{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EUCSMTYP76HXA675JLZLGSPNC7","short_pith_number":"pith:EUCSMTYP","schema_version":"1.0","canonical_sha256":"2505264f0fff8f707bfd4af2b349ed17f67ea06f251f7c23e283509c22ec979d","source":{"kind":"arxiv","id":"2506.08592","version":2},"attestation_state":"computed","paper":{"title":"Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Jiangnan Li, Jie Zhou, Liyan Xu, Mo Yu, Zhenlin Su","submitted_at":"2025-06-10T09:00:33Z","abstract_excerpt":"This work stems from an observed limitation of text encoders: embeddings may not be able to recognize fine-grained entities or events within encoded semantics, resulting in failed retrieval even in simple cases. To examine such behaviors, we first introduce a new evaluation dataset, CapRetrieval, in which passages are image captions and queries are phrases targeting entity or event concepts in diverse forms. Zero-shot evaluation suggests that encoders often struggle with these fine-grained matching, regardless of training sources or model size. Aiming for enhancement, we proceed to finetune en"},"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":"2506.08592","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T09:00:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ac1a52bbace9d53d5312c5215e378ddf4a4cf33d3ca76a519d64090f645c03d0","abstract_canon_sha256":"66a73cb25652b52bbd2626345676304b95089bcc3e23a959ddcd35a4d8a0f864"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:15.430542Z","signature_b64":"TiH4WJiaXQnmlvj4NJedELpHFfoSMxItT0oUUpY5L22j5OshDuVUeF/0m/PSq2R6xp4ee3xzYTjJnNg2cyIgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2505264f0fff8f707bfd4af2b349ed17f67ea06f251f7c23e283509c22ec979d","last_reissued_at":"2026-07-05T11:59:15.430054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:15.430054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Jiangnan Li, Jie Zhou, Liyan Xu, Mo Yu, Zhenlin Su","submitted_at":"2025-06-10T09:00:33Z","abstract_excerpt":"This work stems from an observed limitation of text encoders: embeddings may not be able to recognize fine-grained entities or events within encoded semantics, resulting in failed retrieval even in simple cases. To examine such behaviors, we first introduce a new evaluation dataset, CapRetrieval, in which passages are image captions and queries are phrases targeting entity or event concepts in diverse forms. Zero-shot evaluation suggests that encoders often struggle with these fine-grained matching, regardless of training sources or model size. Aiming for enhancement, we proceed to finetune en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08592","kind":"arxiv","version":2},"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/2506.08592/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":"2506.08592","created_at":"2026-07-05T11:59:15.430111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08592v2","created_at":"2026-07-05T11:59:15.430111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08592","created_at":"2026-07-05T11:59:15.430111+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUCSMTYP76HX","created_at":"2026-07-05T11:59:15.430111+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUCSMTYP76HXA675","created_at":"2026-07-05T11:59:15.430111+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUCSMTYP","created_at":"2026-07-05T11:59:15.430111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20117","citing_title":"To Know is to Construct: Schema-Constrained Generation for Agent Memory","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EUCSMTYP76HXA675JLZLGSPNC7","json":"https://pith.science/pith/EUCSMTYP76HXA675JLZLGSPNC7.json","graph_json":"https://pith.science/api/pith-number/EUCSMTYP76HXA675JLZLGSPNC7/graph.json","events_json":"https://pith.science/api/pith-number/EUCSMTYP76HXA675JLZLGSPNC7/events.json","paper":"https://pith.science/paper/EUCSMTYP"},"agent_actions":{"view_html":"https://pith.science/pith/EUCSMTYP76HXA675JLZLGSPNC7","download_json":"https://pith.science/pith/EUCSMTYP76HXA675JLZLGSPNC7.json","view_paper":"https://pith.science/paper/EUCSMTYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08592&json=true","fetch_graph":"https://pith.science/api/pith-number/EUCSMTYP76HXA675JLZLGSPNC7/graph.json","fetch_events":"https://pith.science/api/pith-number/EUCSMTYP76HXA675JLZLGSPNC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUCSMTYP76HXA675JLZLGSPNC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUCSMTYP76HXA675JLZLGSPNC7/action/storage_attestation","attest_author":"https://pith.science/pith/EUCSMTYP76HXA675JLZLGSPNC7/action/author_attestation","sign_citation":"https://pith.science/pith/EUCSMTYP76HXA675JLZLGSPNC7/action/citation_signature","submit_replication":"https://pith.science/pith/EUCSMTYP76HXA675JLZLGSPNC7/action/replication_record"}},"created_at":"2026-07-05T11:59:15.430111+00:00","updated_at":"2026-07-05T11:59:15.430111+00:00"}