{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3JN3WURIMOXQ7S245AMOZHMPTR","short_pith_number":"pith:3JN3WURI","schema_version":"1.0","canonical_sha256":"da5bbb522863af0fcb5ce818ec9d8f9c66c5b43f6c432f95148a51fccb3215de","source":{"kind":"arxiv","id":"2608.06060","version":1},"attestation_state":"computed","paper":{"title":"Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Wang, Kaicheng Yang, Tiancheng Gu, Zelong Sun, Zhiwu Lu, Ziyong Feng","submitted_at":"2026-08-06T14:04:56Z","abstract_excerpt":"Unified multimodal retrieval aims to identify candidates that satisfy complex user intent expressed through heterogeneous inputs. Although Large Vision-Language Model (LVLM)-based retrievers are efficient and scalable, directly encoding raw multimodal inputs often misses fine-grained discriminative cues, leading to confusion among semantically similar candidates. Recent methods mitigate this limitation by generating Chain-of-Thought (CoT) rationales to enrich the query representation. However, such reasoning is typically derived from the query alone: it explains what the query describes, but n"},"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":"2608.06060","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T14:04:56Z","cross_cats_sorted":[],"title_canon_sha256":"76f27f6754dbc3aa8093919c3c83c1e1391cc1afc3e11fe958d8c5436ceaef5e","abstract_canon_sha256":"5ca72f73094ed4098dc7ef8894182131878eb6bcf74e3a01a388e704845cb5cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T01:39:55.425742Z","signature_b64":"t36pxkSLqgluJGOp5YbhYmn/j2hgPty57hbnYFiCv0fUe2iixbZbEzvupD/F1j2kWLFe2GmyFsI4zGtzZDKRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da5bbb522863af0fcb5ce818ec9d8f9c66c5b43f6c432f95148a51fccb3215de","last_reissued_at":"2026-08-07T01:39:55.424062Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T01:39:55.424062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Wang, Kaicheng Yang, Tiancheng Gu, Zelong Sun, Zhiwu Lu, Ziyong Feng","submitted_at":"2026-08-06T14:04:56Z","abstract_excerpt":"Unified multimodal retrieval aims to identify candidates that satisfy complex user intent expressed through heterogeneous inputs. Although Large Vision-Language Model (LVLM)-based retrievers are efficient and scalable, directly encoding raw multimodal inputs often misses fine-grained discriminative cues, leading to confusion among semantically similar candidates. Recent methods mitigate this limitation by generating Chain-of-Thought (CoT) rationales to enrich the query representation. However, such reasoning is typically derived from the query alone: it explains what the query describes, but n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06060","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/2608.06060/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":"2608.06060","created_at":"2026-08-07T01:39:55.426603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06060v1","created_at":"2026-08-07T01:39:55.426603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06060","created_at":"2026-08-07T01:39:55.426603+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JN3WURIMOXQ","created_at":"2026-08-07T01:39:55.426603+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JN3WURIMOXQ7S24","created_at":"2026-08-07T01:39:55.426603+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JN3WURI","created_at":"2026-08-07T01:39:55.426603+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/3JN3WURIMOXQ7S245AMOZHMPTR","json":"https://pith.science/pith/3JN3WURIMOXQ7S245AMOZHMPTR.json","graph_json":"https://pith.science/api/pith-number/3JN3WURIMOXQ7S245AMOZHMPTR/graph.json","events_json":"https://pith.science/api/pith-number/3JN3WURIMOXQ7S245AMOZHMPTR/events.json","paper":"https://pith.science/paper/3JN3WURI"},"agent_actions":{"view_html":"https://pith.science/pith/3JN3WURIMOXQ7S245AMOZHMPTR","download_json":"https://pith.science/pith/3JN3WURIMOXQ7S245AMOZHMPTR.json","view_paper":"https://pith.science/paper/3JN3WURI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06060&json=true","fetch_graph":"https://pith.science/api/pith-number/3JN3WURIMOXQ7S245AMOZHMPTR/graph.json","fetch_events":"https://pith.science/api/pith-number/3JN3WURIMOXQ7S245AMOZHMPTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JN3WURIMOXQ7S245AMOZHMPTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JN3WURIMOXQ7S245AMOZHMPTR/action/storage_attestation","attest_author":"https://pith.science/pith/3JN3WURIMOXQ7S245AMOZHMPTR/action/author_attestation","sign_citation":"https://pith.science/pith/3JN3WURIMOXQ7S245AMOZHMPTR/action/citation_signature","submit_replication":"https://pith.science/pith/3JN3WURIMOXQ7S245AMOZHMPTR/action/replication_record"}},"created_at":"2026-08-07T01:39:55.426603+00:00","updated_at":"2026-08-07T01:39:55.426603+00:00"}