{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EC4XSB22UR6BLYWWDECOXSPEGP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0629e2fe4db43a5f9050c2a1bcf623d4d37d24b1b0ff8119554a99ecf1904a7f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:48:08Z","title_canon_sha256":"60e44aafa3df874bec2bc47f521d741dfd92ef86f5275c9e4dc748ef74d0500d"},"schema_version":"1.0","source":{"id":"2408.00744","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.00744","created_at":"2026-07-05T09:44:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.00744v2","created_at":"2026-07-05T09:44:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00744","created_at":"2026-07-05T09:44:13Z"},{"alias_kind":"pith_short_12","alias_value":"EC4XSB22UR6B","created_at":"2026-07-05T09:44:13Z"},{"alias_kind":"pith_short_16","alias_value":"EC4XSB22UR6BLYWW","created_at":"2026-07-05T09:44:13Z"},{"alias_kind":"pith_short_8","alias_value":"EC4XSB22","created_at":"2026-07-05T09:44:13Z"}],"graph_snapshots":[{"event_id":"sha256:2c079e2c017cdd14637f4c0880fb1559d315173c7a1591d553283d1fdba8e8bb","target":"graph","created_at":"2026-07-05T09:44:13Z","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":[],"endpoint":"/pith/2408.00744/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained vision-language models, e.g. CLIP, have been increasingly used to address the challenging Open-Vocabulary Segmentation (OVS) task, benefiting from their well-aligned vision-text embedding space. Typical solutions involve either freezing CLIP during training to unilaterally maintain its zero-shot capability, or fine-tuning CLIP vision encoder to achieve perceptual sensitivity to local regions. However, few of them incorporate vision-text collaborative optimization. Based on this, we propose the Content-Dependent Transfer to adaptively enhance each text embedding by interacting with ","authors_text":"Hongguang Zhu, Humphrey Shi, Jiannan Huang, Siyu Jiao, Yao Zhao, Yunchao Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:48:08Z","title":"Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00744","kind":"arxiv","version":2},"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:a0f60f08375de702840af6978c82bcbc53e570af587676af6d415cd7a5f413d8","target":"record","created_at":"2026-07-05T09:44:13Z","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":"0629e2fe4db43a5f9050c2a1bcf623d4d37d24b1b0ff8119554a99ecf1904a7f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:48:08Z","title_canon_sha256":"60e44aafa3df874bec2bc47f521d741dfd92ef86f5275c9e4dc748ef74d0500d"},"schema_version":"1.0","source":{"id":"2408.00744","kind":"arxiv","version":2}},"canonical_sha256":"20b979075aa47c15e2d61904ebc9e433f7a65a2850928a45bd3538174d96e2ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20b979075aa47c15e2d61904ebc9e433f7a65a2850928a45bd3538174d96e2ba","first_computed_at":"2026-07-05T09:44:13.540661Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:13.540661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0vwunNcI4zCdGDDHJeq3JbIRJgI8JkDypLzr/WJWwJXXjFRotRsDABYuKncy8Jrw/xEub05p/Wzt2rMhYfkMDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:13.541139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.00744","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0f60f08375de702840af6978c82bcbc53e570af587676af6d415cd7a5f413d8","sha256:2c079e2c017cdd14637f4c0880fb1559d315173c7a1591d553283d1fdba8e8bb"],"state_sha256":"b5d6f3b634991dec5e739e1eaee9db04f1d6c8cc831cd992203e50e6972c7b7d"}