{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:54QE4CYPA5RWBZLGNSMWDRHJQZ","short_pith_number":"pith:54QE4CYP","canonical_record":{"source":{"id":"2206.00205","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-01T03:02:07Z","cross_cats_sorted":[],"title_canon_sha256":"7fea363e109587d220dd736f99568802740de06092514728feda09f6121fffdd","abstract_canon_sha256":"fe3b5848237016c9520df2a39aee25ab655ef0a6d3e67646630903667985b334"},"schema_version":"1.0"},"canonical_sha256":"ef204e0b0f076360e5666c9961c4e98642620b58ce901f9930d3a639c8a2827e","source":{"kind":"arxiv","id":"2206.00205","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00205","created_at":"2026-07-05T06:47:13Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00205v3","created_at":"2026-07-05T06:47:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00205","created_at":"2026-07-05T06:47:13Z"},{"alias_kind":"pith_short_12","alias_value":"54QE4CYPA5RW","created_at":"2026-07-05T06:47:13Z"},{"alias_kind":"pith_short_16","alias_value":"54QE4CYPA5RWBZLG","created_at":"2026-07-05T06:47:13Z"},{"alias_kind":"pith_short_8","alias_value":"54QE4CYP","created_at":"2026-07-05T06:47:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:54QE4CYPA5RWBZLGNSMWDRHJQZ","target":"record","payload":{"canonical_record":{"source":{"id":"2206.00205","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-01T03:02:07Z","cross_cats_sorted":[],"title_canon_sha256":"7fea363e109587d220dd736f99568802740de06092514728feda09f6121fffdd","abstract_canon_sha256":"fe3b5848237016c9520df2a39aee25ab655ef0a6d3e67646630903667985b334"},"schema_version":"1.0"},"canonical_sha256":"ef204e0b0f076360e5666c9961c4e98642620b58ce901f9930d3a639c8a2827e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:13.304787Z","signature_b64":"dxaT52DWMNIhADtmOXUpNvTEJFaGcrSQPqCVM7Nr/A80hp9Sk2zWI6DvldZJB4B5gEGFvtq0Fk4k7y9jgim8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef204e0b0f076360e5666c9961c4e98642620b58ce901f9930d3a639c8a2827e","last_reissued_at":"2026-07-05T06:47:13.304388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:13.304388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.00205","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":"2026-07-05T06:47:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"276mkfPmuGtH3l+ra7BBsvnx77zmgKzr4q7i+/yeQdeiUCw9LKnZ5D4kW3kRR77ewiafncVmgen+mOx+ReXXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:42:14.602970Z"},"content_sha256":"6d2335766f602f4ebdf78007b1b50885f64c7a22a8ff6910c2db780938606191","schema_version":"1.0","event_id":"sha256:6d2335766f602f4ebdf78007b1b50885f64c7a22a8ff6910c2db780938606191"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:54QE4CYPA5RWBZLGNSMWDRHJQZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CAFA: Class-Aware Feature Alignment for Test-Time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amirreza Shaban, Byron Boots, Jaegul Choo, Jungsoo Lee, Nanhee Kim, Sanghun Jung","submitted_at":"2022-06-01T03:02:07Z","abstract_excerpt":"Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. TTA can be applied to pretrained networks without modifying their training procedures, enabling them to utilize a well-formed source distribution for adaptation. One possible approach is to align the representation space of test samples to the source distribution (\\textit{i.e.,} feature alignment). However, performi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00205","kind":"arxiv","version":3},"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/2206.00205/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:47:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cE5b/C9wpshBlAnYZUKkJcgtljIVVQvZDs2Wo/B4tHcnNBiCuPFiMiY71aObQycxm9nWdY3avUE+y61wF92DDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:42:14.603970Z"},"content_sha256":"1476f0adcec614f6c0223a03fd939bfa6c4f38d63866f4f0fb28d97a001b5449","schema_version":"1.0","event_id":"sha256:1476f0adcec614f6c0223a03fd939bfa6c4f38d63866f4f0fb28d97a001b5449"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54QE4CYPA5RWBZLGNSMWDRHJQZ/bundle.json","state_url":"https://pith.science/pith/54QE4CYPA5RWBZLGNSMWDRHJQZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54QE4CYPA5RWBZLGNSMWDRHJQZ/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":"2026-08-03T19:42:14Z","links":{"resolver":"https://pith.science/pith/54QE4CYPA5RWBZLGNSMWDRHJQZ","bundle":"https://pith.science/pith/54QE4CYPA5RWBZLGNSMWDRHJQZ/bundle.json","state":"https://pith.science/pith/54QE4CYPA5RWBZLGNSMWDRHJQZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54QE4CYPA5RWBZLGNSMWDRHJQZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:54QE4CYPA5RWBZLGNSMWDRHJQZ","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":"fe3b5848237016c9520df2a39aee25ab655ef0a6d3e67646630903667985b334","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-01T03:02:07Z","title_canon_sha256":"7fea363e109587d220dd736f99568802740de06092514728feda09f6121fffdd"},"schema_version":"1.0","source":{"id":"2206.00205","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00205","created_at":"2026-07-05T06:47:13Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00205v3","created_at":"2026-07-05T06:47:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00205","created_at":"2026-07-05T06:47:13Z"},{"alias_kind":"pith_short_12","alias_value":"54QE4CYPA5RW","created_at":"2026-07-05T06:47:13Z"},{"alias_kind":"pith_short_16","alias_value":"54QE4CYPA5RWBZLG","created_at":"2026-07-05T06:47:13Z"},{"alias_kind":"pith_short_8","alias_value":"54QE4CYP","created_at":"2026-07-05T06:47:13Z"}],"graph_snapshots":[{"event_id":"sha256:1476f0adcec614f6c0223a03fd939bfa6c4f38d63866f4f0fb28d97a001b5449","target":"graph","created_at":"2026-07-05T06:47:13Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.00205/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. TTA can be applied to pretrained networks without modifying their training procedures, enabling them to utilize a well-formed source distribution for adaptation. One possible approach is to align the representation space of test samples to the source distribution (\\textit{i.e.,} feature alignment). However, performi","authors_text":"Amirreza Shaban, Byron Boots, Jaegul Choo, Jungsoo Lee, Nanhee Kim, Sanghun Jung","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-01T03:02:07Z","title":"CAFA: Class-Aware Feature Alignment for Test-Time Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00205","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6d2335766f602f4ebdf78007b1b50885f64c7a22a8ff6910c2db780938606191","target":"record","created_at":"2026-07-05T06:47:13Z","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":"fe3b5848237016c9520df2a39aee25ab655ef0a6d3e67646630903667985b334","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-01T03:02:07Z","title_canon_sha256":"7fea363e109587d220dd736f99568802740de06092514728feda09f6121fffdd"},"schema_version":"1.0","source":{"id":"2206.00205","kind":"arxiv","version":3}},"canonical_sha256":"ef204e0b0f076360e5666c9961c4e98642620b58ce901f9930d3a639c8a2827e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef204e0b0f076360e5666c9961c4e98642620b58ce901f9930d3a639c8a2827e","first_computed_at":"2026-07-05T06:47:13.304388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:13.304388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dxaT52DWMNIhADtmOXUpNvTEJFaGcrSQPqCVM7Nr/A80hp9Sk2zWI6DvldZJB4B5gEGFvtq0Fk4k7y9jgim8Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:13.304787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.00205","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d2335766f602f4ebdf78007b1b50885f64c7a22a8ff6910c2db780938606191","sha256:1476f0adcec614f6c0223a03fd939bfa6c4f38d63866f4f0fb28d97a001b5449"],"state_sha256":"04703911a42282a113941b304914286d4367280f99c987a53cc7ef306a8f34b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+xRHxqBRlQ6F6qVwISArswqKwYhlfETSKbIJHECXaNzVZSchswHpcjXNX+MqwI0fJ2lpbhD6D4+3olMePLwrBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:42:14.611944Z","bundle_sha256":"1c94d74c1a4bd8efa44666b158473a85aa2e04eccf1a631738715f05a7651707"}}