{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LB4U4INJZKDL3JTU2NBIDMT2SP","short_pith_number":"pith:LB4U4INJ","schema_version":"1.0","canonical_sha256":"58794e21a9ca86bda674d34281b27a93ea8b833ceacd70649c9f4da97be533a0","source":{"kind":"arxiv","id":"2402.18695","version":2},"attestation_state":"computed","paper":{"title":"Grounding Language Models for Visual Entity Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jie Wu, Ming Gong, Paola Cascante-Bonilla, Vicente Ordonez, Xingyao Zhang, Zilin Xiao","submitted_at":"2024-02-28T20:22:17Z","abstract_excerpt":"We introduce AutoVER, an Autoregressive model for Visual Entity Recognition. Our model extends an autoregressive Multi-modal Large Language Model by employing retrieval augmented constrained generation. It mitigates low performance on out-of-domain entities while excelling in queries that require visually-situated reasoning. Our method learns to distinguish similar entities within a vast label space by contrastively training on hard negative pairs in parallel with a sequence-to-sequence objective without an external retriever. During inference, a list of retrieved candidate answers explicitly "},"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":"2402.18695","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T20:22:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5fff1f2088ab9e7972a34be0751377fd40ac1a77c4b34af3e599d22f355e94a6","abstract_canon_sha256":"1d5b7655947a70f03f655660392cd656b48ff623ad61d7724ff6169247329e32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:41.682414Z","signature_b64":"00EMkjbcvPNkrC2WV9nr2XqfLJIWW99EOYWjky0VV5CheSHYdm5EndpXLYOjY5eWZPYhwcyusXzBpZExDknsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58794e21a9ca86bda674d34281b27a93ea8b833ceacd70649c9f4da97be533a0","last_reissued_at":"2026-07-05T08:48:41.681925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:41.681925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding Language Models for Visual Entity Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jie Wu, Ming Gong, Paola Cascante-Bonilla, Vicente Ordonez, Xingyao Zhang, Zilin Xiao","submitted_at":"2024-02-28T20:22:17Z","abstract_excerpt":"We introduce AutoVER, an Autoregressive model for Visual Entity Recognition. Our model extends an autoregressive Multi-modal Large Language Model by employing retrieval augmented constrained generation. It mitigates low performance on out-of-domain entities while excelling in queries that require visually-situated reasoning. Our method learns to distinguish similar entities within a vast label space by contrastively training on hard negative pairs in parallel with a sequence-to-sequence objective without an external retriever. During inference, a list of retrieved candidate answers explicitly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18695","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/2402.18695/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":"2402.18695","created_at":"2026-07-05T08:48:41.681990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18695v2","created_at":"2026-07-05T08:48:41.681990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18695","created_at":"2026-07-05T08:48:41.681990+00:00"},{"alias_kind":"pith_short_12","alias_value":"LB4U4INJZKDL","created_at":"2026-07-05T08:48:41.681990+00:00"},{"alias_kind":"pith_short_16","alias_value":"LB4U4INJZKDL3JTU","created_at":"2026-07-05T08:48:41.681990+00:00"},{"alias_kind":"pith_short_8","alias_value":"LB4U4INJ","created_at":"2026-07-05T08:48:41.681990+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/LB4U4INJZKDL3JTU2NBIDMT2SP","json":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP.json","graph_json":"https://pith.science/api/pith-number/LB4U4INJZKDL3JTU2NBIDMT2SP/graph.json","events_json":"https://pith.science/api/pith-number/LB4U4INJZKDL3JTU2NBIDMT2SP/events.json","paper":"https://pith.science/paper/LB4U4INJ"},"agent_actions":{"view_html":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP","download_json":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP.json","view_paper":"https://pith.science/paper/LB4U4INJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18695&json=true","fetch_graph":"https://pith.science/api/pith-number/LB4U4INJZKDL3JTU2NBIDMT2SP/graph.json","fetch_events":"https://pith.science/api/pith-number/LB4U4INJZKDL3JTU2NBIDMT2SP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP/action/storage_attestation","attest_author":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP/action/author_attestation","sign_citation":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP/action/citation_signature","submit_replication":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP/action/replication_record"}},"created_at":"2026-07-05T08:48:41.681990+00:00","updated_at":"2026-07-05T08:48:41.681990+00:00"}