{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DO3JTEXFDSSTHDK7ZNQDNBC7LC","short_pith_number":"pith:DO3JTEXF","schema_version":"1.0","canonical_sha256":"1bb69992e51ca5338d5fcb6036845f58b88468cbc0e576dcd0f64830d8ab5708","source":{"kind":"arxiv","id":"2605.15942","version":1},"attestation_state":"computed","paper":{"title":"Decomposed Vision-Language Alignment for Fine-Grained Open-Vocabulary Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenhao Wang, Yao Zhu, Yingrui Ji, Yu Meng","submitted_at":"2026-05-15T13:27:01Z","abstract_excerpt":"Open-vocabulary segmentation models often struggle to generalize to unseen combinations of object categories and attributes, because fine-grained descriptions are typically encoded as holistic sentences that entangle multiple semantic units. We propose a Decomposed Vision-Language Alignment framework that explicitly factorizes textual prompts into a concept token and multiple attribute tokens, enabling separate cross-modal interactions for each semantic unit. At the feature level, we introduce a Feature-Gated Cross-Attention module that generates attribute-specific gating maps to fuse informat"},"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":"2605.15942","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T13:27:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea187a45bc71ff9692217a11c6d03fdaa2fc9177aba74a43b73f3843dd4bcfaa","abstract_canon_sha256":"45b6672d517bfa7fc312383ce76f370d2c4d741dd3fc2b83c039cf2829bcc25c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:45.981886Z","signature_b64":"xbZyQg4AsUu/2EY0QH1Wu8a2apRqTZ7lXIsDa6zhZg9IeTIPPJBHZWlG9QKa7/Wltglf+s8YYFamuKk0tKVcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bb69992e51ca5338d5fcb6036845f58b88468cbc0e576dcd0f64830d8ab5708","last_reissued_at":"2026-05-20T00:01:45.981371Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:45.981371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decomposed Vision-Language Alignment for Fine-Grained Open-Vocabulary Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenhao Wang, Yao Zhu, Yingrui Ji, Yu Meng","submitted_at":"2026-05-15T13:27:01Z","abstract_excerpt":"Open-vocabulary segmentation models often struggle to generalize to unseen combinations of object categories and attributes, because fine-grained descriptions are typically encoded as holistic sentences that entangle multiple semantic units. We propose a Decomposed Vision-Language Alignment framework that explicitly factorizes textual prompts into a concept token and multiple attribute tokens, enabling separate cross-modal interactions for each semantic unit. At the feature level, we introduce a Feature-Gated Cross-Attention module that generates attribute-specific gating maps to fuse informat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15942","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/2605.15942/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:44.886323Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.724609Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"832522e9f83ce5b81e0cab25d7631343216ddf060756166d6f7710e9320aece5"},"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":"2605.15942","created_at":"2026-05-20T00:01:45.981472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15942v1","created_at":"2026-05-20T00:01:45.981472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15942","created_at":"2026-05-20T00:01:45.981472+00:00"},{"alias_kind":"pith_short_12","alias_value":"DO3JTEXFDSST","created_at":"2026-05-20T00:01:45.981472+00:00"},{"alias_kind":"pith_short_16","alias_value":"DO3JTEXFDSSTHDK7","created_at":"2026-05-20T00:01:45.981472+00:00"},{"alias_kind":"pith_short_8","alias_value":"DO3JTEXF","created_at":"2026-05-20T00:01:45.981472+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/DO3JTEXFDSSTHDK7ZNQDNBC7LC","json":"https://pith.science/pith/DO3JTEXFDSSTHDK7ZNQDNBC7LC.json","graph_json":"https://pith.science/api/pith-number/DO3JTEXFDSSTHDK7ZNQDNBC7LC/graph.json","events_json":"https://pith.science/api/pith-number/DO3JTEXFDSSTHDK7ZNQDNBC7LC/events.json","paper":"https://pith.science/paper/DO3JTEXF"},"agent_actions":{"view_html":"https://pith.science/pith/DO3JTEXFDSSTHDK7ZNQDNBC7LC","download_json":"https://pith.science/pith/DO3JTEXFDSSTHDK7ZNQDNBC7LC.json","view_paper":"https://pith.science/paper/DO3JTEXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15942&json=true","fetch_graph":"https://pith.science/api/pith-number/DO3JTEXFDSSTHDK7ZNQDNBC7LC/graph.json","fetch_events":"https://pith.science/api/pith-number/DO3JTEXFDSSTHDK7ZNQDNBC7LC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DO3JTEXFDSSTHDK7ZNQDNBC7LC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DO3JTEXFDSSTHDK7ZNQDNBC7LC/action/storage_attestation","attest_author":"https://pith.science/pith/DO3JTEXFDSSTHDK7ZNQDNBC7LC/action/author_attestation","sign_citation":"https://pith.science/pith/DO3JTEXFDSSTHDK7ZNQDNBC7LC/action/citation_signature","submit_replication":"https://pith.science/pith/DO3JTEXFDSSTHDK7ZNQDNBC7LC/action/replication_record"}},"created_at":"2026-05-20T00:01:45.981472+00:00","updated_at":"2026-05-20T00:01:45.981472+00:00"}