{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UDS5LKDS2QOJUFPDKDRSQWLZ2O","short_pith_number":"pith:UDS5LKDS","canonical_record":{"source":{"id":"1912.11370","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-24T14:04:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3ef8f797bc4649173f9dac30c0eee2fdef3189f64b350e8bfa9208cb79eb5e24","abstract_canon_sha256":"340bd0f4602ee852b97379524b913ae24aca631d2359603a451b83798914af82"},"schema_version":"1.0"},"canonical_sha256":"a0e5d5a872d41c9a15e350e3285979d3913b21c8db3321606eb5ae291ae76bef","source":{"kind":"arxiv","id":"1912.11370","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.11370","created_at":"2026-07-05T01:00:49Z"},{"alias_kind":"arxiv_version","alias_value":"1912.11370v3","created_at":"2026-07-05T01:00:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.11370","created_at":"2026-07-05T01:00:49Z"},{"alias_kind":"pith_short_12","alias_value":"UDS5LKDS2QOJ","created_at":"2026-07-05T01:00:49Z"},{"alias_kind":"pith_short_16","alias_value":"UDS5LKDS2QOJUFPD","created_at":"2026-07-05T01:00:49Z"},{"alias_kind":"pith_short_8","alias_value":"UDS5LKDS","created_at":"2026-07-05T01:00:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UDS5LKDS2QOJUFPDKDRSQWLZ2O","target":"record","payload":{"canonical_record":{"source":{"id":"1912.11370","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-24T14:04:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3ef8f797bc4649173f9dac30c0eee2fdef3189f64b350e8bfa9208cb79eb5e24","abstract_canon_sha256":"340bd0f4602ee852b97379524b913ae24aca631d2359603a451b83798914af82"},"schema_version":"1.0"},"canonical_sha256":"a0e5d5a872d41c9a15e350e3285979d3913b21c8db3321606eb5ae291ae76bef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:49.557281Z","signature_b64":"8WvCoN/Aj4vcdJ5Img6I6Cnjm8kELfMZDeZprmvgZee7qoMof5k5wCcjTkx056iM6ROBN+siVTy5op9MwOU9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0e5d5a872d41c9a15e350e3285979d3913b21c8db3321606eb5ae291ae76bef","last_reissued_at":"2026-07-05T01:00:49.556778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:49.556778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.11370","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:00:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QAOwao8g7AFavvZLbfxrMxbmOkzhqcaBAowgUgPcNuD5av51TAW+j5Qc1SOi0dGWwupZkR4uK6WIoi9EAJ4PBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:18:04.336886Z"},"content_sha256":"117d6ed8fabce9dad8d3bcb34ce08462417667757fe48ef34af8577af4176b38","schema_version":"1.0","event_id":"sha256:117d6ed8fabce9dad8d3bcb34ce08462417667757fe48ef34af8577af4176b38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UDS5LKDS2QOJUFPDKDRSQWLZ2O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Big Transfer (BiT): General Visual Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Kolesnikov, Jessica Yung, Joan Puigcerver, Lucas Beyer, Neil Houlsby, Sylvain Gelly, Xiaohua Zhai","submitted_at":"2019-12-24T14:04:11Z","abstract_excerpt":"Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the paradigm of pre-training on large supervised datasets and fine-tuning the model on a target task. We scale up pre-training, and propose a simple recipe that we call Big Transfer (BiT). By combining a few carefully selected components, and transferring using a simple heuristic, we achieve strong performance on over 20 datasets. BiT performs well across a surprisingly wide range of data regimes -- from 1 example per class to 1M tota"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.11370","kind":"arxiv","version":3},"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/1912.11370/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":"2026-07-05T01:00:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XNpf6PvyNmBDlgjpwTorji1Vcax57sJKEP/Wp99Z0c4ec+VAjcDop+oade/Tu8ZHYvwlERoVH67pgQD2VHquCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:18:04.337856Z"},"content_sha256":"e5a1335d7ed99919bc7333c83d9fa569a3f5e4ce5da88906bc20a972624dac02","schema_version":"1.0","event_id":"sha256:e5a1335d7ed99919bc7333c83d9fa569a3f5e4ce5da88906bc20a972624dac02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UDS5LKDS2QOJUFPDKDRSQWLZ2O/bundle.json","state_url":"https://pith.science/pith/UDS5LKDS2QOJUFPDKDRSQWLZ2O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UDS5LKDS2QOJUFPDKDRSQWLZ2O/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":"2026-08-19T11:18:04Z","links":{"resolver":"https://pith.science/pith/UDS5LKDS2QOJUFPDKDRSQWLZ2O","bundle":"https://pith.science/pith/UDS5LKDS2QOJUFPDKDRSQWLZ2O/bundle.json","state":"https://pith.science/pith/UDS5LKDS2QOJUFPDKDRSQWLZ2O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UDS5LKDS2QOJUFPDKDRSQWLZ2O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UDS5LKDS2QOJUFPDKDRSQWLZ2O","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":"340bd0f4602ee852b97379524b913ae24aca631d2359603a451b83798914af82","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-24T14:04:11Z","title_canon_sha256":"3ef8f797bc4649173f9dac30c0eee2fdef3189f64b350e8bfa9208cb79eb5e24"},"schema_version":"1.0","source":{"id":"1912.11370","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.11370","created_at":"2026-07-05T01:00:49Z"},{"alias_kind":"arxiv_version","alias_value":"1912.11370v3","created_at":"2026-07-05T01:00:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.11370","created_at":"2026-07-05T01:00:49Z"},{"alias_kind":"pith_short_12","alias_value":"UDS5LKDS2QOJ","created_at":"2026-07-05T01:00:49Z"},{"alias_kind":"pith_short_16","alias_value":"UDS5LKDS2QOJUFPD","created_at":"2026-07-05T01:00:49Z"},{"alias_kind":"pith_short_8","alias_value":"UDS5LKDS","created_at":"2026-07-05T01:00:49Z"}],"graph_snapshots":[{"event_id":"sha256:e5a1335d7ed99919bc7333c83d9fa569a3f5e4ce5da88906bc20a972624dac02","target":"graph","created_at":"2026-07-05T01:00:49Z","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/1912.11370/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the paradigm of pre-training on large supervised datasets and fine-tuning the model on a target task. We scale up pre-training, and propose a simple recipe that we call Big Transfer (BiT). By combining a few carefully selected components, and transferring using a simple heuristic, we achieve strong performance on over 20 datasets. BiT performs well across a surprisingly wide range of data regimes -- from 1 example per class to 1M tota","authors_text":"Alexander Kolesnikov, Jessica Yung, Joan Puigcerver, Lucas Beyer, Neil Houlsby, Sylvain Gelly, Xiaohua Zhai","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-24T14:04:11Z","title":"Big Transfer (BiT): General Visual Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.11370","kind":"arxiv","version":3},"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":"sha256:117d6ed8fabce9dad8d3bcb34ce08462417667757fe48ef34af8577af4176b38","target":"record","created_at":"2026-07-05T01:00:49Z","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":"340bd0f4602ee852b97379524b913ae24aca631d2359603a451b83798914af82","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-24T14:04:11Z","title_canon_sha256":"3ef8f797bc4649173f9dac30c0eee2fdef3189f64b350e8bfa9208cb79eb5e24"},"schema_version":"1.0","source":{"id":"1912.11370","kind":"arxiv","version":3}},"canonical_sha256":"a0e5d5a872d41c9a15e350e3285979d3913b21c8db3321606eb5ae291ae76bef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0e5d5a872d41c9a15e350e3285979d3913b21c8db3321606eb5ae291ae76bef","first_computed_at":"2026-07-05T01:00:49.556778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:49.556778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8WvCoN/Aj4vcdJ5Img6I6Cnjm8kELfMZDeZprmvgZee7qoMof5k5wCcjTkx056iM6ROBN+siVTy5op9MwOU9DA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:49.557281Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.11370","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:117d6ed8fabce9dad8d3bcb34ce08462417667757fe48ef34af8577af4176b38","sha256:e5a1335d7ed99919bc7333c83d9fa569a3f5e4ce5da88906bc20a972624dac02"],"state_sha256":"e5a5ca15088cdcd4d838cf20ade1166277faf908572618b0b3ecf9025ff5d323"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+XAUvTvEZ4kSna2Pk96iXNdovX/NfKyw87eEa5/9S19XyjELay4e2vXDYZygRHlXTQOGxVImTv78VWgIpG4mCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T11:18:04.346411Z","bundle_sha256":"08799e88548b1e1c5826175451c8a35c11b006ef414f6798ece874c7c5206e49"}}