{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YQHDL4I4SD3LMRQYXUEDCQPY7T","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":"6b3f318f83f1a956c191f263ac95c4cd449ccc19b20b0022135a79ed82a012fe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T19:06:12Z","title_canon_sha256":"880e01a7ea26b8144d232ac90f68f82ae9a84542d6eb980ab3a9d18717ddc022"},"schema_version":"1.0","source":{"id":"2312.00878","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.00878","created_at":"2026-07-05T07:24:02Z"},{"alias_kind":"arxiv_version","alias_value":"2312.00878v3","created_at":"2026-07-05T07:24:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00878","created_at":"2026-07-05T07:24:02Z"},{"alias_kind":"pith_short_12","alias_value":"YQHDL4I4SD3L","created_at":"2026-07-05T07:24:02Z"},{"alias_kind":"pith_short_16","alias_value":"YQHDL4I4SD3LMRQY","created_at":"2026-07-05T07:24:02Z"},{"alias_kind":"pith_short_8","alias_value":"YQHDL4I4","created_at":"2026-07-05T07:24:02Z"}],"graph_snapshots":[{"event_id":"sha256:388c32c969846be98a464643b7d861b8e31c2e6806b20fb1ab0037b4fa08fc7b","target":"graph","created_at":"2026-07-05T07:24:02Z","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/2312.00878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language foundation models have shown remarkable performance in various zero-shot settings such as image retrieval, classification, or captioning. But so far, those models seem to fall behind when it comes to zero-shot localization of referential expressions and objects in images. As a result, they need to be fine-tuned for this task. In this paper, we show that pretrained vision-language (VL) models allow for zero-shot open-vocabulary object localization without any fine-tuning. To leverage those capabilities, we propose a Grounding Everything Module (GEM) that generalizes the idea of ","authors_text":"Felix Petersen, Hilde Kuehne, Vittorio Ferrari, Walid Bousselham","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T19:06:12Z","title":"Grounding Everything: Emerging Localization Properties in Vision-Language Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00878","kind":"arxiv","version":3},"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":"sha256:5b3f10bbd5fe014839832f12bd5f1dc7bd5f1f271f86cfa80260a2ca3f56737c","target":"record","created_at":"2026-07-05T07:24:02Z","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":"6b3f318f83f1a956c191f263ac95c4cd449ccc19b20b0022135a79ed82a012fe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T19:06:12Z","title_canon_sha256":"880e01a7ea26b8144d232ac90f68f82ae9a84542d6eb980ab3a9d18717ddc022"},"schema_version":"1.0","source":{"id":"2312.00878","kind":"arxiv","version":3}},"canonical_sha256":"c40e35f11c90f6b64618bd083141f8fcd0f9cc4cbfb42ac4c46bd73b278bf028","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c40e35f11c90f6b64618bd083141f8fcd0f9cc4cbfb42ac4c46bd73b278bf028","first_computed_at":"2026-07-05T07:24:02.554956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:02.554956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1eCbTdKOy9hdFFbbZBbFqJTfbOCzdaiZJwuzmxtwPJQzKy6JuJxxI6GznTepXmr9tNL7HqPmN1tUac+crAOCAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:02.555428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.00878","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b3f10bbd5fe014839832f12bd5f1dc7bd5f1f271f86cfa80260a2ca3f56737c","sha256:388c32c969846be98a464643b7d861b8e31c2e6806b20fb1ab0037b4fa08fc7b"],"state_sha256":"6163d4284284b628f130650ebd87d2b9284d67a84b9aef0322131a441d193060"}