{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CZ3DEHME7BS6PIONOW2Q2ODFQF","short_pith_number":"pith:CZ3DEHME","canonical_record":{"source":{"id":"2006.10726","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T17:55:28Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"633f4b66ea7dd4e96d2d1469359bec004d94ae76ea4beb07a36a18ae6a9896af","abstract_canon_sha256":"0dfe9235fdf41855a1a0adae0ccd98f53b031e0d0df549f0e42487e3353063f2"},"schema_version":"1.0"},"canonical_sha256":"1676321d84f865e7a1cd75b50d386581544012943770c5152a8d93b1d90eabc8","source":{"kind":"arxiv","id":"2006.10726","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.10726","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2006.10726v3","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10726","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"CZ3DEHME7BS6","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"CZ3DEHME7BS6PION","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"CZ3DEHME","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CZ3DEHME7BS6PIONOW2Q2ODFQF","target":"record","payload":{"canonical_record":{"source":{"id":"2006.10726","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T17:55:28Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"633f4b66ea7dd4e96d2d1469359bec004d94ae76ea4beb07a36a18ae6a9896af","abstract_canon_sha256":"0dfe9235fdf41855a1a0adae0ccd98f53b031e0d0df549f0e42487e3353063f2"},"schema_version":"1.0"},"canonical_sha256":"1676321d84f865e7a1cd75b50d386581544012943770c5152a8d93b1d90eabc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.234831Z","signature_b64":"PhWjPfXIvzzhkAwCTrzb3unCPzHOGWX9yAXvgjBcGWzSj9EBdX0dfgGUWMDbUM73lRcpJFU/qez86hUoffy8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1676321d84f865e7a1cd75b50d386581544012943770c5152a8d93b1d90eabc8","last_reissued_at":"2026-05-17T23:38:48.234330Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.234330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.10726","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":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aRlEnd67FCXYPsDelVhw6iAOauHZFEHv0NRtS8A8NB0p1ah495iofQmdgYyk8VPCwt4W1xK1n5G6Vx4BAactCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T06:26:01.762379Z"},"content_sha256":"6b2b497684cf60c0c48afc2052670f32bc3a81a486952c46697744174785bb4b","schema_version":"1.0","event_id":"sha256:6b2b497684cf60c0c48afc2052670f32bc3a81a486952c46697744174785bb4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CZ3DEHME7BS6PIONOW2Q2ODFQF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tent: Fully Test-time Adaptation by Entropy Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A model adapts to new test data at inference time by minimizing the entropy of its predictions.","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Olshausen, Dequan Wang, Evan Shelhamer, Shaoteng Liu, Trevor Darrell","submitted_at":"2020-06-18T17:55:28Z","abstract_excerpt":"A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy minimization (tent): we optimize the model for confidence as measured by the entropy of its predictions. Our method estimates normalization statistics and optimizes channel-wise affine transformations to update online on each batch. Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on Imag"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on ImageNet-C. It handles source-free domain adaptation on digit recognition from SVHN to MNIST/MNIST-M/USPS, on semantic segmentation from GTA to Cityscapes, and on the VisDA-C benchmark.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That minimizing the entropy of the model's predictions on unlabeled test batches will improve accuracy on the target distribution without causing collapse to trivial solutions or overfitting to batch-specific noise.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Test-time entropy minimization adapts models by optimizing for confident predictions, reducing error on corrupted ImageNet-C and enabling source-free domain adaptation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A model adapts to new test data at inference time by minimizing the entropy of its predictions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5c313bbf716747553d188c1beacbf52c6ae9b6ee4a72433d5a408a2b489de492"},"source":{"id":"2006.10726","kind":"arxiv","version":3},"verdict":{"id":"93f743de-ee88-4ea5-8efb-ccf94a7c5577","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T10:05:11.122353Z","strongest_claim":"Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on ImageNet-C. It handles source-free domain adaptation on digit recognition from SVHN to MNIST/MNIST-M/USPS, on semantic segmentation from GTA to Cityscapes, and on the VisDA-C benchmark.","one_line_summary":"Test-time entropy minimization adapts models by optimizing for confident predictions, reducing error on corrupted ImageNet-C and enabling source-free domain adaptation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That minimizing the entropy of the model's predictions on unlabeled test batches will improve accuracy on the target distribution without causing collapse to trivial solutions or overfitting to batch-specific noise.","pith_extraction_headline":"A model adapts to new test data at inference time by minimizing the entropy of its predictions."},"references":{"count":12,"sample":[{"doi":"","year":2006,"title":"Multiscale deep equilibrium models","work_id":"00ad9c87-106d-4e2c-97f3-6ae90e33ed30","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Autodial: Automatic domain alignment layers","work_id":"b6daca15-6358-4483-8c97-0841d01090fa","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","work_id":"f3dc32a4-cf81-467b-8ff4-3b2f21d3bf1f","ref_index":3,"cited_arxiv_id":"1706.02677","is_internal_anchor":true},{"doi":"","year":2021,"title":"Online domain adaptation of a pre-trained cascade of classifiers","work_id":"2b503756-790e-49fa-a7c9-5d85cc82f7db","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2006,"title":"InProceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tech- nologies (NAACL-HLT), pages 681–691","work_id":"6da0197d-290e-4aa5-9b79-54e048aa4c68","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":12,"snapshot_sha256":"b7631bb58ec1138ede0ffd23f5c2cab4a87c24854663d1e86be049f5afa3317f","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8db0e90b01c88d16689af4f52f3a43eea1aa97c6377f654b49929b27e6660567"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"93f743de-ee88-4ea5-8efb-ccf94a7c5577"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eEc3b7oQV4EWy+Xb7QMHqrlKLaW0JnWczJTR4qTkuk+O+curCLB6NJpUgTOfPn33e8NkYaAN3BsnzpBFeU2BAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T06:26:01.763592Z"},"content_sha256":"59ddf544a96d390d3a2d0f10e03948bad437324ce00c17248d12baba83e12d00","schema_version":"1.0","event_id":"sha256:59ddf544a96d390d3a2d0f10e03948bad437324ce00c17248d12baba83e12d00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZ3DEHME7BS6PIONOW2Q2ODFQF/bundle.json","state_url":"https://pith.science/pith/CZ3DEHME7BS6PIONOW2Q2ODFQF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZ3DEHME7BS6PIONOW2Q2ODFQF/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":"2026-05-30T06:26:01Z","links":{"resolver":"https://pith.science/pith/CZ3DEHME7BS6PIONOW2Q2ODFQF","bundle":"https://pith.science/pith/CZ3DEHME7BS6PIONOW2Q2ODFQF/bundle.json","state":"https://pith.science/pith/CZ3DEHME7BS6PIONOW2Q2ODFQF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZ3DEHME7BS6PIONOW2Q2ODFQF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CZ3DEHME7BS6PIONOW2Q2ODFQF","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":"0dfe9235fdf41855a1a0adae0ccd98f53b031e0d0df549f0e42487e3353063f2","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T17:55:28Z","title_canon_sha256":"633f4b66ea7dd4e96d2d1469359bec004d94ae76ea4beb07a36a18ae6a9896af"},"schema_version":"1.0","source":{"id":"2006.10726","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.10726","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2006.10726v3","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10726","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"CZ3DEHME7BS6","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"CZ3DEHME7BS6PION","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"CZ3DEHME","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:59ddf544a96d390d3a2d0f10e03948bad437324ce00c17248d12baba83e12d00","target":"graph","created_at":"2026-05-17T23:38:48Z","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":"Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on ImageNet-C. It handles source-free domain adaptation on digit recognition from SVHN to MNIST/MNIST-M/USPS, on semantic segmentation from GTA to Cityscapes, and on the VisDA-C benchmark."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That minimizing the entropy of the model's predictions on unlabeled test batches will improve accuracy on the target distribution without causing collapse to trivial solutions or overfitting to batch-specific noise."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Test-time entropy minimization adapts models by optimizing for confident predictions, reducing error on corrupted ImageNet-C and enabling source-free domain adaptation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A model adapts to new test data at inference time by minimizing the entropy of its predictions."}],"snapshot_sha256":"5c313bbf716747553d188c1beacbf52c6ae9b6ee4a72433d5a408a2b489de492"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8db0e90b01c88d16689af4f52f3a43eea1aa97c6377f654b49929b27e6660567"},"paper":{"abstract_excerpt":"A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy minimization (tent): we optimize the model for confidence as measured by the entropy of its predictions. Our method estimates normalization statistics and optimizes channel-wise affine transformations to update online on each batch. Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on Imag","authors_text":"Bruno Olshausen, Dequan Wang, Evan Shelhamer, Shaoteng Liu, Trevor Darrell","cross_cats":["cs.CV","stat.ML"],"headline":"A model adapts to new test data at inference time by minimizing the entropy of its predictions.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T17:55:28Z","title":"Tent: Fully Test-time Adaptation by Entropy Minimization"},"references":{"count":12,"internal_anchors":3,"resolved_work":12,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Multiscale deep equilibrium models","work_id":"00ad9c87-106d-4e2c-97f3-6ae90e33ed30","year":2006},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Autodial: Automatic domain alignment layers","work_id":"b6daca15-6358-4483-8c97-0841d01090fa","year":2017},{"cited_arxiv_id":"1706.02677","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","work_id":"f3dc32a4-cf81-467b-8ff4-3b2f21d3bf1f","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Online domain adaptation of a pre-trained cascade of classifiers","work_id":"2b503756-790e-49fa-a7c9-5d85cc82f7db","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"InProceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tech- nologies (NAACL-HLT), pages 681–691","work_id":"6da0197d-290e-4aa5-9b79-54e048aa4c68","year":2006}],"snapshot_sha256":"b7631bb58ec1138ede0ffd23f5c2cab4a87c24854663d1e86be049f5afa3317f"},"source":{"id":"2006.10726","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T10:05:11.122353Z","id":"93f743de-ee88-4ea5-8efb-ccf94a7c5577","model_set":{"reader":"grok-4.3"},"one_line_summary":"Test-time entropy minimization adapts models by optimizing for confident predictions, reducing error on corrupted ImageNet-C and enabling source-free domain adaptation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A model adapts to new test data at inference time by minimizing the entropy of its predictions.","strongest_claim":"Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on ImageNet-C. It handles source-free domain adaptation on digit recognition from SVHN to MNIST/MNIST-M/USPS, on semantic segmentation from GTA to Cityscapes, and on the VisDA-C benchmark.","weakest_assumption":"That minimizing the entropy of the model's predictions on unlabeled test batches will improve accuracy on the target distribution without causing collapse to trivial solutions or overfitting to batch-specific noise."}},"verdict_id":"93f743de-ee88-4ea5-8efb-ccf94a7c5577"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6b2b497684cf60c0c48afc2052670f32bc3a81a486952c46697744174785bb4b","target":"record","created_at":"2026-05-17T23:38:48Z","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":"0dfe9235fdf41855a1a0adae0ccd98f53b031e0d0df549f0e42487e3353063f2","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T17:55:28Z","title_canon_sha256":"633f4b66ea7dd4e96d2d1469359bec004d94ae76ea4beb07a36a18ae6a9896af"},"schema_version":"1.0","source":{"id":"2006.10726","kind":"arxiv","version":3}},"canonical_sha256":"1676321d84f865e7a1cd75b50d386581544012943770c5152a8d93b1d90eabc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1676321d84f865e7a1cd75b50d386581544012943770c5152a8d93b1d90eabc8","first_computed_at":"2026-05-17T23:38:48.234330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.234330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PhWjPfXIvzzhkAwCTrzb3unCPzHOGWX9yAXvgjBcGWzSj9EBdX0dfgGUWMDbUM73lRcpJFU/qez86hUoffy8CA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.234831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.10726","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b2b497684cf60c0c48afc2052670f32bc3a81a486952c46697744174785bb4b","sha256:59ddf544a96d390d3a2d0f10e03948bad437324ce00c17248d12baba83e12d00"],"state_sha256":"5b92ec4c410a789efe0c6619adaf3d76623be8315dd11233d1548a26a642bc22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UkzwxFVI449l12gcNLp4QNn4mbj/UbPGmz+8eFWiHwITEWIQLsbxhFhkQ9XFKiIEdQ2+kEe13MOzK6G2tOQ5Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T06:26:01.768088Z","bundle_sha256":"4c26ede7bd25110b3a7a890c033155d8ef94fc47a887a2f56c520c31cf02cdfc"}}