{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ETJXWZ4M7U4TESZD6RKY35Y7WG","short_pith_number":"pith:ETJXWZ4M","canonical_record":{"source":{"id":"2403.12267","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T21:32:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"95b2209a54887838116d086337c4aaf13e1032c5d927763f7005c01afe266fb0","abstract_canon_sha256":"1738022c8672bc0fa28f4f0d210c14879df887158b3f40dc702465168b9cbc08"},"schema_version":"1.0"},"canonical_sha256":"24d37b678cfd39324b23f4558df71fb1ac16fd2e50dc5852934dac702fb5aaed","source":{"kind":"arxiv","id":"2403.12267","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12267","created_at":"2026-07-05T07:58:29Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12267v2","created_at":"2026-07-05T07:58:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12267","created_at":"2026-07-05T07:58:29Z"},{"alias_kind":"pith_short_12","alias_value":"ETJXWZ4M7U4T","created_at":"2026-07-05T07:58:29Z"},{"alias_kind":"pith_short_16","alias_value":"ETJXWZ4M7U4TESZD","created_at":"2026-07-05T07:58:29Z"},{"alias_kind":"pith_short_8","alias_value":"ETJXWZ4M","created_at":"2026-07-05T07:58:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ETJXWZ4M7U4TESZD6RKY35Y7WG","target":"record","payload":{"canonical_record":{"source":{"id":"2403.12267","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T21:32:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"95b2209a54887838116d086337c4aaf13e1032c5d927763f7005c01afe266fb0","abstract_canon_sha256":"1738022c8672bc0fa28f4f0d210c14879df887158b3f40dc702465168b9cbc08"},"schema_version":"1.0"},"canonical_sha256":"24d37b678cfd39324b23f4558df71fb1ac16fd2e50dc5852934dac702fb5aaed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:29.208841Z","signature_b64":"2+zhqpf+dNGeg7whYf7E/0JgAMbOEKF9+CEk4j/KAcp+NTmoncy+p4GJPQdhVO5OevErOrFmorcspIE3hyfQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24d37b678cfd39324b23f4558df71fb1ac16fd2e50dc5852934dac702fb5aaed","last_reissued_at":"2026-07-05T07:58:29.208383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:29.208383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.12267","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":"2026-07-05T07:58:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WDwWLAn6i8bhxLbee3PT0iyWx6FmMLxJpi3HF/k0K5B9k1GtSUYKqP55zmBqOKGco7aWvV8VruaiimPv8UedAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:42:28.843700Z"},"content_sha256":"2574ca5e8dd886fe1408ccc9acacadf406378233802c46b6400fe33935778768","schema_version":"1.0","event_id":"sha256:2574ca5e8dd886fe1408ccc9acacadf406378233802c46b6400fe33935778768"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ETJXWZ4M7U4TESZD6RKY35Y7WG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Payani, Arnav Jain, Baharan Mirzasoleiman, Siddharth Joshi","submitted_at":"2024-03-18T21:32:58Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) on large-scale image-caption datasets learns representations that can achieve remarkable zero-shot generalization. However, such models require a massive amount of pre-training data. Improving the quality of the pre-training data has been shown to be much more effective in improving CLIP's performance than increasing its volume. Nevertheless, finding small subsets of training data that provably generalize the best has remained an open question. In this work, we propose the first theoretically rigorous data selection method for CLIP. We show that s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12267","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/2403.12267/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":"2026-07-05T07:58:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nuK9+LtBJKfU5kIV9Z7uUBvOUwQYKgw9n21ShJYYx+zlElH7+6WY4ErlL3CpEhv0xHCl4yBAK97YqMs9LtFDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:42:28.844611Z"},"content_sha256":"9b8503146e261d1ac24e3a041aaf77ec780aa6291fe177c46b8d9be7aea1edb3","schema_version":"1.0","event_id":"sha256:9b8503146e261d1ac24e3a041aaf77ec780aa6291fe177c46b8d9be7aea1edb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ETJXWZ4M7U4TESZD6RKY35Y7WG/bundle.json","state_url":"https://pith.science/pith/ETJXWZ4M7U4TESZD6RKY35Y7WG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ETJXWZ4M7U4TESZD6RKY35Y7WG/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":"2026-08-15T17:42:28Z","links":{"resolver":"https://pith.science/pith/ETJXWZ4M7U4TESZD6RKY35Y7WG","bundle":"https://pith.science/pith/ETJXWZ4M7U4TESZD6RKY35Y7WG/bundle.json","state":"https://pith.science/pith/ETJXWZ4M7U4TESZD6RKY35Y7WG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ETJXWZ4M7U4TESZD6RKY35Y7WG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ETJXWZ4M7U4TESZD6RKY35Y7WG","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":"1738022c8672bc0fa28f4f0d210c14879df887158b3f40dc702465168b9cbc08","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T21:32:58Z","title_canon_sha256":"95b2209a54887838116d086337c4aaf13e1032c5d927763f7005c01afe266fb0"},"schema_version":"1.0","source":{"id":"2403.12267","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12267","created_at":"2026-07-05T07:58:29Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12267v2","created_at":"2026-07-05T07:58:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12267","created_at":"2026-07-05T07:58:29Z"},{"alias_kind":"pith_short_12","alias_value":"ETJXWZ4M7U4T","created_at":"2026-07-05T07:58:29Z"},{"alias_kind":"pith_short_16","alias_value":"ETJXWZ4M7U4TESZD","created_at":"2026-07-05T07:58:29Z"},{"alias_kind":"pith_short_8","alias_value":"ETJXWZ4M","created_at":"2026-07-05T07:58:29Z"}],"graph_snapshots":[{"event_id":"sha256:9b8503146e261d1ac24e3a041aaf77ec780aa6291fe177c46b8d9be7aea1edb3","target":"graph","created_at":"2026-07-05T07:58:29Z","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/2403.12267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) on large-scale image-caption datasets learns representations that can achieve remarkable zero-shot generalization. However, such models require a massive amount of pre-training data. Improving the quality of the pre-training data has been shown to be much more effective in improving CLIP's performance than increasing its volume. Nevertheless, finding small subsets of training data that provably generalize the best has remained an open question. In this work, we propose the first theoretically rigorous data selection method for CLIP. We show that s","authors_text":"Ali Payani, Arnav Jain, Baharan Mirzasoleiman, Siddharth Joshi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T21:32:58Z","title":"Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12267","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":"sha256:2574ca5e8dd886fe1408ccc9acacadf406378233802c46b6400fe33935778768","target":"record","created_at":"2026-07-05T07:58:29Z","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":"1738022c8672bc0fa28f4f0d210c14879df887158b3f40dc702465168b9cbc08","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T21:32:58Z","title_canon_sha256":"95b2209a54887838116d086337c4aaf13e1032c5d927763f7005c01afe266fb0"},"schema_version":"1.0","source":{"id":"2403.12267","kind":"arxiv","version":2}},"canonical_sha256":"24d37b678cfd39324b23f4558df71fb1ac16fd2e50dc5852934dac702fb5aaed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24d37b678cfd39324b23f4558df71fb1ac16fd2e50dc5852934dac702fb5aaed","first_computed_at":"2026-07-05T07:58:29.208383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:29.208383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2+zhqpf+dNGeg7whYf7E/0JgAMbOEKF9+CEk4j/KAcp+NTmoncy+p4GJPQdhVO5OevErOrFmorcspIE3hyfQDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:29.208841Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12267","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2574ca5e8dd886fe1408ccc9acacadf406378233802c46b6400fe33935778768","sha256:9b8503146e261d1ac24e3a041aaf77ec780aa6291fe177c46b8d9be7aea1edb3"],"state_sha256":"da06038fead16c08c8abb6f473914452d93bc9b3fc389c05502f2c7d9a4b4032"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O7ZHTKIbe3OSiGL2W/z2i37nwQ5g76HpsMPVd6rwm5Gz4LnGvc5tFIeyrWRx5Hmp+gzR66X4uRggWQXex8rjBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:42:28.849491Z","bundle_sha256":"e78b9f021ad20c2988812ae793a51a6e631ae73d1b317db079445461ee75fac1"}}