{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RES7IW24BXP7TTLUPIFU6ST4BQ","short_pith_number":"pith:RES7IW24","schema_version":"1.0","canonical_sha256":"8925f45b5c0ddff9cd747a0b4f4a7c0c1c2faa5000e963778b4bbbac3ddf542f","source":{"kind":"arxiv","id":"2410.01709","version":1},"attestation_state":"computed","paper":{"title":"Meta-TTT: A Meta-learning Minimax Framework For Test-Time Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Tao, Li Shen, Soumik Mondal","submitted_at":"2024-10-02T16:16:05Z","abstract_excerpt":"Test-time domain adaptation is a challenging task that aims to adapt a pre-trained model to limited, unlabeled target data during inference. Current methods that rely on self-supervision and entropy minimization underperform when the self-supervised learning (SSL) task does not align well with the primary objective. Additionally, minimizing entropy can lead to suboptimal solutions when there is limited diversity within minibatches. This paper introduces a meta-learning minimax framework for test-time training on batch normalization (BN) layers, ensuring that the SSL task aligns with the primar"},"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":"2410.01709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T16:16:05Z","cross_cats_sorted":[],"title_canon_sha256":"9c9fd56aec76e197250438e4ab24085bdcf2fb8e58b0b5fd46761f45a8073da2","abstract_canon_sha256":"9ebc4fb800ec7522b4925a329724d9449682b6e140441f5ee01f45579b2421e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:51.019222Z","signature_b64":"byXdmZW/apeOw4vHJnna5uB4YvzcwbfqH4LtwuV/jykgvbFX8Zv+iZ3t917Ohs+sl4F7RfClhd2LLUey2wD6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8925f45b5c0ddff9cd747a0b4f4a7c0c1c2faa5000e963778b4bbbac3ddf542f","last_reissued_at":"2026-07-05T09:14:51.018759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:51.018759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-TTT: A Meta-learning Minimax Framework For Test-Time Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Tao, Li Shen, Soumik Mondal","submitted_at":"2024-10-02T16:16:05Z","abstract_excerpt":"Test-time domain adaptation is a challenging task that aims to adapt a pre-trained model to limited, unlabeled target data during inference. Current methods that rely on self-supervision and entropy minimization underperform when the self-supervised learning (SSL) task does not align well with the primary objective. Additionally, minimizing entropy can lead to suboptimal solutions when there is limited diversity within minibatches. This paper introduces a meta-learning minimax framework for test-time training on batch normalization (BN) layers, ensuring that the SSL task aligns with the primar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01709","kind":"arxiv","version":1},"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/2410.01709/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":"2410.01709","created_at":"2026-07-05T09:14:51.018817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01709v1","created_at":"2026-07-05T09:14:51.018817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01709","created_at":"2026-07-05T09:14:51.018817+00:00"},{"alias_kind":"pith_short_12","alias_value":"RES7IW24BXP7","created_at":"2026-07-05T09:14:51.018817+00:00"},{"alias_kind":"pith_short_16","alias_value":"RES7IW24BXP7TTLU","created_at":"2026-07-05T09:14:51.018817+00:00"},{"alias_kind":"pith_short_8","alias_value":"RES7IW24","created_at":"2026-07-05T09:14:51.018817+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/RES7IW24BXP7TTLUPIFU6ST4BQ","json":"https://pith.science/pith/RES7IW24BXP7TTLUPIFU6ST4BQ.json","graph_json":"https://pith.science/api/pith-number/RES7IW24BXP7TTLUPIFU6ST4BQ/graph.json","events_json":"https://pith.science/api/pith-number/RES7IW24BXP7TTLUPIFU6ST4BQ/events.json","paper":"https://pith.science/paper/RES7IW24"},"agent_actions":{"view_html":"https://pith.science/pith/RES7IW24BXP7TTLUPIFU6ST4BQ","download_json":"https://pith.science/pith/RES7IW24BXP7TTLUPIFU6ST4BQ.json","view_paper":"https://pith.science/paper/RES7IW24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01709&json=true","fetch_graph":"https://pith.science/api/pith-number/RES7IW24BXP7TTLUPIFU6ST4BQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RES7IW24BXP7TTLUPIFU6ST4BQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RES7IW24BXP7TTLUPIFU6ST4BQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RES7IW24BXP7TTLUPIFU6ST4BQ/action/storage_attestation","attest_author":"https://pith.science/pith/RES7IW24BXP7TTLUPIFU6ST4BQ/action/author_attestation","sign_citation":"https://pith.science/pith/RES7IW24BXP7TTLUPIFU6ST4BQ/action/citation_signature","submit_replication":"https://pith.science/pith/RES7IW24BXP7TTLUPIFU6ST4BQ/action/replication_record"}},"created_at":"2026-07-05T09:14:51.018817+00:00","updated_at":"2026-07-05T09:14:51.018817+00:00"}