{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZXKYHEH6SF5FI2TUW4FLFOYLZP","short_pith_number":"pith:ZXKYHEH6","schema_version":"1.0","canonical_sha256":"cdd58390fe917a546a74b70ab2bb0bcbd0d9643530b04698018b14de53e49010","source":{"kind":"arxiv","id":"2407.15773","version":2},"attestation_state":"computed","paper":{"title":"STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jian Liang, Lijun Sheng, Ran He, Yongcan Yu","submitted_at":"2024-07-22T16:25:41Z","abstract_excerpt":"Test-time adaptation (TTA) aims to address the distribution shift between the training and test data with only unlabeled data at test time. Existing TTA methods often focus on improving recognition performance specifically for test data associated with classes in the training set. However, during the open-world inference process, there are inevitably test data instances from unknown classes, commonly referred to as outliers. This paper pays attention to the problem that conducts both sample recognition and outlier rejection during inference while outliers exist. To address this problem, we pro"},"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":"2407.15773","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-22T16:25:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"66d24e13b85b2d4864e0a33b7dc5f5ee034ddee724a614e9066813f5285f24bc","abstract_canon_sha256":"4334491dd3176aa9460bf50e443c37a1fbf3bda70da28a2e0804f15475cb96f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:31.937488Z","signature_b64":"SPNQyaQDCX3bjLDolWE+vpy87pCJ2E2S7pgmjS/Tw/oAm4ULt4nydGR07LlbfyhfKgMLSgraNnn1EX3D7gXDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdd58390fe917a546a74b70ab2bb0bcbd0d9643530b04698018b14de53e49010","last_reissued_at":"2026-07-05T08:59:31.937046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:31.937046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jian Liang, Lijun Sheng, Ran He, Yongcan Yu","submitted_at":"2024-07-22T16:25:41Z","abstract_excerpt":"Test-time adaptation (TTA) aims to address the distribution shift between the training and test data with only unlabeled data at test time. Existing TTA methods often focus on improving recognition performance specifically for test data associated with classes in the training set. However, during the open-world inference process, there are inevitably test data instances from unknown classes, commonly referred to as outliers. This paper pays attention to the problem that conducts both sample recognition and outlier rejection during inference while outliers exist. To address this problem, we pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15773","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/2407.15773/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":"2407.15773","created_at":"2026-07-05T08:59:31.937103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15773v2","created_at":"2026-07-05T08:59:31.937103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15773","created_at":"2026-07-05T08:59:31.937103+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXKYHEH6SF5F","created_at":"2026-07-05T08:59:31.937103+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXKYHEH6SF5FI2TU","created_at":"2026-07-05T08:59:31.937103+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXKYHEH6","created_at":"2026-07-05T08:59:31.937103+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":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXKYHEH6SF5FI2TUW4FLFOYLZP","json":"https://pith.science/pith/ZXKYHEH6SF5FI2TUW4FLFOYLZP.json","graph_json":"https://pith.science/api/pith-number/ZXKYHEH6SF5FI2TUW4FLFOYLZP/graph.json","events_json":"https://pith.science/api/pith-number/ZXKYHEH6SF5FI2TUW4FLFOYLZP/events.json","paper":"https://pith.science/paper/ZXKYHEH6"},"agent_actions":{"view_html":"https://pith.science/pith/ZXKYHEH6SF5FI2TUW4FLFOYLZP","download_json":"https://pith.science/pith/ZXKYHEH6SF5FI2TUW4FLFOYLZP.json","view_paper":"https://pith.science/paper/ZXKYHEH6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15773&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXKYHEH6SF5FI2TUW4FLFOYLZP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXKYHEH6SF5FI2TUW4FLFOYLZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXKYHEH6SF5FI2TUW4FLFOYLZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXKYHEH6SF5FI2TUW4FLFOYLZP/action/storage_attestation","attest_author":"https://pith.science/pith/ZXKYHEH6SF5FI2TUW4FLFOYLZP/action/author_attestation","sign_citation":"https://pith.science/pith/ZXKYHEH6SF5FI2TUW4FLFOYLZP/action/citation_signature","submit_replication":"https://pith.science/pith/ZXKYHEH6SF5FI2TUW4FLFOYLZP/action/replication_record"}},"created_at":"2026-07-05T08:59:31.937103+00:00","updated_at":"2026-07-05T08:59:31.937103+00:00"}