{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:U5KSI7L7FAUCGPCADRUKFFXYQP","short_pith_number":"pith:U5KSI7L7","canonical_record":{"source":{"id":"2301.02280","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-05T19:48:01Z","cross_cats_sorted":[],"title_canon_sha256":"0a9d5058595e8736e7613d85f59315d83f0e2b1dc705eefb65b098ac6045f70e","abstract_canon_sha256":"60fe8a84ced99dfb4a94f06a5dcebd8a007ce1ad70d68b4fbec4dd5253473224"},"schema_version":"1.0"},"canonical_sha256":"a755247d7f2828233c401c68a296f883eb9fd31445bbc650a2b6f8af9baf7139","source":{"kind":"arxiv","id":"2301.02280","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.02280","created_at":"2026-07-05T05:56:15Z"},{"alias_kind":"arxiv_version","alias_value":"2301.02280v2","created_at":"2026-07-05T05:56:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02280","created_at":"2026-07-05T05:56:15Z"},{"alias_kind":"pith_short_12","alias_value":"U5KSI7L7FAUC","created_at":"2026-07-05T05:56:15Z"},{"alias_kind":"pith_short_16","alias_value":"U5KSI7L7FAUCGPCA","created_at":"2026-07-05T05:56:15Z"},{"alias_kind":"pith_short_8","alias_value":"U5KSI7L7","created_at":"2026-07-05T05:56:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:U5KSI7L7FAUCGPCADRUKFFXYQP","target":"record","payload":{"canonical_record":{"source":{"id":"2301.02280","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-05T19:48:01Z","cross_cats_sorted":[],"title_canon_sha256":"0a9d5058595e8736e7613d85f59315d83f0e2b1dc705eefb65b098ac6045f70e","abstract_canon_sha256":"60fe8a84ced99dfb4a94f06a5dcebd8a007ce1ad70d68b4fbec4dd5253473224"},"schema_version":"1.0"},"canonical_sha256":"a755247d7f2828233c401c68a296f883eb9fd31445bbc650a2b6f8af9baf7139","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:15.594462Z","signature_b64":"4Q4ADgWemK+05Hhq90I6KBEbgZkz/i9GgV8vS+JMAn4VZLRwF85QV5s8/0x6XXi9HlG56aamyesRk236BAJyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a755247d7f2828233c401c68a296f883eb9fd31445bbc650a2b6f8af9baf7139","last_reissued_at":"2026-07-05T05:56:15.593948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:15.593948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.02280","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":"2026-07-05T05:56:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K2YHHAIXK/7lXmIlKjcjnb1Xwc5JPJPyr3TQ/0ITmDWDQSZY8qRVJMAhDlLIkCFDlbZYVzsYWCMqIi5tNrkYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:49:54.672217Z"},"content_sha256":"db4dbf181144abd02b865ecbb7e0cce25f55186e9ffa48024ce8bace8f2d2474","schema_version":"1.0","event_id":"sha256:db4dbf181144abd02b865ecbb7e0cce25f55186e9ffa48024ce8bace8f2d2474"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:U5KSI7L7FAUCGPCADRUKFFXYQP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhimanyu Dubey, Abhishek Kadian, Dhruv Mahajan, Filip Radenovic, Simon Vandenhende, Todor Mihaylov, Vignesh Ramanathan, Yash Patel, Yi Wen","submitted_at":"2023-01-05T19:48:01Z","abstract_excerpt":"Vision-language models trained with contrastive learning on large-scale noisy data are becoming increasingly popular for zero-shot recognition problems. In this paper we improve the following three aspects of the contrastive pre-training pipeline: dataset noise, model initialization and the training objective. First, we propose a straightforward filtering strategy titled Complexity, Action, and Text-spotting (CAT) that significantly reduces dataset size, while achieving improved performance across zero-shot vision-language tasks. Next, we propose an approach titled Concept Distillation to leve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02280","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/2301.02280/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":"2026-07-05T05:56:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JLoH03KqTlbZQKPEDKfdEokgdAVgirhDTZsBdeLWPtNtEaO3I34AyaVSnEdo5gpKXCWiI/QFwoqHb5qSDhBTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:49:54.672732Z"},"content_sha256":"59c54d9d264b1cb6b7d1584644a53947a1c5753951bcca71d538a192de4da78b","schema_version":"1.0","event_id":"sha256:59c54d9d264b1cb6b7d1584644a53947a1c5753951bcca71d538a192de4da78b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U5KSI7L7FAUCGPCADRUKFFXYQP/bundle.json","state_url":"https://pith.science/pith/U5KSI7L7FAUCGPCADRUKFFXYQP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U5KSI7L7FAUCGPCADRUKFFXYQP/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":"2026-08-06T07:49:54Z","links":{"resolver":"https://pith.science/pith/U5KSI7L7FAUCGPCADRUKFFXYQP","bundle":"https://pith.science/pith/U5KSI7L7FAUCGPCADRUKFFXYQP/bundle.json","state":"https://pith.science/pith/U5KSI7L7FAUCGPCADRUKFFXYQP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U5KSI7L7FAUCGPCADRUKFFXYQP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U5KSI7L7FAUCGPCADRUKFFXYQP","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":"60fe8a84ced99dfb4a94f06a5dcebd8a007ce1ad70d68b4fbec4dd5253473224","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-05T19:48:01Z","title_canon_sha256":"0a9d5058595e8736e7613d85f59315d83f0e2b1dc705eefb65b098ac6045f70e"},"schema_version":"1.0","source":{"id":"2301.02280","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.02280","created_at":"2026-07-05T05:56:15Z"},{"alias_kind":"arxiv_version","alias_value":"2301.02280v2","created_at":"2026-07-05T05:56:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02280","created_at":"2026-07-05T05:56:15Z"},{"alias_kind":"pith_short_12","alias_value":"U5KSI7L7FAUC","created_at":"2026-07-05T05:56:15Z"},{"alias_kind":"pith_short_16","alias_value":"U5KSI7L7FAUCGPCA","created_at":"2026-07-05T05:56:15Z"},{"alias_kind":"pith_short_8","alias_value":"U5KSI7L7","created_at":"2026-07-05T05:56:15Z"}],"graph_snapshots":[{"event_id":"sha256:59c54d9d264b1cb6b7d1584644a53947a1c5753951bcca71d538a192de4da78b","target":"graph","created_at":"2026-07-05T05:56:15Z","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/2301.02280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models trained with contrastive learning on large-scale noisy data are becoming increasingly popular for zero-shot recognition problems. In this paper we improve the following three aspects of the contrastive pre-training pipeline: dataset noise, model initialization and the training objective. First, we propose a straightforward filtering strategy titled Complexity, Action, and Text-spotting (CAT) that significantly reduces dataset size, while achieving improved performance across zero-shot vision-language tasks. Next, we propose an approach titled Concept Distillation to leve","authors_text":"Abhimanyu Dubey, Abhishek Kadian, Dhruv Mahajan, Filip Radenovic, Simon Vandenhende, Todor Mihaylov, Vignesh Ramanathan, Yash Patel, Yi Wen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-05T19:48:01Z","title":"Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02280","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:db4dbf181144abd02b865ecbb7e0cce25f55186e9ffa48024ce8bace8f2d2474","target":"record","created_at":"2026-07-05T05:56:15Z","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":"60fe8a84ced99dfb4a94f06a5dcebd8a007ce1ad70d68b4fbec4dd5253473224","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-05T19:48:01Z","title_canon_sha256":"0a9d5058595e8736e7613d85f59315d83f0e2b1dc705eefb65b098ac6045f70e"},"schema_version":"1.0","source":{"id":"2301.02280","kind":"arxiv","version":2}},"canonical_sha256":"a755247d7f2828233c401c68a296f883eb9fd31445bbc650a2b6f8af9baf7139","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a755247d7f2828233c401c68a296f883eb9fd31445bbc650a2b6f8af9baf7139","first_computed_at":"2026-07-05T05:56:15.593948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:56:15.593948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Q4ADgWemK+05Hhq90I6KBEbgZkz/i9GgV8vS+JMAn4VZLRwF85QV5s8/0x6XXi9HlG56aamyesRk236BAJyDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:56:15.594462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.02280","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db4dbf181144abd02b865ecbb7e0cce25f55186e9ffa48024ce8bace8f2d2474","sha256:59c54d9d264b1cb6b7d1584644a53947a1c5753951bcca71d538a192de4da78b"],"state_sha256":"1cc698aa9c06b37d19004055cf857dccb599ddf67b9780d059e61a14b69ec1f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5uVndCibWKmNXtwLGi7tFd5ywEi3JrdMeQzLef2iM1NGK/XQnaOUqKe3awz/Uau7DfOKnUZN9Qhha26B7Bj2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:49:54.676756Z","bundle_sha256":"1161d9d989347696dc454571a6f4ae0cac11a03da4094d0dd420f9b30661b637"}}