{"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"}