{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2R5L3ATX6EUU3KOOVRKL7ZC6XX","short_pith_number":"pith:2R5L3ATX","canonical_record":{"source":{"id":"2305.05095","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-08T23:47:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c0e2087a71ea9afe9b9cb4cf9e84cc1023cc7937a9891a9743564b0dd0300331","abstract_canon_sha256":"66de1c08d39db6511be56cd727ebf84ace8ebe322ba2cb78c8a446801f8854fc"},"schema_version":"1.0"},"canonical_sha256":"d47abd8277f1294da9ceac54bfe45ebdd1093710681dc5d9d4181332e1d51a4b","source":{"kind":"arxiv","id":"2305.05095","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05095","created_at":"2026-07-05T06:08:30Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05095v1","created_at":"2026-07-05T06:08:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05095","created_at":"2026-07-05T06:08:30Z"},{"alias_kind":"pith_short_12","alias_value":"2R5L3ATX6EUU","created_at":"2026-07-05T06:08:30Z"},{"alias_kind":"pith_short_16","alias_value":"2R5L3ATX6EUU3KOO","created_at":"2026-07-05T06:08:30Z"},{"alias_kind":"pith_short_8","alias_value":"2R5L3ATX","created_at":"2026-07-05T06:08:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2R5L3ATX6EUU3KOOVRKL7ZC6XX","target":"record","payload":{"canonical_record":{"source":{"id":"2305.05095","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-08T23:47:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c0e2087a71ea9afe9b9cb4cf9e84cc1023cc7937a9891a9743564b0dd0300331","abstract_canon_sha256":"66de1c08d39db6511be56cd727ebf84ace8ebe322ba2cb78c8a446801f8854fc"},"schema_version":"1.0"},"canonical_sha256":"d47abd8277f1294da9ceac54bfe45ebdd1093710681dc5d9d4181332e1d51a4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:30.902974Z","signature_b64":"uJviwNjHcfBkKNILs4JgK+X0w5ClCe8nu0d1t/724q5DtnAnYE/WWvMOfkPWv4fwHSAxqSN58+Rjaryu5CgEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d47abd8277f1294da9ceac54bfe45ebdd1093710681dc5d9d4181332e1d51a4b","last_reissued_at":"2026-07-05T06:08:30.902575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:30.902575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.05095","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:08:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jov5pLwa683t5+PsyMu4NaOoFOQBxNNYYjzqVD07IIEplyZEDEocOPpuDqYA+m/UUd311HvriSTtb84ZoTMADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:57:06.724477Z"},"content_sha256":"826ba1bf810c556e1da7dbc057c41620a08257d560221c79e1c38e4f18393a68","schema_version":"1.0","event_id":"sha256:826ba1bf810c556e1da7dbc057c41620a08257d560221c79e1c38e4f18393a68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2R5L3ATX6EUU3KOOVRKL7ZC6XX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Chen Chen, Liangliang Cao, Wencong Zhang, Xianzhi Du, Yantao Zheng, Yinfei Yang, Zhiyun Lu","submitted_at":"2023-05-08T23:47:07Z","abstract_excerpt":"The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive. Furthermore, the conventional CLIP model doesn't differentiate between the visual semantics and meaning of text regions embedded in images. This can lead to non-robustness when the text in the embedded region doesn't match the image's visual appearance. In this paper, we discuss two effective approaches to improve the efficiency and robustness of CLIP traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05095","kind":"arxiv","version":1},"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/2305.05095/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":"2026-07-05T06:08:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J9XeaYYSWCkLesmXlJN8z4gSZ5fg6wZEwC2Os0U2+HnkTrKJ7XHzNhAIZG/3CO4AbaBymGTGqThx7K8A5e5gDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:57:06.724996Z"},"content_sha256":"c18429aa22bf49035d2d89d83e37b7f024cd6323b42f06d2a83e6dbdc70b88ce","schema_version":"1.0","event_id":"sha256:c18429aa22bf49035d2d89d83e37b7f024cd6323b42f06d2a83e6dbdc70b88ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2R5L3ATX6EUU3KOOVRKL7ZC6XX/bundle.json","state_url":"https://pith.science/pith/2R5L3ATX6EUU3KOOVRKL7ZC6XX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2R5L3ATX6EUU3KOOVRKL7ZC6XX/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":"2026-08-08T12:57:06Z","links":{"resolver":"https://pith.science/pith/2R5L3ATX6EUU3KOOVRKL7ZC6XX","bundle":"https://pith.science/pith/2R5L3ATX6EUU3KOOVRKL7ZC6XX/bundle.json","state":"https://pith.science/pith/2R5L3ATX6EUU3KOOVRKL7ZC6XX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2R5L3ATX6EUU3KOOVRKL7ZC6XX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2R5L3ATX6EUU3KOOVRKL7ZC6XX","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":"66de1c08d39db6511be56cd727ebf84ace8ebe322ba2cb78c8a446801f8854fc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-08T23:47:07Z","title_canon_sha256":"c0e2087a71ea9afe9b9cb4cf9e84cc1023cc7937a9891a9743564b0dd0300331"},"schema_version":"1.0","source":{"id":"2305.05095","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05095","created_at":"2026-07-05T06:08:30Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05095v1","created_at":"2026-07-05T06:08:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05095","created_at":"2026-07-05T06:08:30Z"},{"alias_kind":"pith_short_12","alias_value":"2R5L3ATX6EUU","created_at":"2026-07-05T06:08:30Z"},{"alias_kind":"pith_short_16","alias_value":"2R5L3ATX6EUU3KOO","created_at":"2026-07-05T06:08:30Z"},{"alias_kind":"pith_short_8","alias_value":"2R5L3ATX","created_at":"2026-07-05T06:08:30Z"}],"graph_snapshots":[{"event_id":"sha256:c18429aa22bf49035d2d89d83e37b7f024cd6323b42f06d2a83e6dbdc70b88ce","target":"graph","created_at":"2026-07-05T06:08:30Z","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/2305.05095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive. Furthermore, the conventional CLIP model doesn't differentiate between the visual semantics and meaning of text regions embedded in images. This can lead to non-robustness when the text in the embedded region doesn't match the image's visual appearance. In this paper, we discuss two effective approaches to improve the efficiency and robustness of CLIP traini","authors_text":"Bowen Zhang, Chen Chen, Liangliang Cao, Wencong Zhang, Xianzhi Du, Yantao Zheng, Yinfei Yang, Zhiyun Lu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-08T23:47:07Z","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05095","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":"sha256:826ba1bf810c556e1da7dbc057c41620a08257d560221c79e1c38e4f18393a68","target":"record","created_at":"2026-07-05T06:08:30Z","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":"66de1c08d39db6511be56cd727ebf84ace8ebe322ba2cb78c8a446801f8854fc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-08T23:47:07Z","title_canon_sha256":"c0e2087a71ea9afe9b9cb4cf9e84cc1023cc7937a9891a9743564b0dd0300331"},"schema_version":"1.0","source":{"id":"2305.05095","kind":"arxiv","version":1}},"canonical_sha256":"d47abd8277f1294da9ceac54bfe45ebdd1093710681dc5d9d4181332e1d51a4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d47abd8277f1294da9ceac54bfe45ebdd1093710681dc5d9d4181332e1d51a4b","first_computed_at":"2026-07-05T06:08:30.902575Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:30.902575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uJviwNjHcfBkKNILs4JgK+X0w5ClCe8nu0d1t/724q5DtnAnYE/WWvMOfkPWv4fwHSAxqSN58+Rjaryu5CgEAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:30.902974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.05095","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:826ba1bf810c556e1da7dbc057c41620a08257d560221c79e1c38e4f18393a68","sha256:c18429aa22bf49035d2d89d83e37b7f024cd6323b42f06d2a83e6dbdc70b88ce"],"state_sha256":"83c49cf4d0eb1c5b7ee38d2134edd43eac508fb30fcbd3c75c128d765f328d8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJAJmXhO7419LdpsWrTsWOv/0JLbWwTD4Y55N0dwi7EfV+pAM9120YmIicfhLgjbikIL2zXLDPXfI5EadPAtDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:57:06.729000Z","bundle_sha256":"df52cac68256fc3d5d06c037ae5271bae010ff79091540a55feabaa086a2b60d"}}