{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L64OXB7C5GV4RVRLWPDF2ZVCJG","short_pith_number":"pith:L64OXB7C","schema_version":"1.0","canonical_sha256":"5fb8eb87e2e9abc8d62bb3c65d66a249b72dde91377de578462f6e933227b187","source":{"kind":"arxiv","id":"2503.19777","version":2},"attestation_state":"computed","paper":{"title":"LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Giorgos Tolias, Ji\\v{r}\\'i Matas, Vladan Stojni\\'c, Yannis Kalantidis","submitted_at":"2025-03-25T15:47:13Z","abstract_excerpt":"We propose a training-free method for open-vocabulary semantic segmentation using Vision-and-Language Models (VLMs). Our approach enhances the initial per-patch predictions of VLMs through label propagation, which jointly optimizes predictions by incorporating patch-to-patch relationships. Since VLMs are primarily optimized for cross-modal alignment and not for intra-modal similarity, we use a Vision Model (VM) that is observed to better capture these relationships. We address resolution limitations inherent to patch-based encoders by applying label propagation at the pixel level as a refineme"},"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":"2503.19777","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T15:47:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5306c68a3f7d7baee2d01a43aa63b4f2136fab89f0fe0891555857059c9ec11d","abstract_canon_sha256":"3138b7053fd9c153e708bd5c8e05b90df46c378bba9f90d19febc2af1310ef06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:49.241392Z","signature_b64":"F8Ztl+VrLeJMAV1lHOlbwL1eqHV7p5vWfp6ZstYZ1vL+8Ii05essYpgA33g6Q+cpn7L36hXiGiDXXUcYzSMvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fb8eb87e2e9abc8d62bb3c65d66a249b72dde91377de578462f6e933227b187","last_reissued_at":"2026-07-05T11:26:49.240897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:49.240897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Giorgos Tolias, Ji\\v{r}\\'i Matas, Vladan Stojni\\'c, Yannis Kalantidis","submitted_at":"2025-03-25T15:47:13Z","abstract_excerpt":"We propose a training-free method for open-vocabulary semantic segmentation using Vision-and-Language Models (VLMs). Our approach enhances the initial per-patch predictions of VLMs through label propagation, which jointly optimizes predictions by incorporating patch-to-patch relationships. Since VLMs are primarily optimized for cross-modal alignment and not for intra-modal similarity, we use a Vision Model (VM) that is observed to better capture these relationships. We address resolution limitations inherent to patch-based encoders by applying label propagation at the pixel level as a refineme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19777","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/2503.19777/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":"2503.19777","created_at":"2026-07-05T11:26:49.240954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19777v2","created_at":"2026-07-05T11:26:49.240954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19777","created_at":"2026-07-05T11:26:49.240954+00:00"},{"alias_kind":"pith_short_12","alias_value":"L64OXB7C5GV4","created_at":"2026-07-05T11:26:49.240954+00:00"},{"alias_kind":"pith_short_16","alias_value":"L64OXB7C5GV4RVRL","created_at":"2026-07-05T11:26:49.240954+00:00"},{"alias_kind":"pith_short_8","alias_value":"L64OXB7C","created_at":"2026-07-05T11:26:49.240954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09474","citing_title":"Training-Free Generalized Few-Shot Segmentation through Open-Vocabulary Semantic Arbitration","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L64OXB7C5GV4RVRLWPDF2ZVCJG","json":"https://pith.science/pith/L64OXB7C5GV4RVRLWPDF2ZVCJG.json","graph_json":"https://pith.science/api/pith-number/L64OXB7C5GV4RVRLWPDF2ZVCJG/graph.json","events_json":"https://pith.science/api/pith-number/L64OXB7C5GV4RVRLWPDF2ZVCJG/events.json","paper":"https://pith.science/paper/L64OXB7C"},"agent_actions":{"view_html":"https://pith.science/pith/L64OXB7C5GV4RVRLWPDF2ZVCJG","download_json":"https://pith.science/pith/L64OXB7C5GV4RVRLWPDF2ZVCJG.json","view_paper":"https://pith.science/paper/L64OXB7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19777&json=true","fetch_graph":"https://pith.science/api/pith-number/L64OXB7C5GV4RVRLWPDF2ZVCJG/graph.json","fetch_events":"https://pith.science/api/pith-number/L64OXB7C5GV4RVRLWPDF2ZVCJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L64OXB7C5GV4RVRLWPDF2ZVCJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L64OXB7C5GV4RVRLWPDF2ZVCJG/action/storage_attestation","attest_author":"https://pith.science/pith/L64OXB7C5GV4RVRLWPDF2ZVCJG/action/author_attestation","sign_citation":"https://pith.science/pith/L64OXB7C5GV4RVRLWPDF2ZVCJG/action/citation_signature","submit_replication":"https://pith.science/pith/L64OXB7C5GV4RVRLWPDF2ZVCJG/action/replication_record"}},"created_at":"2026-07-05T11:26:49.240954+00:00","updated_at":"2026-07-05T11:26:49.240954+00:00"}