{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JGBGL2UZSDW44HLJKLDOWC2SHD","short_pith_number":"pith:JGBGL2UZ","canonical_record":{"source":{"id":"2310.01403","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:58:52Z","cross_cats_sorted":[],"title_canon_sha256":"679dd212ae79b63e54c0e3bb7e9584572bbb421887b2f5bc62d4ba14635fd20a","abstract_canon_sha256":"c4b47745fd31c9eecb97fc4de67f08e7d69e5ae8186108e6b2c02ecbe3a08620"},"schema_version":"1.0"},"canonical_sha256":"498265ea9990edce1d6952c6eb0b5238daca1908daa72e00a7f1b57c0acf1c72","source":{"kind":"arxiv","id":"2310.01403","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01403","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01403v2","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01403","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"JGBGL2UZSDW4","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"JGBGL2UZSDW44HLJ","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"JGBGL2UZ","created_at":"2026-07-05T07:36:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JGBGL2UZSDW44HLJKLDOWC2SHD","target":"record","payload":{"canonical_record":{"source":{"id":"2310.01403","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:58:52Z","cross_cats_sorted":[],"title_canon_sha256":"679dd212ae79b63e54c0e3bb7e9584572bbb421887b2f5bc62d4ba14635fd20a","abstract_canon_sha256":"c4b47745fd31c9eecb97fc4de67f08e7d69e5ae8186108e6b2c02ecbe3a08620"},"schema_version":"1.0"},"canonical_sha256":"498265ea9990edce1d6952c6eb0b5238daca1908daa72e00a7f1b57c0acf1c72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:54.871586Z","signature_b64":"+yn1Mteuz5FGCaBRp4tsbB++Za4Xa/mrxEw6eq2IsbrHP1r5vHfgsWbcx3pgXnaOJ8NjHYSwySRcLRsBFSOgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"498265ea9990edce1d6952c6eb0b5238daca1908daa72e00a7f1b57c0acf1c72","last_reissued_at":"2026-07-05T07:36:54.871161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:54.871161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.01403","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7e93XOPfv2paM1qjLoN51bJguKlUfGEBTan8NiI5uWRQqPIKNHyTp2ikGk5rlU1HaNydzrP3C2GQWNbMDQh1Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T19:53:01.346571Z"},"content_sha256":"1b9b5b5497fbc3b63e9477a82e4727d8335fb7c8b461bdeabe65144f37b15080","schema_version":"1.0","event_id":"sha256:1b9b5b5497fbc3b63e9477a82e4727d8335fb7c8b461bdeabe65144f37b15080"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JGBGL2UZSDW44HLJKLDOWC2SHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Lumin Xu, Sheng Jin, Size Wu, Wentao Liu, Wenwei Zhang, Xiangtai Li","submitted_at":"2023-10-02T17:58:52Z","abstract_excerpt":"Open-vocabulary dense prediction tasks including object detection and image segmentation have been advanced by the success of Contrastive Language-Image Pre-training (CLIP). CLIP models, particularly those incorporating vision transformers (ViTs), have exhibited remarkable generalization ability in zero-shot image classification. However, when transferring the vision-language alignment of CLIP from global image representation to local region representation for the open-vocabulary dense prediction tasks, CLIP ViTs suffer from the domain shift from full images to local image regions. In this pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01403","kind":"arxiv","version":2},"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/2310.01403/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xnqvA1imT3nY42lD6IsVcRmnnKru8YkptSQotI3qDmeMLeMgA+YsduetbT3Z+gfisoUzbxQj7VXUEhkP2yXtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T19:53:01.346943Z"},"content_sha256":"75c1dc5eaec2589bde8ff3a4d97176ab121564cbbd4655eb48b749e244ac1509","schema_version":"1.0","event_id":"sha256:75c1dc5eaec2589bde8ff3a4d97176ab121564cbbd4655eb48b749e244ac1509"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD/bundle.json","state_url":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JGBGL2UZSDW44HLJKLDOWC2SHD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-26T19:53:01Z","links":{"resolver":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD","bundle":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD/bundle.json","state":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JGBGL2UZSDW44HLJKLDOWC2SHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JGBGL2UZSDW44HLJKLDOWC2SHD","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":"c4b47745fd31c9eecb97fc4de67f08e7d69e5ae8186108e6b2c02ecbe3a08620","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:58:52Z","title_canon_sha256":"679dd212ae79b63e54c0e3bb7e9584572bbb421887b2f5bc62d4ba14635fd20a"},"schema_version":"1.0","source":{"id":"2310.01403","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01403","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01403v2","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01403","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"JGBGL2UZSDW4","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"JGBGL2UZSDW44HLJ","created_at":"2026-07-05T07:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"JGBGL2UZ","created_at":"2026-07-05T07:36:54Z"}],"graph_snapshots":[{"event_id":"sha256:75c1dc5eaec2589bde8ff3a4d97176ab121564cbbd4655eb48b749e244ac1509","target":"graph","created_at":"2026-07-05T07:36:54Z","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/2310.01403/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary dense prediction tasks including object detection and image segmentation have been advanced by the success of Contrastive Language-Image Pre-training (CLIP). CLIP models, particularly those incorporating vision transformers (ViTs), have exhibited remarkable generalization ability in zero-shot image classification. However, when transferring the vision-language alignment of CLIP from global image representation to local region representation for the open-vocabulary dense prediction tasks, CLIP ViTs suffer from the domain shift from full images to local image regions. In this pap","authors_text":"Chen Change Loy, Lumin Xu, Sheng Jin, Size Wu, Wentao Liu, Wenwei Zhang, Xiangtai Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:58:52Z","title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01403","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":"sha256:1b9b5b5497fbc3b63e9477a82e4727d8335fb7c8b461bdeabe65144f37b15080","target":"record","created_at":"2026-07-05T07:36:54Z","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":"c4b47745fd31c9eecb97fc4de67f08e7d69e5ae8186108e6b2c02ecbe3a08620","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:58:52Z","title_canon_sha256":"679dd212ae79b63e54c0e3bb7e9584572bbb421887b2f5bc62d4ba14635fd20a"},"schema_version":"1.0","source":{"id":"2310.01403","kind":"arxiv","version":2}},"canonical_sha256":"498265ea9990edce1d6952c6eb0b5238daca1908daa72e00a7f1b57c0acf1c72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"498265ea9990edce1d6952c6eb0b5238daca1908daa72e00a7f1b57c0acf1c72","first_computed_at":"2026-07-05T07:36:54.871161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:54.871161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+yn1Mteuz5FGCaBRp4tsbB++Za4Xa/mrxEw6eq2IsbrHP1r5vHfgsWbcx3pgXnaOJ8NjHYSwySRcLRsBFSOgAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:54.871586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.01403","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b9b5b5497fbc3b63e9477a82e4727d8335fb7c8b461bdeabe65144f37b15080","sha256:75c1dc5eaec2589bde8ff3a4d97176ab121564cbbd4655eb48b749e244ac1509"],"state_sha256":"8df293d4fe731bfbe9bfb706c015fa2104d79d32b6a40808b2c630384906f1e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bnQL8oo/EzZmZTHfgSMY5mWyQwp48Jwf337c3Q4293MFwyf2pV0yD2LuZnQl8LDriu8+dNy9S6RgzqZekQAFAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T19:53:01.349403Z","bundle_sha256":"7f3815fcde2a42943ee302627a4fe749f58b76ab98a9f05d94168f134aefefa4"}}