{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DQWMDIF3BVNJEFGWB2U2HKHQAL","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":"69734dea8b957592e1aadd6a40238910fbdb45dca6e34ef042a3ef13cd46436a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T09:52:20Z","title_canon_sha256":"65ee95b69c18dfc261223f628b60065ab4b51e1043be553151d4a066deda283e"},"schema_version":"1.0","source":{"id":"2407.12442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12442","created_at":"2026-07-05T08:45:04Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12442v1","created_at":"2026-07-05T08:45:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12442","created_at":"2026-07-05T08:45:04Z"},{"alias_kind":"pith_short_12","alias_value":"DQWMDIF3BVNJ","created_at":"2026-07-05T08:45:04Z"},{"alias_kind":"pith_short_16","alias_value":"DQWMDIF3BVNJEFGW","created_at":"2026-07-05T08:45:04Z"},{"alias_kind":"pith_short_8","alias_value":"DQWMDIF3","created_at":"2026-07-05T08:45:04Z"}],"graph_snapshots":[{"event_id":"sha256:42b76b4d41f6d6f00157fae00101362e7e5a83d40e4e55bec432aede7153a2ee","target":"graph","created_at":"2026-07-05T08:45:04Z","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/2407.12442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the success of large-scale pretrained Vision-Language Models (VLMs) especially CLIP in various open-vocabulary tasks, their application to semantic segmentation remains challenging, producing noisy segmentation maps with mis-segmented regions. In this paper, we carefully re-investigate the architecture of CLIP, and identify residual connections as the primary source of noise that degrades segmentation quality. With a comparative analysis of statistical properties in the residual connection and the attention output across different pretrained models, we discover that CLIP's image-text c","authors_text":"Chaofeng Chen, Litong Feng, Mengcheng Lan, Wayne Zhang, Xinjiang Wang, Yiping Ke","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T09:52:20Z","title":"ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12442","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":"sha256:28e310d9143c8a9757d6d956b5120581e8962ed232015b5d59a130f470af0b61","target":"record","created_at":"2026-07-05T08:45:04Z","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":"69734dea8b957592e1aadd6a40238910fbdb45dca6e34ef042a3ef13cd46436a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T09:52:20Z","title_canon_sha256":"65ee95b69c18dfc261223f628b60065ab4b51e1043be553151d4a066deda283e"},"schema_version":"1.0","source":{"id":"2407.12442","kind":"arxiv","version":1}},"canonical_sha256":"1c2cc1a0bb0d5a9214d60ea9a3a8f002f9c271e3a1d6a17a7b5d1c66a2343ec4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c2cc1a0bb0d5a9214d60ea9a3a8f002f9c271e3a1d6a17a7b5d1c66a2343ec4","first_computed_at":"2026-07-05T08:45:04.662401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:04.662401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rrG5nzlbL+mGT/FdXv5J3HFkD6jFyj6jhghAuqo9EG5C3PSxm91r/O9apxqDlvclvw+hKddV7YI3Rip0ms3ZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:04.662811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28e310d9143c8a9757d6d956b5120581e8962ed232015b5d59a130f470af0b61","sha256:42b76b4d41f6d6f00157fae00101362e7e5a83d40e4e55bec432aede7153a2ee"],"state_sha256":"641fa59881c675efa040183c217155f329f3dd09d8e8962c924ff9cc230818e2"}