{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P2HPXGKYMDG5UOEH4GA6PPBNGR","short_pith_number":"pith:P2HPXGKY","schema_version":"1.0","canonical_sha256":"7e8efb995860cdda3887e181e7bc2d3472e17793b308e095d2e473b05e3ac0b4","source":{"kind":"arxiv","id":"2504.05216","version":3},"attestation_state":"computed","paper":{"title":"Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Daiting Shi, Dawei Yin, Hengran Zhang, Jiafeng Guo, Keping Bi, Shihao Liu, Xiaojie Sun, Xueqi Cheng","submitted_at":"2025-04-07T16:03:59Z","abstract_excerpt":"Dense retrieval is a crucial task in Information Retrieval (IR), serving as the basis for downstream tasks such as re-ranking and augmenting generation. Recently, large language models (LLMs) have demonstrated impressive semantic understanding capabilities, making them attractive to researchers focusing on dense retrieval. While LLMs, as decoder-style generative models, excel in language generation, they often fall short in modeling global information due to a lack of attention to subsequent tokens. Drawing inspiration from the classical word-based language modeling approach for IR, specifical"},"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":"2504.05216","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-04-07T16:03:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0d2ac8743e6a47cab9074212fcbd235e08eb66c3185bf90d5c41f23b9beb8d71","abstract_canon_sha256":"67af9b5cf40d351c40c161697206a06f2c0ac796e380a60dfddb43e36c6c749a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:39.222858Z","signature_b64":"h41dC6y+StD/kKNZiYa/8y2PwqWn93ThzBOkejM9UfQchqPzRBzaovFcp24tkVXOZ8fRDePxylo/vrrx0M3zBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e8efb995860cdda3887e181e7bc2d3472e17793b308e095d2e473b05e3ac0b4","last_reissued_at":"2026-07-05T11:55:39.222368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:39.222368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Daiting Shi, Dawei Yin, Hengran Zhang, Jiafeng Guo, Keping Bi, Shihao Liu, Xiaojie Sun, Xueqi Cheng","submitted_at":"2025-04-07T16:03:59Z","abstract_excerpt":"Dense retrieval is a crucial task in Information Retrieval (IR), serving as the basis for downstream tasks such as re-ranking and augmenting generation. Recently, large language models (LLMs) have demonstrated impressive semantic understanding capabilities, making them attractive to researchers focusing on dense retrieval. While LLMs, as decoder-style generative models, excel in language generation, they often fall short in modeling global information due to a lack of attention to subsequent tokens. Drawing inspiration from the classical word-based language modeling approach for IR, specifical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05216","kind":"arxiv","version":3},"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/2504.05216/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":"2504.05216","created_at":"2026-07-05T11:55:39.222429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05216v3","created_at":"2026-07-05T11:55:39.222429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05216","created_at":"2026-07-05T11:55:39.222429+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2HPXGKYMDG5","created_at":"2026-07-05T11:55:39.222429+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2HPXGKYMDG5UOEH","created_at":"2026-07-05T11:55:39.222429+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2HPXGKY","created_at":"2026-07-05T11:55:39.222429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08920","citing_title":"Beyond Relevance: Utility-Centric Retrieval in the LLM Era","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2HPXGKYMDG5UOEH4GA6PPBNGR","json":"https://pith.science/pith/P2HPXGKYMDG5UOEH4GA6PPBNGR.json","graph_json":"https://pith.science/api/pith-number/P2HPXGKYMDG5UOEH4GA6PPBNGR/graph.json","events_json":"https://pith.science/api/pith-number/P2HPXGKYMDG5UOEH4GA6PPBNGR/events.json","paper":"https://pith.science/paper/P2HPXGKY"},"agent_actions":{"view_html":"https://pith.science/pith/P2HPXGKYMDG5UOEH4GA6PPBNGR","download_json":"https://pith.science/pith/P2HPXGKYMDG5UOEH4GA6PPBNGR.json","view_paper":"https://pith.science/paper/P2HPXGKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05216&json=true","fetch_graph":"https://pith.science/api/pith-number/P2HPXGKYMDG5UOEH4GA6PPBNGR/graph.json","fetch_events":"https://pith.science/api/pith-number/P2HPXGKYMDG5UOEH4GA6PPBNGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2HPXGKYMDG5UOEH4GA6PPBNGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2HPXGKYMDG5UOEH4GA6PPBNGR/action/storage_attestation","attest_author":"https://pith.science/pith/P2HPXGKYMDG5UOEH4GA6PPBNGR/action/author_attestation","sign_citation":"https://pith.science/pith/P2HPXGKYMDG5UOEH4GA6PPBNGR/action/citation_signature","submit_replication":"https://pith.science/pith/P2HPXGKYMDG5UOEH4GA6PPBNGR/action/replication_record"}},"created_at":"2026-07-05T11:55:39.222429+00:00","updated_at":"2026-07-05T11:55:39.222429+00:00"}