{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:67JQCB22U4P6KXH4PVX2RIRGSQ","short_pith_number":"pith:67JQCB22","canonical_record":{"source":{"id":"2207.09640","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T04:02:19Z","cross_cats_sorted":[],"title_canon_sha256":"fb44417bd5ae3ae82644d745be6c7d22d480dc221164263fb53afa059ef783d1","abstract_canon_sha256":"4bdddc2742a780ec2ddc8678739749cf0736aec6bfc86c067900cdfdea416a70"},"schema_version":"1.0"},"canonical_sha256":"f7d301075aa71fe55cfc7d6fa8a22694392b9716d463f159e1b8fa563bc04217","source":{"kind":"arxiv","id":"2207.09640","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.09640","created_at":"2026-07-05T05:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2207.09640v2","created_at":"2026-07-05T05:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09640","created_at":"2026-07-05T05:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"67JQCB22U4P6","created_at":"2026-07-05T05:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"67JQCB22U4P6KXH4","created_at":"2026-07-05T05:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"67JQCB22","created_at":"2026-07-05T05:18:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:67JQCB22U4P6KXH4PVX2RIRGSQ","target":"record","payload":{"canonical_record":{"source":{"id":"2207.09640","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T04:02:19Z","cross_cats_sorted":[],"title_canon_sha256":"fb44417bd5ae3ae82644d745be6c7d22d480dc221164263fb53afa059ef783d1","abstract_canon_sha256":"4bdddc2742a780ec2ddc8678739749cf0736aec6bfc86c067900cdfdea416a70"},"schema_version":"1.0"},"canonical_sha256":"f7d301075aa71fe55cfc7d6fa8a22694392b9716d463f159e1b8fa563bc04217","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:47.710990Z","signature_b64":"xB19fz0NcHdXn3QZKxSADYOUOrdhhJus/obkdBP2Bkr6HlfQ9W53m9s1pathV/WzaGZJWNccoUnL8YyV4rsjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7d301075aa71fe55cfc7d6fa8a22694392b9716d463f159e1b8fa563bc04217","last_reissued_at":"2026-07-05T05:18:47.710265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:47.710265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.09640","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:18:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zMwihXLfHR4qruoHSiENKzep8H6MY/RVnOfNyXOX3Cd5zSVV65xQxGJ87DIBtL1DkhQodQK6DngBwLABEHAXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:36:53.863649Z"},"content_sha256":"287b9f8ab99e3020f8da09f406564c86efb12859ddbc8559e6dd18befbfe8789","schema_version":"1.0","event_id":"sha256:287b9f8ab99e3020f8da09f406564c86efb12859ddbc8559e6dd18befbfe8789"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:67JQCB22U4P6KXH4PVX2RIRGSQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Test-Time Adaptation via Conjugate Pseudo-labels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditi Raghunathan, Mingjie Sun, Sachin Goyal, Zico Kolter","submitted_at":"2022-07-20T04:02:19Z","abstract_excerpt":"Test-time adaptation (TTA) refers to adapting neural networks to distribution shifts, with access to only the unlabeled test samples from the new domain at test-time. Prior TTA methods optimize over unsupervised objectives such as the entropy of model predictions in TENT [Wang et al., 2021], but it is unclear what exactly makes a good TTA loss. In this paper, we start by presenting a surprising phenomenon: if we attempt to meta-learn the best possible TTA loss over a wide class of functions, then we recover a function that is remarkably similar to (a temperature-scaled version of) the softmax-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09640","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/2207.09640/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":"2026-07-05T05:18:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r9t+GNQ6Yq4POdxbtZIZ8RJQBRDHlSPGq0WtsuvOXeYmk8PpJ3aC01cCpwHZ8WEd3mMZzO7nUjWah4IRVGhwCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:36:53.864242Z"},"content_sha256":"48b4eec2df0242109d777b79a193b6187702607f8d44dcb615def6b3a7b57496","schema_version":"1.0","event_id":"sha256:48b4eec2df0242109d777b79a193b6187702607f8d44dcb615def6b3a7b57496"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/67JQCB22U4P6KXH4PVX2RIRGSQ/bundle.json","state_url":"https://pith.science/pith/67JQCB22U4P6KXH4PVX2RIRGSQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/67JQCB22U4P6KXH4PVX2RIRGSQ/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":"2026-08-12T08:36:53Z","links":{"resolver":"https://pith.science/pith/67JQCB22U4P6KXH4PVX2RIRGSQ","bundle":"https://pith.science/pith/67JQCB22U4P6KXH4PVX2RIRGSQ/bundle.json","state":"https://pith.science/pith/67JQCB22U4P6KXH4PVX2RIRGSQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/67JQCB22U4P6KXH4PVX2RIRGSQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:67JQCB22U4P6KXH4PVX2RIRGSQ","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":"4bdddc2742a780ec2ddc8678739749cf0736aec6bfc86c067900cdfdea416a70","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T04:02:19Z","title_canon_sha256":"fb44417bd5ae3ae82644d745be6c7d22d480dc221164263fb53afa059ef783d1"},"schema_version":"1.0","source":{"id":"2207.09640","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.09640","created_at":"2026-07-05T05:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2207.09640v2","created_at":"2026-07-05T05:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09640","created_at":"2026-07-05T05:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"67JQCB22U4P6","created_at":"2026-07-05T05:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"67JQCB22U4P6KXH4","created_at":"2026-07-05T05:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"67JQCB22","created_at":"2026-07-05T05:18:47Z"}],"graph_snapshots":[{"event_id":"sha256:48b4eec2df0242109d777b79a193b6187702607f8d44dcb615def6b3a7b57496","target":"graph","created_at":"2026-07-05T05:18:47Z","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/2207.09640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Test-time adaptation (TTA) refers to adapting neural networks to distribution shifts, with access to only the unlabeled test samples from the new domain at test-time. Prior TTA methods optimize over unsupervised objectives such as the entropy of model predictions in TENT [Wang et al., 2021], but it is unclear what exactly makes a good TTA loss. In this paper, we start by presenting a surprising phenomenon: if we attempt to meta-learn the best possible TTA loss over a wide class of functions, then we recover a function that is remarkably similar to (a temperature-scaled version of) the softmax-","authors_text":"Aditi Raghunathan, Mingjie Sun, Sachin Goyal, Zico Kolter","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T04:02:19Z","title":"Test-Time Adaptation via Conjugate Pseudo-labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09640","kind":"arxiv","version":2},"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":"sha256:287b9f8ab99e3020f8da09f406564c86efb12859ddbc8559e6dd18befbfe8789","target":"record","created_at":"2026-07-05T05:18:47Z","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":"4bdddc2742a780ec2ddc8678739749cf0736aec6bfc86c067900cdfdea416a70","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T04:02:19Z","title_canon_sha256":"fb44417bd5ae3ae82644d745be6c7d22d480dc221164263fb53afa059ef783d1"},"schema_version":"1.0","source":{"id":"2207.09640","kind":"arxiv","version":2}},"canonical_sha256":"f7d301075aa71fe55cfc7d6fa8a22694392b9716d463f159e1b8fa563bc04217","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7d301075aa71fe55cfc7d6fa8a22694392b9716d463f159e1b8fa563bc04217","first_computed_at":"2026-07-05T05:18:47.710265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:18:47.710265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xB19fz0NcHdXn3QZKxSADYOUOrdhhJus/obkdBP2Bkr6HlfQ9W53m9s1pathV/WzaGZJWNccoUnL8YyV4rsjBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:18:47.710990Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.09640","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:287b9f8ab99e3020f8da09f406564c86efb12859ddbc8559e6dd18befbfe8789","sha256:48b4eec2df0242109d777b79a193b6187702607f8d44dcb615def6b3a7b57496"],"state_sha256":"8750e188923296503b51fbf21902a024aba4746c9f2bc65c0684efb8a4799afd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WVu7If+nVm1tAFieXhqm6xzur830pxToLp5TG+E7aGaDKv3Bro9HKlE2qXn8nf4KBMYWIvV2jrHXPRwGVC73Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T08:36:53.867741Z","bundle_sha256":"e427f0b13dac19b2c12ad85a81aae9425ff2fe0a8b9c8cedf021ba59c49eeb78"}}