{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LB4U4INJZKDL3JTU2NBIDMT2SP","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":"1d5b7655947a70f03f655660392cd656b48ff623ad61d7724ff6169247329e32","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T20:22:17Z","title_canon_sha256":"5fff1f2088ab9e7972a34be0751377fd40ac1a77c4b34af3e599d22f355e94a6"},"schema_version":"1.0","source":{"id":"2402.18695","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18695","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18695v2","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18695","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"LB4U4INJZKDL","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"LB4U4INJZKDL3JTU","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"LB4U4INJ","created_at":"2026-07-05T08:48:41Z"}],"graph_snapshots":[{"event_id":"sha256:fe4ba30e5649982bf89de556a6cbe5e2f769c70dc0bbb49002a649a586732686","target":"graph","created_at":"2026-07-05T08:48:41Z","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/2402.18695/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jie Wu, Ming Gong, Paola Cascante-Bonilla, Vicente Ordonez, Xingyao Zhang, Zilin Xiao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T20:22:17Z","title":"Grounding Language Models for Visual Entity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18695","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:feda26a3cd77669114f4e7737aea9832ba8bc33fd998ca502ef5b0392855f42a","target":"record","created_at":"2026-07-05T08:48:41Z","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":"1d5b7655947a70f03f655660392cd656b48ff623ad61d7724ff6169247329e32","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T20:22:17Z","title_canon_sha256":"5fff1f2088ab9e7972a34be0751377fd40ac1a77c4b34af3e599d22f355e94a6"},"schema_version":"1.0","source":{"id":"2402.18695","kind":"arxiv","version":2}},"canonical_sha256":"58794e21a9ca86bda674d34281b27a93ea8b833ceacd70649c9f4da97be533a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58794e21a9ca86bda674d34281b27a93ea8b833ceacd70649c9f4da97be533a0","first_computed_at":"2026-07-05T08:48:41.681925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:41.681925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"00EMkjbcvPNkrC2WV9nr2XqfLJIWW99EOYWjky0VV5CheSHYdm5EndpXLYOjY5eWZPYhwcyusXzBpZExDknsCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:41.682414Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18695","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:feda26a3cd77669114f4e7737aea9832ba8bc33fd998ca502ef5b0392855f42a","sha256:fe4ba30e5649982bf89de556a6cbe5e2f769c70dc0bbb49002a649a586732686"],"state_sha256":"ae13fd86095a226db0faa3ca584d1e3a99379ab4797cb1c170974d06611962da"}