{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WWHLL4AK2KAMSYWURNIWAW4JOC","short_pith_number":"pith:WWHLL4AK","schema_version":"1.0","canonical_sha256":"b58eb5f00ad280c962d48b51605b897083be4c8e29470bc1ec7be300bafff730","source":{"kind":"arxiv","id":"2407.08268","version":1},"attestation_state":"computed","paper":{"title":"Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Zhao, Jingyong Su, Tong Shao, Zhuotao Tian","submitted_at":"2024-07-11T08:12:16Z","abstract_excerpt":"CLIP, as a vision-language model, has significantly advanced Open-Vocabulary Semantic Segmentation (OVSS) with its zero-shot capabilities. Despite its success, its application to OVSS faces challenges due to its initial image-level alignment training, which affects its performance in tasks requiring detailed local context. Our study delves into the impact of CLIP's [CLS] token on patch feature correlations, revealing a dominance of \"global\" patches that hinders local feature discrimination. To overcome this, we propose CLIPtrase, a novel training-free semantic segmentation strategy that enhanc"},"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":"2407.08268","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T08:12:16Z","cross_cats_sorted":[],"title_canon_sha256":"b0f6d51fd891d8bff003174b106aa1402dbcdc8367c554d7aac73735692266da","abstract_canon_sha256":"8748da34d832345b8b3811e78f784ad44bd92cdedb8614193d824e35412fd1ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:45.940482Z","signature_b64":"zsQYIp+F/puOxtUnBIgdBuu3It/oSq7UtvlMrxDIgWvJZV/cmhiTYKTKi0DRsyb6QHIDXkxz1xdYMYpP4pxyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b58eb5f00ad280c962d48b51605b897083be4c8e29470bc1ec7be300bafff730","last_reissued_at":"2026-07-05T08:42:45.940076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:45.940076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Zhao, Jingyong Su, Tong Shao, Zhuotao Tian","submitted_at":"2024-07-11T08:12:16Z","abstract_excerpt":"CLIP, as a vision-language model, has significantly advanced Open-Vocabulary Semantic Segmentation (OVSS) with its zero-shot capabilities. Despite its success, its application to OVSS faces challenges due to its initial image-level alignment training, which affects its performance in tasks requiring detailed local context. Our study delves into the impact of CLIP's [CLS] token on patch feature correlations, revealing a dominance of \"global\" patches that hinders local feature discrimination. To overcome this, we propose CLIPtrase, a novel training-free semantic segmentation strategy that enhanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08268","kind":"arxiv","version":1},"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/2407.08268/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":"2407.08268","created_at":"2026-07-05T08:42:45.940130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08268v1","created_at":"2026-07-05T08:42:45.940130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08268","created_at":"2026-07-05T08:42:45.940130+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWHLL4AK2KAM","created_at":"2026-07-05T08:42:45.940130+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWHLL4AK2KAMSYWU","created_at":"2026-07-05T08:42:45.940130+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWHLL4AK","created_at":"2026-07-05T08:42:45.940130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07135","citing_title":"Sparse Attention for Dense Open-Vocabulary Prediction in CLIP","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WWHLL4AK2KAMSYWURNIWAW4JOC","json":"https://pith.science/pith/WWHLL4AK2KAMSYWURNIWAW4JOC.json","graph_json":"https://pith.science/api/pith-number/WWHLL4AK2KAMSYWURNIWAW4JOC/graph.json","events_json":"https://pith.science/api/pith-number/WWHLL4AK2KAMSYWURNIWAW4JOC/events.json","paper":"https://pith.science/paper/WWHLL4AK"},"agent_actions":{"view_html":"https://pith.science/pith/WWHLL4AK2KAMSYWURNIWAW4JOC","download_json":"https://pith.science/pith/WWHLL4AK2KAMSYWURNIWAW4JOC.json","view_paper":"https://pith.science/paper/WWHLL4AK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08268&json=true","fetch_graph":"https://pith.science/api/pith-number/WWHLL4AK2KAMSYWURNIWAW4JOC/graph.json","fetch_events":"https://pith.science/api/pith-number/WWHLL4AK2KAMSYWURNIWAW4JOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWHLL4AK2KAMSYWURNIWAW4JOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWHLL4AK2KAMSYWURNIWAW4JOC/action/storage_attestation","attest_author":"https://pith.science/pith/WWHLL4AK2KAMSYWURNIWAW4JOC/action/author_attestation","sign_citation":"https://pith.science/pith/WWHLL4AK2KAMSYWURNIWAW4JOC/action/citation_signature","submit_replication":"https://pith.science/pith/WWHLL4AK2KAMSYWURNIWAW4JOC/action/replication_record"}},"created_at":"2026-07-05T08:42:45.940130+00:00","updated_at":"2026-07-05T08:42:45.940130+00:00"}