{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EUCSMTYP76HXA675JLZLGSPNC7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"66a73cb25652b52bbd2626345676304b95089bcc3e23a959ddcd35a4d8a0f864","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T09:00:33Z","title_canon_sha256":"ac1a52bbace9d53d5312c5215e378ddf4a4cf33d3ca76a519d64090f645c03d0"},"schema_version":"1.0","source":{"id":"2506.08592","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08592","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08592v2","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08592","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"pith_short_12","alias_value":"EUCSMTYP76HX","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"pith_short_16","alias_value":"EUCSMTYP76HXA675","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"pith_short_8","alias_value":"EUCSMTYP","created_at":"2026-07-05T11:59:15Z"}],"graph_snapshots":[{"event_id":"sha256:554fd7b4122756857bb5f110214b8e90e901aa1f27b03b8506d501d57b688d50","target":"graph","created_at":"2026-07-05T11:59:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.08592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fandong Meng, Jiangnan Li, Jie Zhou, Liyan Xu, Mo Yu, Zhenlin Su","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T09:00:33Z","title":"Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08592","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:41424ae9233275b716608947f34b7614371c8dd32cca4468d1ca22acd9ba89b5","target":"record","created_at":"2026-07-05T11:59:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"66a73cb25652b52bbd2626345676304b95089bcc3e23a959ddcd35a4d8a0f864","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T09:00:33Z","title_canon_sha256":"ac1a52bbace9d53d5312c5215e378ddf4a4cf33d3ca76a519d64090f645c03d0"},"schema_version":"1.0","source":{"id":"2506.08592","kind":"arxiv","version":2}},"canonical_sha256":"2505264f0fff8f707bfd4af2b349ed17f67ea06f251f7c23e283509c22ec979d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2505264f0fff8f707bfd4af2b349ed17f67ea06f251f7c23e283509c22ec979d","first_computed_at":"2026-07-05T11:59:15.430054Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:15.430054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TiH4WJiaXQnmlvj4NJedELpHFfoSMxItT0oUUpY5L22j5OshDuVUeF/0m/PSq2R6xp4ee3xzYTjJnNg2cyIgBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:15.430542Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08592","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41424ae9233275b716608947f34b7614371c8dd32cca4468d1ca22acd9ba89b5","sha256:554fd7b4122756857bb5f110214b8e90e901aa1f27b03b8506d501d57b688d50"],"state_sha256":"64e37e756d34156bbf1a4ba41f1e7280bfa072e3d76540a41dbe9b8233b6ca30"}