{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4XTGDXEK3J26OQIZZSNJDS6I7M","short_pith_number":"pith:4XTGDXEK","schema_version":"1.0","canonical_sha256":"e5e661dc8ada75e74119cc9a91cbc8fb10cc5336bfc88a618993f122a4577312","source":{"kind":"arxiv","id":"2605.28522","version":1},"attestation_state":"computed","paper":{"title":"Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Eugene Yang, Jia-Huei Ju, Suzan Verberne, Trevor Adriaanse","submitted_at":"2026-05-27T14:20:52Z","abstract_excerpt":"Long-form Retrieval-Augmented Generation (RAG) brings the challenge of coverage-based ranking, because ranking methods must ensure the inclusion of comprehensive relevant nuggets (i.e., facts), which can thereby be synthesized into a comprehensive output. In this work, we propose CoveR (Our code is available at https://github.com/DylanJoo/CoveR ) a dense retrieval method optimized for coverage-aware retrieval scenarios. CoveR is a bi-encoder trained with the coverage-based contrastive and distillation objectives, which enables CoveR to capture diverse aspects of information needs. To train Cov"},"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":"2605.28522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-27T14:20:52Z","cross_cats_sorted":[],"title_canon_sha256":"ffd1bca0cbcb83a890251ebc122cc26e8f29a85a13911954a3ef21dc8e86e5e7","abstract_canon_sha256":"f67793494c83c37be039a22936f9474e20cae080235684b38dceb127991b8de7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:55.342439Z","signature_b64":"xA46kQjphDZPJAmZQa+77JjJYVUJEFyZsIgy7f4J1g94q4/ArH31tuGGXPUXwiJxVfe+XYfBff425+/dqyQmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5e661dc8ada75e74119cc9a91cbc8fb10cc5336bfc88a618993f122a4577312","last_reissued_at":"2026-05-28T02:04:55.342026Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:55.342026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Eugene Yang, Jia-Huei Ju, Suzan Verberne, Trevor Adriaanse","submitted_at":"2026-05-27T14:20:52Z","abstract_excerpt":"Long-form Retrieval-Augmented Generation (RAG) brings the challenge of coverage-based ranking, because ranking methods must ensure the inclusion of comprehensive relevant nuggets (i.e., facts), which can thereby be synthesized into a comprehensive output. In this work, we propose CoveR (Our code is available at https://github.com/DylanJoo/CoveR ) a dense retrieval method optimized for coverage-aware retrieval scenarios. CoveR is a bi-encoder trained with the coverage-based contrastive and distillation objectives, which enables CoveR to capture diverse aspects of information needs. To train Cov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28522","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/2605.28522/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":"2605.28522","created_at":"2026-05-28T02:04:55.342090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28522v1","created_at":"2026-05-28T02:04:55.342090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28522","created_at":"2026-05-28T02:04:55.342090+00:00"},{"alias_kind":"pith_short_12","alias_value":"4XTGDXEK3J26","created_at":"2026-05-28T02:04:55.342090+00:00"},{"alias_kind":"pith_short_16","alias_value":"4XTGDXEK3J26OQIZ","created_at":"2026-05-28T02:04:55.342090+00:00"},{"alias_kind":"pith_short_8","alias_value":"4XTGDXEK","created_at":"2026-05-28T02:04:55.342090+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/4XTGDXEK3J26OQIZZSNJDS6I7M","json":"https://pith.science/pith/4XTGDXEK3J26OQIZZSNJDS6I7M.json","graph_json":"https://pith.science/api/pith-number/4XTGDXEK3J26OQIZZSNJDS6I7M/graph.json","events_json":"https://pith.science/api/pith-number/4XTGDXEK3J26OQIZZSNJDS6I7M/events.json","paper":"https://pith.science/paper/4XTGDXEK"},"agent_actions":{"view_html":"https://pith.science/pith/4XTGDXEK3J26OQIZZSNJDS6I7M","download_json":"https://pith.science/pith/4XTGDXEK3J26OQIZZSNJDS6I7M.json","view_paper":"https://pith.science/paper/4XTGDXEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28522&json=true","fetch_graph":"https://pith.science/api/pith-number/4XTGDXEK3J26OQIZZSNJDS6I7M/graph.json","fetch_events":"https://pith.science/api/pith-number/4XTGDXEK3J26OQIZZSNJDS6I7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4XTGDXEK3J26OQIZZSNJDS6I7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4XTGDXEK3J26OQIZZSNJDS6I7M/action/storage_attestation","attest_author":"https://pith.science/pith/4XTGDXEK3J26OQIZZSNJDS6I7M/action/author_attestation","sign_citation":"https://pith.science/pith/4XTGDXEK3J26OQIZZSNJDS6I7M/action/citation_signature","submit_replication":"https://pith.science/pith/4XTGDXEK3J26OQIZZSNJDS6I7M/action/replication_record"}},"created_at":"2026-05-28T02:04:55.342090+00:00","updated_at":"2026-05-28T02:04:55.342090+00:00"}