{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DO3JTEXFDSSTHDK7ZNQDNBC7LC","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"45b6672d517bfa7fc312383ce76f370d2c4d741dd3fc2b83c039cf2829bcc25c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T13:27:01Z","title_canon_sha256":"ea187a45bc71ff9692217a11c6d03fdaa2fc9177aba74a43b73f3843dd4bcfaa"},"schema_version":"1.0","source":{"id":"2605.15942","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15942","created_at":"2026-05-20T00:01:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15942v1","created_at":"2026-05-20T00:01:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15942","created_at":"2026-05-20T00:01:45Z"},{"alias_kind":"pith_short_12","alias_value":"DO3JTEXFDSST","created_at":"2026-05-20T00:01:45Z"},{"alias_kind":"pith_short_16","alias_value":"DO3JTEXFDSSTHDK7","created_at":"2026-05-20T00:01:45Z"},{"alias_kind":"pith_short_8","alias_value":"DO3JTEXF","created_at":"2026-05-20T00:01:45Z"}],"graph_snapshots":[{"event_id":"sha256:e94e740a36ba379015653d2f49b05852367adc4b40afab3c355e08611ff7b7fb","target":"graph","created_at":"2026-05-20T00:01:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.15942/integrity.json","findings":[],"snapshot_sha256":"832522e9f83ce5b81e0cab25d7631343216ddf060756166d6f7710e9320aece5","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenhao Wang, Yao Zhu, Yingrui Ji, Yu Meng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T13:27:01Z","title":"Decomposed Vision-Language Alignment for Fine-Grained Open-Vocabulary Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15942","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:033edc224a3b8f1e5eea808536d2e918008540cce7e59aab6bf5015d7c521fe4","target":"record","created_at":"2026-05-20T00:01:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"45b6672d517bfa7fc312383ce76f370d2c4d741dd3fc2b83c039cf2829bcc25c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T13:27:01Z","title_canon_sha256":"ea187a45bc71ff9692217a11c6d03fdaa2fc9177aba74a43b73f3843dd4bcfaa"},"schema_version":"1.0","source":{"id":"2605.15942","kind":"arxiv","version":1}},"canonical_sha256":"1bb69992e51ca5338d5fcb6036845f58b88468cbc0e576dcd0f64830d8ab5708","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bb69992e51ca5338d5fcb6036845f58b88468cbc0e576dcd0f64830d8ab5708","first_computed_at":"2026-05-20T00:01:45.981371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:45.981371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xbZyQg4AsUu/2EY0QH1Wu8a2apRqTZ7lXIsDa6zhZg9IeTIPPJBHZWlG9QKa7/Wltglf+s8YYFamuKk0tKVcCA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:45.981886Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15942","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:c925961b245a3ae420be42faf65fc080d1d8c46cce5e903e09274c668f584196","sha256:d87c6f7042d9a3774d57a084bd09ba3c76ebb2ab712d89de51849b4bbbace3fe"]}],"invalid_events":[],"applied_event_ids":["sha256:033edc224a3b8f1e5eea808536d2e918008540cce7e59aab6bf5015d7c521fe4","sha256:e94e740a36ba379015653d2f49b05852367adc4b40afab3c355e08611ff7b7fb"],"state_sha256":"3563ff46d64a689ca0b8d468183c5a8640f8be611b9fa2a82fca5153d467cacd"}