{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7YWWPYMXTYDVZ5SWD4A7KXGLFI","short_pith_number":"pith:7YWWPYMX","schema_version":"1.0","canonical_sha256":"fe2d67e1979e075cf6561f01f55ccb2a279709afcc3b6de32db0879d0719af07","source":{"kind":"arxiv","id":"2103.16201","version":2},"attestation_state":"computed","paper":{"title":"MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexander Bartler, Andre B\\\"uhler, Bin Yang, Felix Wiewel, Mario D\\\"obler","submitted_at":"2021-03-30T09:33:38Z","abstract_excerpt":"An unresolved problem in Deep Learning is the ability of neural networks to cope with domain shifts during test-time, imposed by commonly fixing network parameters after training. Our proposed method Meta Test-Time Training (MT3), however, breaks this paradigm and enables adaption at test-time. We combine meta-learning, self-supervision and test-time training to learn to adapt to unseen test distributions. By minimizing the self-supervised loss, we learn task-specific model parameters for different tasks. A meta-model is optimized such that its adaption to the different task-specific models le"},"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":"2103.16201","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T09:33:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3392c411cc3c5803b0304652f480c58c9081004147020f7cb7c27fae4abe791a","abstract_canon_sha256":"927bd11ee71981d375aafdfd59136e8161d95ba3ea75339d983dd60a4f1a917b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:49:59.948254Z","signature_b64":"Dem88L3prKOYuNDPtkUoOwkIh/gZc4xiqH5OI8wyw4VaT3IuXKqZhEJIAi4QiEHeFLJr5g9FBqyxbBO7/SzjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe2d67e1979e075cf6561f01f55ccb2a279709afcc3b6de32db0879d0719af07","last_reissued_at":"2026-07-05T03:49:59.947786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:49:59.947786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexander Bartler, Andre B\\\"uhler, Bin Yang, Felix Wiewel, Mario D\\\"obler","submitted_at":"2021-03-30T09:33:38Z","abstract_excerpt":"An unresolved problem in Deep Learning is the ability of neural networks to cope with domain shifts during test-time, imposed by commonly fixing network parameters after training. Our proposed method Meta Test-Time Training (MT3), however, breaks this paradigm and enables adaption at test-time. We combine meta-learning, self-supervision and test-time training to learn to adapt to unseen test distributions. By minimizing the self-supervised loss, we learn task-specific model parameters for different tasks. A meta-model is optimized such that its adaption to the different task-specific models le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16201","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/2103.16201/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":"2103.16201","created_at":"2026-07-05T03:49:59.947849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.16201v2","created_at":"2026-07-05T03:49:59.947849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16201","created_at":"2026-07-05T03:49:59.947849+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YWWPYMXTYDV","created_at":"2026-07-05T03:49:59.947849+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YWWPYMXTYDVZ5SW","created_at":"2026-07-05T03:49:59.947849+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YWWPYMX","created_at":"2026-07-05T03:49:59.947849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YWWPYMXTYDVZ5SWD4A7KXGLFI","json":"https://pith.science/pith/7YWWPYMXTYDVZ5SWD4A7KXGLFI.json","graph_json":"https://pith.science/api/pith-number/7YWWPYMXTYDVZ5SWD4A7KXGLFI/graph.json","events_json":"https://pith.science/api/pith-number/7YWWPYMXTYDVZ5SWD4A7KXGLFI/events.json","paper":"https://pith.science/paper/7YWWPYMX"},"agent_actions":{"view_html":"https://pith.science/pith/7YWWPYMXTYDVZ5SWD4A7KXGLFI","download_json":"https://pith.science/pith/7YWWPYMXTYDVZ5SWD4A7KXGLFI.json","view_paper":"https://pith.science/paper/7YWWPYMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.16201&json=true","fetch_graph":"https://pith.science/api/pith-number/7YWWPYMXTYDVZ5SWD4A7KXGLFI/graph.json","fetch_events":"https://pith.science/api/pith-number/7YWWPYMXTYDVZ5SWD4A7KXGLFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YWWPYMXTYDVZ5SWD4A7KXGLFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YWWPYMXTYDVZ5SWD4A7KXGLFI/action/storage_attestation","attest_author":"https://pith.science/pith/7YWWPYMXTYDVZ5SWD4A7KXGLFI/action/author_attestation","sign_citation":"https://pith.science/pith/7YWWPYMXTYDVZ5SWD4A7KXGLFI/action/citation_signature","submit_replication":"https://pith.science/pith/7YWWPYMXTYDVZ5SWD4A7KXGLFI/action/replication_record"}},"created_at":"2026-07-05T03:49:59.947849+00:00","updated_at":"2026-07-05T03:49:59.947849+00:00"}