{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IEL4UMBWBLX2WCPCQC6BN3TGQ6","short_pith_number":"pith:IEL4UMBW","schema_version":"1.0","canonical_sha256":"4117ca30360aefab09e280bc16ee668797a40c0aaee705949e1a7aaf50946d1b","source":{"kind":"arxiv","id":"2301.12171","version":2},"attestation_state":"computed","paper":{"title":"ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jong Chul Ye, Kwanyoung Kim, Yujin Oh","submitted_at":"2023-01-28T11:51:20Z","abstract_excerpt":"Recent success of large-scale Contrastive Language-Image Pre-training (CLIP) has led to great promise in zero-shot semantic segmentation by transferring image-text aligned knowledge to pixel-level classification. However, existing methods usually require an additional image encoder or retraining/tuning the CLIP module. Here, we propose a novel Zero-shot segmentation with Optimal Transport (ZegOT) method that matches multiple text prompts with frozen image embeddings through optimal transport. In particular, we introduce a novel Multiple Prompt Optimal Transport Solver (MPOT), which is designed"},"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":"2301.12171","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-28T11:51:20Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"9f4635f3d315ebc498d6f90224a9528084e0d273e277b020f79879a35420fff1","abstract_canon_sha256":"d2bbc2ceca66d2396d2af00a267e76633b6574fc146f9632868ab1c39eb14e55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:22.822586Z","signature_b64":"Y4AmV3PookwB7eUV/u/q8PraEpRfdjcFC0tgFaC0OYSl8o1M8uZajH+nq0tKsuTWbhGb+i5mCuZQiSn1mnmmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4117ca30360aefab09e280bc16ee668797a40c0aaee705949e1a7aaf50946d1b","last_reissued_at":"2026-07-05T06:15:22.822049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:22.822049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jong Chul Ye, Kwanyoung Kim, Yujin Oh","submitted_at":"2023-01-28T11:51:20Z","abstract_excerpt":"Recent success of large-scale Contrastive Language-Image Pre-training (CLIP) has led to great promise in zero-shot semantic segmentation by transferring image-text aligned knowledge to pixel-level classification. However, existing methods usually require an additional image encoder or retraining/tuning the CLIP module. Here, we propose a novel Zero-shot segmentation with Optimal Transport (ZegOT) method that matches multiple text prompts with frozen image embeddings through optimal transport. In particular, we introduce a novel Multiple Prompt Optimal Transport Solver (MPOT), which is designed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12171","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/2301.12171/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":"2301.12171","created_at":"2026-07-05T06:15:22.822224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12171v2","created_at":"2026-07-05T06:15:22.822224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12171","created_at":"2026-07-05T06:15:22.822224+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEL4UMBWBLX2","created_at":"2026-07-05T06:15:22.822224+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEL4UMBWBLX2WCPC","created_at":"2026-07-05T06:15:22.822224+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEL4UMBW","created_at":"2026-07-05T06:15:22.822224+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03706","citing_title":"OV-COAST: Cost Aggregation with Optimal Transport for Open-Vocabulary Semantic Segmentation","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IEL4UMBWBLX2WCPCQC6BN3TGQ6","json":"https://pith.science/pith/IEL4UMBWBLX2WCPCQC6BN3TGQ6.json","graph_json":"https://pith.science/api/pith-number/IEL4UMBWBLX2WCPCQC6BN3TGQ6/graph.json","events_json":"https://pith.science/api/pith-number/IEL4UMBWBLX2WCPCQC6BN3TGQ6/events.json","paper":"https://pith.science/paper/IEL4UMBW"},"agent_actions":{"view_html":"https://pith.science/pith/IEL4UMBWBLX2WCPCQC6BN3TGQ6","download_json":"https://pith.science/pith/IEL4UMBWBLX2WCPCQC6BN3TGQ6.json","view_paper":"https://pith.science/paper/IEL4UMBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12171&json=true","fetch_graph":"https://pith.science/api/pith-number/IEL4UMBWBLX2WCPCQC6BN3TGQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/IEL4UMBWBLX2WCPCQC6BN3TGQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEL4UMBWBLX2WCPCQC6BN3TGQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEL4UMBWBLX2WCPCQC6BN3TGQ6/action/storage_attestation","attest_author":"https://pith.science/pith/IEL4UMBWBLX2WCPCQC6BN3TGQ6/action/author_attestation","sign_citation":"https://pith.science/pith/IEL4UMBWBLX2WCPCQC6BN3TGQ6/action/citation_signature","submit_replication":"https://pith.science/pith/IEL4UMBWBLX2WCPCQC6BN3TGQ6/action/replication_record"}},"created_at":"2026-07-05T06:15:22.822224+00:00","updated_at":"2026-07-05T06:15:22.822224+00:00"}