{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AM5O3CQ3QVMUCLPA4V64MA4JG7","short_pith_number":"pith:AM5O3CQ3","schema_version":"1.0","canonical_sha256":"033aed8a1b8559412de0e57dc6038937d5ae6f4cfab7c062e54950ae4a575dba","source":{"kind":"arxiv","id":"2508.06115","version":3},"attestation_state":"computed","paper":{"title":"SynSeg: Feature Synergy for Multi-Category Contrastive Learning in End-to-End Open-Vocabulary Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Dang, Kebin Liu, Weichen Zhang, Xikai Sun, Yunhao Liu, Zhui Zhu","submitted_at":"2025-08-08T08:26:41Z","abstract_excerpt":"Semantic segmentation in open-vocabulary scenarios presents significant challenges due to the wide range and granularity of semantic categories. Existing weakly-supervised methods often rely on category-specific supervision and ill-suited feature construction methods for contrastive learning, leading to semantic misalignment and poor performance. In this work, we introduce a novel weakly-supervised approach, SynSeg, to address the challenges. SynSeg performs Multi-Category Contrastive Learning (MCCL) as a stronger training signal which robustly injecting intra- and inter-category knowledge dur"},"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":"2508.06115","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-08T08:26:41Z","cross_cats_sorted":[],"title_canon_sha256":"752a2276e2505885b869189c225bd3abefa77b54c2c096041bf9d37237064d6c","abstract_canon_sha256":"f3826c1de6135a76a55117a25e621ebee1ac2437e44129a2020d609e2e76c736"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:03.606260Z","signature_b64":"VHmX2jHQGZOYt5a1AMJ4xVEH9X6Q1cv1tmUhsEl0slrIVycd7iZ2rEBgxST3ELrcAoBmYQyI0vySjYqMr0haAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"033aed8a1b8559412de0e57dc6038937d5ae6f4cfab7c062e54950ae4a575dba","last_reissued_at":"2026-06-29T01:14:03.605749Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:03.605749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynSeg: Feature Synergy for Multi-Category Contrastive Learning in End-to-End Open-Vocabulary Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Dang, Kebin Liu, Weichen Zhang, Xikai Sun, Yunhao Liu, Zhui Zhu","submitted_at":"2025-08-08T08:26:41Z","abstract_excerpt":"Semantic segmentation in open-vocabulary scenarios presents significant challenges due to the wide range and granularity of semantic categories. Existing weakly-supervised methods often rely on category-specific supervision and ill-suited feature construction methods for contrastive learning, leading to semantic misalignment and poor performance. In this work, we introduce a novel weakly-supervised approach, SynSeg, to address the challenges. SynSeg performs Multi-Category Contrastive Learning (MCCL) as a stronger training signal which robustly injecting intra- and inter-category knowledge dur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06115","kind":"arxiv","version":3},"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/2508.06115/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":"2508.06115","created_at":"2026-06-29T01:14:03.605806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06115v3","created_at":"2026-06-29T01:14:03.605806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06115","created_at":"2026-06-29T01:14:03.605806+00:00"},{"alias_kind":"pith_short_12","alias_value":"AM5O3CQ3QVMU","created_at":"2026-06-29T01:14:03.605806+00:00"},{"alias_kind":"pith_short_16","alias_value":"AM5O3CQ3QVMUCLPA","created_at":"2026-06-29T01:14:03.605806+00:00"},{"alias_kind":"pith_short_8","alias_value":"AM5O3CQ3","created_at":"2026-06-29T01:14:03.605806+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/AM5O3CQ3QVMUCLPA4V64MA4JG7","json":"https://pith.science/pith/AM5O3CQ3QVMUCLPA4V64MA4JG7.json","graph_json":"https://pith.science/api/pith-number/AM5O3CQ3QVMUCLPA4V64MA4JG7/graph.json","events_json":"https://pith.science/api/pith-number/AM5O3CQ3QVMUCLPA4V64MA4JG7/events.json","paper":"https://pith.science/paper/AM5O3CQ3"},"agent_actions":{"view_html":"https://pith.science/pith/AM5O3CQ3QVMUCLPA4V64MA4JG7","download_json":"https://pith.science/pith/AM5O3CQ3QVMUCLPA4V64MA4JG7.json","view_paper":"https://pith.science/paper/AM5O3CQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06115&json=true","fetch_graph":"https://pith.science/api/pith-number/AM5O3CQ3QVMUCLPA4V64MA4JG7/graph.json","fetch_events":"https://pith.science/api/pith-number/AM5O3CQ3QVMUCLPA4V64MA4JG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AM5O3CQ3QVMUCLPA4V64MA4JG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AM5O3CQ3QVMUCLPA4V64MA4JG7/action/storage_attestation","attest_author":"https://pith.science/pith/AM5O3CQ3QVMUCLPA4V64MA4JG7/action/author_attestation","sign_citation":"https://pith.science/pith/AM5O3CQ3QVMUCLPA4V64MA4JG7/action/citation_signature","submit_replication":"https://pith.science/pith/AM5O3CQ3QVMUCLPA4V64MA4JG7/action/replication_record"}},"created_at":"2026-06-29T01:14:03.605806+00:00","updated_at":"2026-06-29T01:14:03.605806+00:00"}