{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MMGYCY5Y7EFMFTIGZPTGYOVZZU","short_pith_number":"pith:MMGYCY5Y","schema_version":"1.0","canonical_sha256":"630d8163b8f90ac2cd06cbe66c3ab9cd3c8f6ef0eb44f939706c79702ad718cb","source":{"kind":"arxiv","id":"2311.14402","version":2},"attestation_state":"computed","paper":{"title":"TEA: Test-time Energy Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingbing Xu, Fei Sun, Huawei Shen, Liang Hou, Xueqi Cheng, Yige Yuan","submitted_at":"2023-11-24T10:49:49Z","abstract_excerpt":"Test-time adaptation (TTA) aims to improve model generalizability when test data diverges from training distribution, offering the distinct advantage of not requiring access to training data and processes, especially valuable in the context of large pre-trained models. However, current TTA methods fail to address the fundamental issue: covariate shift, i.e., the decreased generalizability can be attributed to the model's reliance on the marginal distribution of the training data, which may impair model calibration and introduce confirmation bias. To address this, we propose a novel energy-base"},"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":"2311.14402","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-24T10:49:49Z","cross_cats_sorted":[],"title_canon_sha256":"8b8ba580f6adcb9202cae3d773bc0660b5d80c07347c564e160e3aba73e36ddf","abstract_canon_sha256":"cf89038c5b352deeb4255220bc65db13d197acc51e881c8bf435b9025ded5143"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:35.261498Z","signature_b64":"nZX+aJV/1Clc+l6cTQbW/xd8Ft7U4U48hzJ5Nh57CZWgl6nix6S5DdXUgdBWfFpScjB2NQiR89y9pulKdeZqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"630d8163b8f90ac2cd06cbe66c3ab9cd3c8f6ef0eb44f939706c79702ad718cb","last_reissued_at":"2026-07-05T07:49:35.260936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:35.260936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TEA: Test-time Energy Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingbing Xu, Fei Sun, Huawei Shen, Liang Hou, Xueqi Cheng, Yige Yuan","submitted_at":"2023-11-24T10:49:49Z","abstract_excerpt":"Test-time adaptation (TTA) aims to improve model generalizability when test data diverges from training distribution, offering the distinct advantage of not requiring access to training data and processes, especially valuable in the context of large pre-trained models. However, current TTA methods fail to address the fundamental issue: covariate shift, i.e., the decreased generalizability can be attributed to the model's reliance on the marginal distribution of the training data, which may impair model calibration and introduce confirmation bias. To address this, we propose a novel energy-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14402","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/2311.14402/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":"2311.14402","created_at":"2026-07-05T07:49:35.261020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14402v2","created_at":"2026-07-05T07:49:35.261020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14402","created_at":"2026-07-05T07:49:35.261020+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMGYCY5Y7EFM","created_at":"2026-07-05T07:49:35.261020+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMGYCY5Y7EFMFTIG","created_at":"2026-07-05T07:49:35.261020+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMGYCY5Y","created_at":"2026-07-05T07:49:35.261020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19890","citing_title":"GoTTA be Diverse: Rethinking Memory Policies for Test-Time Adaptation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMGYCY5Y7EFMFTIGZPTGYOVZZU","json":"https://pith.science/pith/MMGYCY5Y7EFMFTIGZPTGYOVZZU.json","graph_json":"https://pith.science/api/pith-number/MMGYCY5Y7EFMFTIGZPTGYOVZZU/graph.json","events_json":"https://pith.science/api/pith-number/MMGYCY5Y7EFMFTIGZPTGYOVZZU/events.json","paper":"https://pith.science/paper/MMGYCY5Y"},"agent_actions":{"view_html":"https://pith.science/pith/MMGYCY5Y7EFMFTIGZPTGYOVZZU","download_json":"https://pith.science/pith/MMGYCY5Y7EFMFTIGZPTGYOVZZU.json","view_paper":"https://pith.science/paper/MMGYCY5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14402&json=true","fetch_graph":"https://pith.science/api/pith-number/MMGYCY5Y7EFMFTIGZPTGYOVZZU/graph.json","fetch_events":"https://pith.science/api/pith-number/MMGYCY5Y7EFMFTIGZPTGYOVZZU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMGYCY5Y7EFMFTIGZPTGYOVZZU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMGYCY5Y7EFMFTIGZPTGYOVZZU/action/storage_attestation","attest_author":"https://pith.science/pith/MMGYCY5Y7EFMFTIGZPTGYOVZZU/action/author_attestation","sign_citation":"https://pith.science/pith/MMGYCY5Y7EFMFTIGZPTGYOVZZU/action/citation_signature","submit_replication":"https://pith.science/pith/MMGYCY5Y7EFMFTIGZPTGYOVZZU/action/replication_record"}},"created_at":"2026-07-05T07:49:35.261020+00:00","updated_at":"2026-07-05T07:49:35.261020+00:00"}