{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J73QG353UX6RKINF6ZUUINKBL2","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":"42608a78dcf893c685ef41f25466edb9fe5030ca9e2adb8763f519d74d0e5786","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T10:40:52Z","title_canon_sha256":"dbb623af2dbbaea3ef0b79d02583d79814299395bff57f2f890b3da7832aeea5"},"schema_version":"1.0","source":{"id":"2311.17518","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17518","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17518v2","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17518","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"J73QG353UX6R","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"J73QG353UX6RKINF","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"J73QG353","created_at":"2026-07-05T08:05:06Z"}],"graph_snapshots":[{"event_id":"sha256:fe96210521cf8669b1063bc16421a82ec10aca17d1e63e61f922d13b5249a178","target":"graph","created_at":"2026-07-05T08:05:06Z","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/2311.17518/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large vision-language models enabled visual object detection in open-vocabulary scenarios, where object classes are defined in free-text formats during inference. In this paper, we aim to probe the state-of-the-art methods for open-vocabulary object detection to determine to what extent they understand fine-grained properties of objects and their parts. To this end, we introduce an evaluation protocol based on dynamic vocabulary generation to test whether models detect, discern, and assign the correct fine-grained description to objects in the presence of hard-negative c","authors_text":"Claudio Gennaro, Fabio Carrara, Fabrizio Falchi, Lorenzo Bianchi, Nicola Messina","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T10:40:52Z","title":"The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17518","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:cb3ca37a4b3c84bfc979b83af782afa68f6f544b5e3163bea5abde9801d1e09d","target":"record","created_at":"2026-07-05T08:05:06Z","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":"42608a78dcf893c685ef41f25466edb9fe5030ca9e2adb8763f519d74d0e5786","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T10:40:52Z","title_canon_sha256":"dbb623af2dbbaea3ef0b79d02583d79814299395bff57f2f890b3da7832aeea5"},"schema_version":"1.0","source":{"id":"2311.17518","kind":"arxiv","version":2}},"canonical_sha256":"4ff7036fbba5fd1521a5f6694435415ea50db8ef38eca99c730e844ab09cb271","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ff7036fbba5fd1521a5f6694435415ea50db8ef38eca99c730e844ab09cb271","first_computed_at":"2026-07-05T08:05:06.141589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:06.141589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gbvxh74qospulJxueozpdUCNnp8zCnY71GOgngLtp7zkt5CvodVYluBDQkq8wlGzNT59onkTc2m8030VdhtAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:06.141997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17518","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb3ca37a4b3c84bfc979b83af782afa68f6f544b5e3163bea5abde9801d1e09d","sha256:fe96210521cf8669b1063bc16421a82ec10aca17d1e63e61f922d13b5249a178"],"state_sha256":"800108149aea2763d16641402f1b76879d366e471dee8f4ea6f85a4df1950b03"}