG7CUKIN4HNR3IHAY/graph.json","events_json":"https://pith.science/api/pith-number/XOOIOQNX4QG7CUKIN4HNR3IHAY/events.json","paper":"https://pith.science/paper/XOOIOQNX"},"agent_actions":{"view_html":"https://pith.science/pith/XOOIOQNX4QG7CUKIN4HNR3IHAY","download_json":"https://pith.science/pith/XOOIOQNX4QG7CUKIN4HNR3IHAY.json","view_paper":"https://pith.science/paper/XOOIOQNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.04026&json=true","fetch_graph":"https://pith.science/api/pith-number/XOOIOQNX4QG7CUKIN4HNR3IHAY/graph.json","fetch_events":"https://pith.science/api/pith-number/XOOIOQNX4QG7CUKIN4HNR3IHAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOOIOQNX4QG7CUKIN4HNR3IHAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOOIOQNX4QG7CUKIN4HNR3IHAY/action/storage_attestation","attest_author":"https://pith.science/pith/XOOIOQNX4QG7CUKIN4HNR3IHAY/action/author_attestation","sign_citation":"https://pith.science/pith/XOOIOQNX4QG7CUKIN4HNR3IHAY/action/citation_signature","submit_replication":"https://pith.science/pith/XOOIOQNX4QG7CUKIN4HNR3IHAY/action/replication_record"}},"created_at":"2026-07-05T03:04:12.163593+00:00","updated_at":"2026-07-05T03:04:12.163593+00:00"}