{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3EU3MUW3Y6TNM3IDTP2I4EKV46","short_pith_number":"pith:3EU3MUW3","canonical_record":{"source":{"id":"1910.04867","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-01T17:06:29Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"01dfec4774dbcf3571afc230ad20ba5f5e08b81e5bbc3a0773410759e70002cf","abstract_canon_sha256":"2ee84f2872483f7fc0373f486fda0ec03e71cdcf6d2e260eb245a11256983169"},"schema_version":"1.0"},"canonical_sha256":"d929b652dbc7a6d66d039bf48e1155e7bd4d0d8336f66fa3c9da0729f98ec8d3","source":{"kind":"arxiv","id":"1910.04867","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.04867","created_at":"2026-05-17T23:38:12Z"},{"alias_kind":"arxiv_version","alias_value":"1910.04867v2","created_at":"2026-05-17T23:38:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04867","created_at":"2026-05-17T23:38:12Z"},{"alias_kind":"pith_short_12","alias_value":"3EU3MUW3Y6TN","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"3EU3MUW3Y6TNM3ID","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"3EU3MUW3","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3EU3MUW3Y6TNM3IDTP2I4EKV46","target":"record","payload":{"canonical_record":{"source":{"id":"1910.04867","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-01T17:06:29Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"01dfec4774dbcf3571afc230ad20ba5f5e08b81e5bbc3a0773410759e70002cf","abstract_canon_sha256":"2ee84f2872483f7fc0373f486fda0ec03e71cdcf6d2e260eb245a11256983169"},"schema_version":"1.0"},"canonical_sha256":"d929b652dbc7a6d66d039bf48e1155e7bd4d0d8336f66fa3c9da0729f98ec8d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:12.891649Z","signature_b64":"CPCVib8cQ2QFlrWG7Q1gK2Kw8R35FAjmTOHbaMlxhHlpGRAvtgtixKANTHdfBrfOyU3f4g7sV3RqKLZLDBhBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d929b652dbc7a6d66d039bf48e1155e7bd4d0d8336f66fa3c9da0729f98ec8d3","last_reissued_at":"2026-05-17T23:38:12.891040Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:12.891040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.04867","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":"2026-05-17T23:38:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m+paxTczRD5tqHrgudmPnlogTZqNxQy/6Z+ZBS2AY2XCTB4JgnDYkNrlUy1guQemgcurTCC7nck29ntXS+TEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T16:39:46.870257Z"},"content_sha256":"1248c9a52e0db191ee43080c1f11142692b2a930b9a3df32801deadc445518f9","schema_version":"1.0","event_id":"sha256:1248c9a52e0db191ee43080c1f11142692b2a930b9a3df32801deadc445518f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3EU3MUW3Y6TNM3IDTP2I4EKV46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The Visual Task Adaptation Benchmark defines good representations as those that adapt to diverse unseen tasks with few examples.","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alexander Kolesnikov, Alexey Dosovitskiy, Andre Susano Pinto, Carlos Riquelme, Joan Puigcerver, Josip Djolonga, Lucas Beyer, Marcin Michalski, Mario Lucic, Maxim Neumann, Michael Tschannen, Neil Houlsby, Olivier Bachem, Olivier Bousquet, Pierre Ruyssen, Sylvain Gelly, Xiaohua Zhai","submitted_at":"2019-10-01T17:06:29Z","abstract_excerpt":"Representation learning promises to unlock deep learning for the long tail of vision tasks without expensive labelled datasets. Yet, the absence of a unified evaluation for general visual representations hinders progress. Popular protocols are often too constrained (linear classification), limited in diversity (ImageNet, CIFAR, Pascal-VOC), or only weakly related to representation quality (ELBO, reconstruction error). We present the Visual Task Adaptation Benchmark (VTAB), which defines good representations as those that adapt to diverse, unseen tasks with few examples. With VTAB, we conduct a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We present the Visual Task Adaptation Benchmark (VTAB), which defines good representations as those that adapt to diverse, unseen tasks with few examples.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That performance on the 19 selected tasks under few-shot linear or fine-tuning adaptation is a reliable proxy for representation quality on arbitrary future vision problems.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VTAB is a 19-task benchmark that measures representation quality by few-shot adaptation performance across diverse vision domains, with a controlled large-scale comparison of popular pretraining methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The Visual Task Adaptation Benchmark defines good representations as those that adapt to diverse unseen tasks with few examples.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"230bc010fe30a13dc4621d61162e32d6c2bdf136237e09836eeb837e0ce31cac"},"source":{"id":"1910.04867","kind":"arxiv","version":2},"verdict":{"id":"81db5567-0e80-4630-944a-029956d166f7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T22:07:35.805305Z","strongest_claim":"We present the Visual Task Adaptation Benchmark (VTAB), which defines good representations as those that adapt to diverse, unseen tasks with few examples.","one_line_summary":"VTAB is a 19-task benchmark that measures representation quality by few-shot adaptation performance across diverse vision domains, with a controlled large-scale comparison of popular pretraining methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That performance on the 19 selected tasks under few-shot linear or fine-tuning adaptation is a reliable proxy for representation quality on arbitrary future vision problems.","pith_extraction_headline":"The Visual Task Adaptation Benchmark defines good representations as those that adapt to diverse unseen tasks with few examples."},"references":{"count":25,"sample":[{"doi":"","year":null,"title":"DeepMind Lab","work_id":"8a8d827f-5377-4733-bfe8-bc66c011d458","ref_index":1,"cited_arxiv_id":"1612.03801","is_internal_anchor":true},{"doi":"","year":1907,"title":"Large scale adversarial representation learning","work_id":"0d7176d3-a311-4e05-9a09-5db679be48fb","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1905,"title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","work_id":"7991ef7e-1245-4a3f-acf4-f7509b670d8b","ref_index":3,"cited_arxiv_id":"1905.01235","is_internal_anchor":true},{"doi":"","year":null,"title":"Rethinking ImageNet pre-training.arXiv preprint arXiv:1811.08883","work_id":"9b366d91-12ae-42d4-9009-cdccc3efe6d2","ref_index":4,"cited_arxiv_id":"1811.08883","is_internal_anchor":true},{"doi":"","year":1905,"title":"J., Razavi, A., Doersch, C., Eslami, S., and Oord, A","work_id":"5c545404-7449-457a-92aa-390c9d328c06","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":25,"snapshot_sha256":"d371c0c782cdec833171ce168889ab4d6ef29c262d83533c94cc8eba57cc5cfa","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a09b8e2054ca76035a8e0dd563bf115307d7cc44447e786a7fadf3e388c599d0"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"81db5567-0e80-4630-944a-029956d166f7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nMQrWApB2BD7HfsoO7+9j2HgvRBwxYRwDDuG7HwBRukNwBnL1emCW6rU8jXTdQhOsubd+mtHP+TOUxjVQ1IwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T16:39:46.870869Z"},"content_sha256":"0e7a35b235dd4c3d82b8c719b9e928460af1f55404da6ac3ffc5114b07a4b3e3","schema_version":"1.0","event_id":"sha256:0e7a35b235dd4c3d82b8c719b9e928460af1f55404da6ac3ffc5114b07a4b3e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3EU3MUW3Y6TNM3IDTP2I4EKV46/bundle.json","state_url":"https://pith.science/pith/3EU3MUW3Y6TNM3IDTP2I4EKV46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3EU3MUW3Y6TNM3IDTP2I4EKV46/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":"2026-05-26T16:39:46Z","links":{"resolver":"https://pith.science/pith/3EU3MUW3Y6TNM3IDTP2I4EKV46","bundle":"https://pith.science/pith/3EU3MUW3Y6TNM3IDTP2I4EKV46/bundle.json","state":"https://pith.science/pith/3EU3MUW3Y6TNM3IDTP2I4EKV46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3EU3MUW3Y6TNM3IDTP2I4EKV46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3EU3MUW3Y6TNM3IDTP2I4EKV46","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":"2ee84f2872483f7fc0373f486fda0ec03e71cdcf6d2e260eb245a11256983169","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-01T17:06:29Z","title_canon_sha256":"01dfec4774dbcf3571afc230ad20ba5f5e08b81e5bbc3a0773410759e70002cf"},"schema_version":"1.0","source":{"id":"1910.04867","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.04867","created_at":"2026-05-17T23:38:12Z"},{"alias_kind":"arxiv_version","alias_value":"1910.04867v2","created_at":"2026-05-17T23:38:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04867","created_at":"2026-05-17T23:38:12Z"},{"alias_kind":"pith_short_12","alias_value":"3EU3MUW3Y6TN","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"3EU3MUW3Y6TNM3ID","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"3EU3MUW3","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:0e7a35b235dd4c3d82b8c719b9e928460af1f55404da6ac3ffc5114b07a4b3e3","target":"graph","created_at":"2026-05-17T23:38:12Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We present the Visual Task Adaptation Benchmark (VTAB), which defines good representations as those that adapt to diverse, unseen tasks with few examples."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That performance on the 19 selected tasks under few-shot linear or fine-tuning adaptation is a reliable proxy for representation quality on arbitrary future vision problems."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"VTAB is a 19-task benchmark that measures representation quality by few-shot adaptation performance across diverse vision domains, with a controlled large-scale comparison of popular pretraining methods."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"The Visual Task Adaptation Benchmark defines good representations as those that adapt to diverse unseen tasks with few examples."}],"snapshot_sha256":"230bc010fe30a13dc4621d61162e32d6c2bdf136237e09836eeb837e0ce31cac"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a09b8e2054ca76035a8e0dd563bf115307d7cc44447e786a7fadf3e388c599d0"},"paper":{"abstract_excerpt":"Representation learning promises to unlock deep learning for the long tail of vision tasks without expensive labelled datasets. Yet, the absence of a unified evaluation for general visual representations hinders progress. Popular protocols are often too constrained (linear classification), limited in diversity (ImageNet, CIFAR, Pascal-VOC), or only weakly related to representation quality (ELBO, reconstruction error). We present the Visual Task Adaptation Benchmark (VTAB), which defines good representations as those that adapt to diverse, unseen tasks with few examples. With VTAB, we conduct a","authors_text":"Alexander Kolesnikov, Alexey Dosovitskiy, Andre Susano Pinto, Carlos Riquelme, Joan Puigcerver, Josip Djolonga, Lucas Beyer, Marcin Michalski, Mario Lucic, Maxim Neumann, Michael Tschannen, Neil Houlsby, Olivier Bachem, Olivier Bousquet, Pierre Ruyssen, Sylvain Gelly, Xiaohua Zhai","cross_cats":["cs.LG","stat.ML"],"headline":"The Visual Task Adaptation Benchmark defines good representations as those that adapt to diverse unseen tasks with few examples.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-01T17:06:29Z","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark"},"references":{"count":25,"internal_anchors":7,"resolved_work":25,"sample":[{"cited_arxiv_id":"1612.03801","doi":"","is_internal_anchor":true,"ref_index":1,"title":"DeepMind Lab","work_id":"8a8d827f-5377-4733-bfe8-bc66c011d458","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Large scale adversarial representation learning","work_id":"0d7176d3-a311-4e05-9a09-5db679be48fb","year":1907},{"cited_arxiv_id":"1905.01235","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","work_id":"7991ef7e-1245-4a3f-acf4-f7509b670d8b","year":1905},{"cited_arxiv_id":"1811.08883","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Rethinking ImageNet pre-training.arXiv preprint arXiv:1811.08883","work_id":"9b366d91-12ae-42d4-9009-cdccc3efe6d2","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"J., Razavi, A., Doersch, C., Eslami, S., and Oord, A","work_id":"5c545404-7449-457a-92aa-390c9d328c06","year":1905}],"snapshot_sha256":"d371c0c782cdec833171ce168889ab4d6ef29c262d83533c94cc8eba57cc5cfa"},"source":{"id":"1910.04867","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T22:07:35.805305Z","id":"81db5567-0e80-4630-944a-029956d166f7","model_set":{"reader":"grok-4.3"},"one_line_summary":"VTAB is a 19-task benchmark that measures representation quality by few-shot adaptation performance across diverse vision domains, with a controlled large-scale comparison of popular pretraining methods.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"The Visual Task Adaptation Benchmark defines good representations as those that adapt to diverse unseen tasks with few examples.","strongest_claim":"We present the Visual Task Adaptation Benchmark (VTAB), which defines good representations as those that adapt to diverse, unseen tasks with few examples.","weakest_assumption":"That performance on the 19 selected tasks under few-shot linear or fine-tuning adaptation is a reliable proxy for representation quality on arbitrary future vision problems."}},"verdict_id":"81db5567-0e80-4630-944a-029956d166f7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1248c9a52e0db191ee43080c1f11142692b2a930b9a3df32801deadc445518f9","target":"record","created_at":"2026-05-17T23:38:12Z","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":"2ee84f2872483f7fc0373f486fda0ec03e71cdcf6d2e260eb245a11256983169","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-01T17:06:29Z","title_canon_sha256":"01dfec4774dbcf3571afc230ad20ba5f5e08b81e5bbc3a0773410759e70002cf"},"schema_version":"1.0","source":{"id":"1910.04867","kind":"arxiv","version":2}},"canonical_sha256":"d929b652dbc7a6d66d039bf48e1155e7bd4d0d8336f66fa3c9da0729f98ec8d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d929b652dbc7a6d66d039bf48e1155e7bd4d0d8336f66fa3c9da0729f98ec8d3","first_computed_at":"2026-05-17T23:38:12.891040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:12.891040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CPCVib8cQ2QFlrWG7Q1gK2Kw8R35FAjmTOHbaMlxhHlpGRAvtgtixKANTHdfBrfOyU3f4g7sV3RqKLZLDBhBDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:12.891649Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.04867","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1248c9a52e0db191ee43080c1f11142692b2a930b9a3df32801deadc445518f9","sha256:0e7a35b235dd4c3d82b8c719b9e928460af1f55404da6ac3ffc5114b07a4b3e3"],"state_sha256":"d046fe6e5d1b8e28453aaaa7bdbbee0fa3d974c29c05f131b1be1c4b7374423a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i64yFKheONp2YZxG3bw10BI1CSbHUOR7GVaE5BpdPfYeGQuzX3B7eAL3wP48ofJDUcGH4qDNBybMqR2SdOgpBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T16:39:46.873748Z","bundle_sha256":"db4f79d35b62b72a21edb3e9c8ca7ae4fb08018df26c6ade977b76f9b01b253e"}}