{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FN2JQ2UDPVLIJRJY7KC22VTYRQ","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":"61c632bc2b36e030398562c125e166182839df287198f11ffb524637dd007043","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T08:54:54Z","title_canon_sha256":"5c9e107571ddb955c82e3f468c0b7e745b9604a2329f8d7f077dbaf4d59b45a2"},"schema_version":"1.0","source":{"id":"2411.16198","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16198","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16198v4","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16198","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"pith_short_12","alias_value":"FN2JQ2UDPVLI","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"pith_short_16","alias_value":"FN2JQ2UDPVLIJRJY","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"pith_short_8","alias_value":"FN2JQ2UD","created_at":"2026-07-05T10:44:20Z"}],"graph_snapshots":[{"event_id":"sha256:0a33eca32169e1e2e0c181a556ffb9a55b26b793f2ca6de1e1a29b9f30817080","target":"graph","created_at":"2026-07-05T10:44:20Z","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/2411.16198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advances in multimodal pre-training have propelled object-level foundation models, such as Grounding DINO and Florence-2, in tasks like visual grounding and object detection. However, interpreting these models' decisions has grown increasingly challenging. Existing interpretable attribution methods for object-level task interpretation have notable limitations: (1) gradient-based methods lack precise localization due to visual-textual fusion in foundation models, and (2) perturbation-based methods produce noisy saliency maps, limiting fine-grained interpretability. To address these, we propose ","authors_text":"Hua Zhang, Jingzhi Li, Maosen Li, Ruoyu Chen, Shiming Liu, Siyuan Liang, Xiaochun Cao, Zhen Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T08:54:54Z","title":"Interpreting Object-level Foundation Models via Visual Precision Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16198","kind":"arxiv","version":4},"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":"sha256:3c8b0a82171163802f4671daefc5b4ecf911cf7d01c5e93f6fd2ac4696ee6c27","target":"record","created_at":"2026-07-05T10:44:20Z","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":"61c632bc2b36e030398562c125e166182839df287198f11ffb524637dd007043","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T08:54:54Z","title_canon_sha256":"5c9e107571ddb955c82e3f468c0b7e745b9604a2329f8d7f077dbaf4d59b45a2"},"schema_version":"1.0","source":{"id":"2411.16198","kind":"arxiv","version":4}},"canonical_sha256":"2b74986a837d5684c538fa85ad56788c2d6fd1eee2847dfb6e47f67ff711525e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b74986a837d5684c538fa85ad56788c2d6fd1eee2847dfb6e47f67ff711525e","first_computed_at":"2026-07-05T10:44:20.137033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:20.137033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R5KS3mHt19zRrk8Zq8OuYxmTcnrETnrmtYZXPbeeAN/MzUPRvSj3U66cdEyusK/Q2G3WGbiQ6Vvb4gXTracFBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:20.137549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16198","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c8b0a82171163802f4671daefc5b4ecf911cf7d01c5e93f6fd2ac4696ee6c27","sha256:0a33eca32169e1e2e0c181a556ffb9a55b26b793f2ca6de1e1a29b9f30817080"],"state_sha256":"e51149671e1bd4a03d2705978401636254325d92e9cb123d1c002fd741333529"}