{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DDIUHV2X5P7HGDUISAKUYUNEZF","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":"d953b961c9469d0b277afa3ba2659708055e87266f3528019a3a404fddff00c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T04:54:30Z","title_canon_sha256":"77a7b3f867a0c20bc7f1323e9e8067b99619b46591f3b777d648dc50a196077b"},"schema_version":"1.0","source":{"id":"2411.13836","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13836","created_at":"2026-07-05T09:38:37Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13836v1","created_at":"2026-07-05T09:38:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13836","created_at":"2026-07-05T09:38:37Z"},{"alias_kind":"pith_short_12","alias_value":"DDIUHV2X5P7H","created_at":"2026-07-05T09:38:37Z"},{"alias_kind":"pith_short_16","alias_value":"DDIUHV2X5P7HGDUI","created_at":"2026-07-05T09:38:37Z"},{"alias_kind":"pith_short_8","alias_value":"DDIUHV2X","created_at":"2026-07-05T09:38:37Z"}],"graph_snapshots":[{"event_id":"sha256:0079b392d34a3ee288629d9ef7813143404c1111153b02e1a10e5d122051c491","target":"graph","created_at":"2026-07-05T09:38:37Z","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/2411.13836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) exhibits strong zero-shot classification ability on various image-level tasks, leading to the research to adapt CLIP for pixel-level open-vocabulary semantic segmentation without additional training. The key is to improve spatial representation of image-level CLIP, such as replacing self-attention map at last layer with self-self attention map or vision foundation model based attention map. In this paper, we present a novel hierarchical framework, named CLIPer, that hierarchically improves spatial representation of CLIP. The proposed CLIPer includ","authors_text":"Jiale Cao, Jin Xie, Lin Sun, Xiaoheng Jiang, Yanwei Pang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T04:54:30Z","title":"CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13836","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":"sha256:203d0d493aea56fd951032efef46ebfbc4819f4ef6d98413a5a4e1fd5f81e459","target":"record","created_at":"2026-07-05T09:38:37Z","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":"d953b961c9469d0b277afa3ba2659708055e87266f3528019a3a404fddff00c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T04:54:30Z","title_canon_sha256":"77a7b3f867a0c20bc7f1323e9e8067b99619b46591f3b777d648dc50a196077b"},"schema_version":"1.0","source":{"id":"2411.13836","kind":"arxiv","version":1}},"canonical_sha256":"18d143d757ebfe730e8890154c51a4c95368023db7f3138f887944cbe7296db4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18d143d757ebfe730e8890154c51a4c95368023db7f3138f887944cbe7296db4","first_computed_at":"2026-07-05T09:38:37.794393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:37.794393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b5HGz3CbHPRlkAAvhQbkVUqfPJFzVRVauZD/AyuEYApP2c3MMhxSS7eedjZ3W7HSQxmakN3tPQD0Yobe8Cx3Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:37.794802Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13836","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:203d0d493aea56fd951032efef46ebfbc4819f4ef6d98413a5a4e1fd5f81e459","sha256:0079b392d34a3ee288629d9ef7813143404c1111153b02e1a10e5d122051c491"],"state_sha256":"35e56ced38a2f7f62a066f03c14ee0135e94f21b52d67d3a822df161bf7df60e"}