{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KJYAICR3HQNVXED3SRNHSD3PIB","short_pith_number":"pith:KJYAICR3","schema_version":"1.0","canonical_sha256":"5270040a3b3c1b5b907b945a790f6f406d04db1037b9b3b90654c7a451589c9e","source":{"kind":"arxiv","id":"2411.15851","version":2},"attestation_state":"computed","paper":{"title":"ResCLIP: Residual Attention for Training-free Dense Vision-language Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinhong Deng, Lixin Duan, Wen Li, Yuhang Yang","submitted_at":"2024-11-24T14:14:14Z","abstract_excerpt":"While vision-language models like CLIP have shown remarkable success in open-vocabulary tasks, their application is currently confined to image-level tasks, and they still struggle with dense predictions. Recent works often attribute such deficiency in dense predictions to the self-attention layers in the final block, and have achieved commendable results by modifying the original query-key attention to self-correlation attention, (e.g., query-query and key-key attention). However, these methods overlook the cross-correlation attention (query-key) properties, which capture the rich spatial cor"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.15851","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-24T14:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"4444e709135f02af5ec0d05e300a14705fd98c9fa4c37dc030e8b9da77404982","abstract_canon_sha256":"a73c5f3f01a7732e4a0db7edaa2408d601306982f5940da7c4aab84002c99490"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:05:40.153286Z","signature_b64":"e/K6/PwjCkDFPuCd3ZnrGWeM0dFBPe8D0JQQDO7uHXySVFD45YRZn5Qe+/+YJXp6v6UTokQ5ayKAw5QtdUPVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5270040a3b3c1b5b907b945a790f6f406d04db1037b9b3b90654c7a451589c9e","last_reissued_at":"2026-06-03T02:05:40.152783Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:05:40.152783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ResCLIP: Residual Attention for Training-free Dense Vision-language Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinhong Deng, Lixin Duan, Wen Li, Yuhang Yang","submitted_at":"2024-11-24T14:14:14Z","abstract_excerpt":"While vision-language models like CLIP have shown remarkable success in open-vocabulary tasks, their application is currently confined to image-level tasks, and they still struggle with dense predictions. Recent works often attribute such deficiency in dense predictions to the self-attention layers in the final block, and have achieved commendable results by modifying the original query-key attention to self-correlation attention, (e.g., query-query and key-key attention). However, these methods overlook the cross-correlation attention (query-key) properties, which capture the rich spatial cor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15851","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/2411.15851/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.15851","created_at":"2026-06-03T02:05:40.152841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15851v2","created_at":"2026-06-03T02:05:40.152841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15851","created_at":"2026-06-03T02:05:40.152841+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJYAICR3HQNV","created_at":"2026-06-03T02:05:40.152841+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJYAICR3HQNVXED3","created_at":"2026-06-03T02:05:40.152841+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJYAICR3","created_at":"2026-06-03T02:05:40.152841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJYAICR3HQNVXED3SRNHSD3PIB","json":"https://pith.science/pith/KJYAICR3HQNVXED3SRNHSD3PIB.json","graph_json":"https://pith.science/api/pith-number/KJYAICR3HQNVXED3SRNHSD3PIB/graph.json","events_json":"https://pith.science/api/pith-number/KJYAICR3HQNVXED3SRNHSD3PIB/events.json","paper":"https://pith.science/paper/KJYAICR3"},"agent_actions":{"view_html":"https://pith.science/pith/KJYAICR3HQNVXED3SRNHSD3PIB","download_json":"https://pith.science/pith/KJYAICR3HQNVXED3SRNHSD3PIB.json","view_paper":"https://pith.science/paper/KJYAICR3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15851&json=true","fetch_graph":"https://pith.science/api/pith-number/KJYAICR3HQNVXED3SRNHSD3PIB/graph.json","fetch_events":"https://pith.science/api/pith-number/KJYAICR3HQNVXED3SRNHSD3PIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJYAICR3HQNVXED3SRNHSD3PIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJYAICR3HQNVXED3SRNHSD3PIB/action/storage_attestation","attest_author":"https://pith.science/pith/KJYAICR3HQNVXED3SRNHSD3PIB/action/author_attestation","sign_citation":"https://pith.science/pith/KJYAICR3HQNVXED3SRNHSD3PIB/action/citation_signature","submit_replication":"https://pith.science/pith/KJYAICR3HQNVXED3SRNHSD3PIB/action/replication_record"}},"created_at":"2026-06-03T02:05:40.152841+00:00","updated_at":"2026-06-03T02:05:40.152841+00:00"}