{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LB4U4INJZKDL3JTU2NBIDMT2SP","short_pith_number":"pith:LB4U4INJ","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"},"canonical_sha256":"58794e21a9ca86bda674d34281b27a93ea8b833ceacd70649c9f4da97be533a0","source":{"kind":"arxiv","id":"2402.18695","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LB4U4INJZKDL3JTU2NBIDMT2SP","target":"record","payload":{"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"},"canonical_sha256":"58794e21a9ca86bda674d34281b27a93ea8b833ceacd70649c9f4da97be533a0","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"},"source_kind":"arxiv","source_id":"2402.18695","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"crS0hxhjjtRWH5z+BvQHMAhrXJXhJffUPeufq0jpDj+RQSX/alDdqLTpKN8l65d176iUjjcFNkzTmcWVPyoIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:43:41.841521Z"},"content_sha256":"feda26a3cd77669114f4e7737aea9832ba8bc33fd998ca502ef5b0392855f42a","schema_version":"1.0","event_id":"sha256:feda26a3cd77669114f4e7737aea9832ba8bc33fd998ca502ef5b0392855f42a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LB4U4INJZKDL3JTU2NBIDMT2SP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yis+7Ej07qgzt/XL+rL6hH9br03//S6bAy4clb/6HZbOQzpAtTxSz+p/5KSJlWtj0SSUi2hOo0dCedwoN0nQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:43:41.841959Z"},"content_sha256":"fe4ba30e5649982bf89de556a6cbe5e2f769c70dc0bbb49002a649a586732686","schema_version":"1.0","event_id":"sha256:fe4ba30e5649982bf89de556a6cbe5e2f769c70dc0bbb49002a649a586732686"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP/bundle.json","state_url":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LB4U4INJZKDL3JTU2NBIDMT2SP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T17:43:41Z","links":{"resolver":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP","bundle":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP/bundle.json","state":"https://pith.science/pith/LB4U4INJZKDL3JTU2NBIDMT2SP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LB4U4INJZKDL3JTU2NBIDMT2SP/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w7khrQ9UHjnfz/U+ikUFMnmvws77YLOYmMVxNJy2OpV3y27EMtYmd1Gy5iNOIc/Kck13xsQdnhin/7VxHVXEDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:43:41.843860Z","bundle_sha256":"67284fa9e3a81c2b4e38a9e1d7c0ded6b605fe7d525708afa4fd70117328b216"}}