{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KNYSOTX7H67XG7U7ROCEQSCQEE","short_pith_number":"pith:KNYSOTX7","schema_version":"1.0","canonical_sha256":"5371274eff3fbf737e9f8b84484850210423a4d2309f9b29708b149d5446e8d4","source":{"kind":"arxiv","id":"2212.07143","version":2},"attestation_state":"computed","paper":{"title":"Reproducible scaling laws for contrastive language-image learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Cade Gordon, Christoph Schuhmann, Gabriel Ilharco, Jenia Jitsev, Ludwig Schmidt, Mehdi Cherti, Mitchell Wortsman, Romain Beaumont, Ross Wightman","submitted_at":"2022-12-14T10:24:50Z","abstract_excerpt":"Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set size, model size, and compute, which offers valuable guidance as large-scale experiments are becoming increasingly expensive. However, previous work on scaling laws has primarily used private data \\& models or focused on uni-modal language or vision learning. To address these limitations, we investigate scaling laws for contrastive language-image pre-training (CLIP) with the public LAION dataset and the open-source Op"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2212.07143","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T10:24:50Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"f04f6ce00e607a59f062571e6f27968a05e9ef3a9a3f600034adfdc0bbd57e98","abstract_canon_sha256":"a355d247a5da5f2fb04edf4832e9a5e193aa41f33222c0a1bbd6e265e279262c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:20.968689Z","signature_b64":"nghlXzre8AP1nsk0PkB091braWa3oGWuVyTlzQNJ11DdclHSHaid0vHw0yZHQIUqvlyalHTmcbphXII+gnCtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5371274eff3fbf737e9f8b84484850210423a4d2309f9b29708b149d5446e8d4","last_reissued_at":"2026-07-05T08:43:20.968291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:20.968291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reproducible scaling laws for contrastive language-image learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Cade Gordon, Christoph Schuhmann, Gabriel Ilharco, Jenia Jitsev, Ludwig Schmidt, Mehdi Cherti, Mitchell Wortsman, Romain Beaumont, Ross Wightman","submitted_at":"2022-12-14T10:24:50Z","abstract_excerpt":"Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set size, model size, and compute, which offers valuable guidance as large-scale experiments are becoming increasingly expensive. However, previous work on scaling laws has primarily used private data \\& models or focused on uni-modal language or vision learning. To address these limitations, we investigate scaling laws for contrastive language-image pre-training (CLIP) with the public LAION dataset and the open-source Op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07143","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/2212.07143/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2212.07143","created_at":"2026-07-05T08:43:20.968356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.07143v2","created_at":"2026-07-05T08:43:20.968356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07143","created_at":"2026-07-05T08:43:20.968356+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNYSOTX7H67X","created_at":"2026-07-05T08:43:20.968356+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNYSOTX7H67XG7U7","created_at":"2026-07-05T08:43:20.968356+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNYSOTX7","created_at":"2026-07-05T08:43:20.968356+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02158","citing_title":"Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29506","citing_title":"Benchmark AUC Is Not Deployable Reliability: A Cross-Dataset Audit of Off-the-Shelf Features for Surveillance Video Anomaly Detection","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03148","citing_title":"$A^2$: Smaller Self-Supervised ViTs Localize Better than Larger Ones","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16671","citing_title":"Demystifying CLIP Data","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2303.00915","citing_title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01325","citing_title":"Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNYSOTX7H67XG7U7ROCEQSCQEE","json":"https://pith.science/pith/KNYSOTX7H67XG7U7ROCEQSCQEE.json","graph_json":"https://pith.science/api/pith-number/KNYSOTX7H67XG7U7ROCEQSCQEE/graph.json","events_json":"https://pith.science/api/pith-number/KNYSOTX7H67XG7U7ROCEQSCQEE/events.json","paper":"https://pith.science/paper/KNYSOTX7"},"agent_actions":{"view_html":"https://pith.science/pith/KNYSOTX7H67XG7U7ROCEQSCQEE","download_json":"https://pith.science/pith/KNYSOTX7H67XG7U7ROCEQSCQEE.json","view_paper":"https://pith.science/paper/KNYSOTX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.07143&json=true","fetch_graph":"https://pith.science/api/pith-number/KNYSOTX7H67XG7U7ROCEQSCQEE/graph.json","fetch_events":"https://pith.science/api/pith-number/KNYSOTX7H67XG7U7ROCEQSCQEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNYSOTX7H67XG7U7ROCEQSCQEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNYSOTX7H67XG7U7ROCEQSCQEE/action/storage_attestation","attest_author":"https://pith.science/pith/KNYSOTX7H67XG7U7ROCEQSCQEE/action/author_attestation","sign_citation":"https://pith.science/pith/KNYSOTX7H67XG7U7ROCEQSCQEE/action/citation_signature","submit_replication":"https://pith.science/pith/KNYSOTX7H67XG7U7ROCEQSCQEE/action/replication_record"}},"created_at":"2026-07-05T08:43:20.968356+00:00","updated_at":"2026-07-05T08:43:20.968356+00:00"}