{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KAYZUY2A42F4UKYFIOL7CBZTJQ","short_pith_number":"pith:KAYZUY2A","canonical_record":{"source":{"id":"2410.02746","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:56:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"84f6f4166f63610a545fdb4b5a736619c2846fa4e75d8b7c6c281181d5425d1f","abstract_canon_sha256":"92086bf0cf86f2b1937a071e9fd123012473340ce50ebe7ba811b35fa3efece5"},"schema_version":"1.0"},"canonical_sha256":"50319a6340e68bca2b054397f107334c067a5d9669b0c209b5b9ed62a67f229d","source":{"kind":"arxiv","id":"2410.02746","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02746","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02746v2","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02746","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"pith_short_12","alias_value":"KAYZUY2A42F4","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"pith_short_16","alias_value":"KAYZUY2A42F4UKYF","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"pith_short_8","alias_value":"KAYZUY2A","created_at":"2026-07-05T10:16:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KAYZUY2A42F4UKYFIOL7CBZTJQ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.02746","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:56:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"84f6f4166f63610a545fdb4b5a736619c2846fa4e75d8b7c6c281181d5425d1f","abstract_canon_sha256":"92086bf0cf86f2b1937a071e9fd123012473340ce50ebe7ba811b35fa3efece5"},"schema_version":"1.0"},"canonical_sha256":"50319a6340e68bca2b054397f107334c067a5d9669b0c209b5b9ed62a67f229d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:38.323420Z","signature_b64":"sJaGEn7aFPD3Wq4xVGUdyfX8565OdAaF6qED6gerSKqTJ1N1+/xC8UkJmm1WY5mHP99qjfKVB6QAf/6O1+flAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50319a6340e68bca2b054397f107334c067a5d9669b0c209b5b9ed62a67f229d","last_reissued_at":"2026-07-05T10:16:38.322823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:38.322823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.02746","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":"2026-07-05T10:16:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0y4Q1Kofvi9eCDloInwTrweKDDq2IPWMnuMdh8M/AesWLH1FEp08Zlm1RXnonb5hdDb7adBxMZHXQ98u8UOrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:16:41.221891Z"},"content_sha256":"8a34463e455d5cac5b92f9128cbfe6238091c3c89af51569c1a1ba6fd18b27e4","schema_version":"1.0","event_id":"sha256:8a34463e455d5cac5b92f9128cbfe6238091c3c89af51569c1a1ba6fd18b27e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KAYZUY2A42F4UKYFIOL7CBZTJQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Localized Language-Image Pre-Training","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Haotian Zhang, Hong-You Chen, Keen You, Marcin Eichner, Meng Cao, Xinze Wang, Yinfei Yang, Zhe Gan, Zhengfeng Lai","submitted_at":"2024-10-03T17:56:09Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone of multimodal large language models (MLLMs) to connect image inputs for language interactions. The success of CLIP as a vision-language foundation model relies on aligning web-crawled noisy text annotations at image levels. Nevertheless, such criteria may become insufficient for downstream tasks in need of fine-grained vision representations, especially whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02746","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/2410.02746/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":"2026-07-05T10:16:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f7USNYidc5TM0YAovOgJKI7r+s62ghuPvH1SEex6ed5Qt9e3UmeBP+9ukcGSjukdNyHC9Iag7BQm11YYlyOHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:16:41.222419Z"},"content_sha256":"5d99394a073509027de1586565b3c90bac54d5bd1969ca1524a7eefd6ad6f5eb","schema_version":"1.0","event_id":"sha256:5d99394a073509027de1586565b3c90bac54d5bd1969ca1524a7eefd6ad6f5eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KAYZUY2A42F4UKYFIOL7CBZTJQ/bundle.json","state_url":"https://pith.science/pith/KAYZUY2A42F4UKYFIOL7CBZTJQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KAYZUY2A42F4UKYFIOL7CBZTJQ/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":"2026-08-10T17:16:41Z","links":{"resolver":"https://pith.science/pith/KAYZUY2A42F4UKYFIOL7CBZTJQ","bundle":"https://pith.science/pith/KAYZUY2A42F4UKYFIOL7CBZTJQ/bundle.json","state":"https://pith.science/pith/KAYZUY2A42F4UKYFIOL7CBZTJQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KAYZUY2A42F4UKYFIOL7CBZTJQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KAYZUY2A42F4UKYFIOL7CBZTJQ","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":"92086bf0cf86f2b1937a071e9fd123012473340ce50ebe7ba811b35fa3efece5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:56:09Z","title_canon_sha256":"84f6f4166f63610a545fdb4b5a736619c2846fa4e75d8b7c6c281181d5425d1f"},"schema_version":"1.0","source":{"id":"2410.02746","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02746","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02746v2","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02746","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"pith_short_12","alias_value":"KAYZUY2A42F4","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"pith_short_16","alias_value":"KAYZUY2A42F4UKYF","created_at":"2026-07-05T10:16:38Z"},{"alias_kind":"pith_short_8","alias_value":"KAYZUY2A","created_at":"2026-07-05T10:16:38Z"}],"graph_snapshots":[{"event_id":"sha256:5d99394a073509027de1586565b3c90bac54d5bd1969ca1524a7eefd6ad6f5eb","target":"graph","created_at":"2026-07-05T10:16:38Z","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/2410.02746/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone of multimodal large language models (MLLMs) to connect image inputs for language interactions. The success of CLIP as a vision-language foundation model relies on aligning web-crawled noisy text annotations at image levels. Nevertheless, such criteria may become insufficient for downstream tasks in need of fine-grained vision representations, especially whe","authors_text":"Bowen Zhang, Haotian Zhang, Hong-You Chen, Keen You, Marcin Eichner, Meng Cao, Xinze Wang, Yinfei Yang, Zhe Gan, Zhengfeng Lai","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:56:09Z","title":"Contrastive Localized Language-Image Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02746","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":"sha256:8a34463e455d5cac5b92f9128cbfe6238091c3c89af51569c1a1ba6fd18b27e4","target":"record","created_at":"2026-07-05T10:16:38Z","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":"92086bf0cf86f2b1937a071e9fd123012473340ce50ebe7ba811b35fa3efece5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:56:09Z","title_canon_sha256":"84f6f4166f63610a545fdb4b5a736619c2846fa4e75d8b7c6c281181d5425d1f"},"schema_version":"1.0","source":{"id":"2410.02746","kind":"arxiv","version":2}},"canonical_sha256":"50319a6340e68bca2b054397f107334c067a5d9669b0c209b5b9ed62a67f229d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50319a6340e68bca2b054397f107334c067a5d9669b0c209b5b9ed62a67f229d","first_computed_at":"2026-07-05T10:16:38.322823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:38.322823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sJaGEn7aFPD3Wq4xVGUdyfX8565OdAaF6qED6gerSKqTJ1N1+/xC8UkJmm1WY5mHP99qjfKVB6QAf/6O1+flAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:38.323420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02746","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a34463e455d5cac5b92f9128cbfe6238091c3c89af51569c1a1ba6fd18b27e4","sha256:5d99394a073509027de1586565b3c90bac54d5bd1969ca1524a7eefd6ad6f5eb"],"state_sha256":"61d8ee33ffdc3523864271fbd6c8d5a7005b2148f007a8d0990d88d38e86a9a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oOF5qh3IfjIQ1HuCoNd4LhWitXQIGB6ENWT9LzgCsZOC43lmeuhUVMeWZAjvYXv/zhv9P2QzKxyAZmWBOQERAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T17:16:41.228159Z","bundle_sha256":"0fdc604e04e97c5aedf24f03b704ba12c8e8795b418f77d957ce81ac5caa13c2"}}