{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LAM3G2AVOMBXYFTNXAZLVM7XS5","short_pith_number":"pith:LAM3G2AV","canonical_record":{"source":{"id":"2201.04234","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-11T23:01:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fb4cbc19c827bddb059fcaab7a70a67c98332b829f4b251a67320c7edacfefb3","abstract_canon_sha256":"651ec98a618fd75d7aa95aec887dbe3f7fbcad0273c5d2f77cf7835f858c8ad4"},"schema_version":"1.0"},"canonical_sha256":"5819b3681573037c166db832bab3f7976746216ac5ef01d54cbc31b1799ecc63","source":{"kind":"arxiv","id":"2201.04234","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.04234","created_at":"2026-07-05T05:06:54Z"},{"alias_kind":"arxiv_version","alias_value":"2201.04234v3","created_at":"2026-07-05T05:06:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04234","created_at":"2026-07-05T05:06:54Z"},{"alias_kind":"pith_short_12","alias_value":"LAM3G2AVOMBX","created_at":"2026-07-05T05:06:54Z"},{"alias_kind":"pith_short_16","alias_value":"LAM3G2AVOMBXYFTN","created_at":"2026-07-05T05:06:54Z"},{"alias_kind":"pith_short_8","alias_value":"LAM3G2AV","created_at":"2026-07-05T05:06:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LAM3G2AVOMBXYFTNXAZLVM7XS5","target":"record","payload":{"canonical_record":{"source":{"id":"2201.04234","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-11T23:01:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fb4cbc19c827bddb059fcaab7a70a67c98332b829f4b251a67320c7edacfefb3","abstract_canon_sha256":"651ec98a618fd75d7aa95aec887dbe3f7fbcad0273c5d2f77cf7835f858c8ad4"},"schema_version":"1.0"},"canonical_sha256":"5819b3681573037c166db832bab3f7976746216ac5ef01d54cbc31b1799ecc63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:54.208873Z","signature_b64":"PjX60Mp96FtLWa8s/aaZsRR68zmWR8DNKHnlPc2eBr4shDQwoLDyz0heMQMU5DiBEiCO5NTo1ES6RbHP3GgrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5819b3681573037c166db832bab3f7976746216ac5ef01d54cbc31b1799ecc63","last_reissued_at":"2026-07-05T05:06:54.208333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:54.208333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.04234","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":"2026-07-05T05:06:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B69QEwNZehD2cA6mRuVbXFbwRlUJdC69X/AbWdTT6vq0wTA4Ni0LDpn5+wZmPpi4hs9OLmKI/pw6qouzAEAPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:16:23.954734Z"},"content_sha256":"18f8b6d4171ea01ef831f0c7c8b5d03d7b3fdff8a73823d9affc859c75a1233d","schema_version":"1.0","event_id":"sha256:18f8b6d4171ea01ef831f0c7c8b5d03d7b3fdff8a73823d9affc859c75a1233d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LAM3G2AVOMBXYFTNXAZLVM7XS5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Behnam Neyshabur, Hanie Sedghi, Saurabh Garg, Sivaraman Balakrishnan, Zachary C. Lipton","submitted_at":"2022-01-11T23:01:12Z","abstract_excerpt":"Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions that may cause performance drops. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples for which model confidence exceeds that threshold. ATC outperforms previous methods across several model architectures"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04234","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/2201.04234/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":"2026-07-05T05:06:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Z0AhZ/FnCm1AcsmOdWFy1BhcxOGFkeyTSIZFKfDhayhgJTFCIJ00xNfP9TyAb9GmPkLcxc0f9iEWwBUJu0eBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:16:23.955272Z"},"content_sha256":"c1fae3e51738fe69d2e9e3332c9ad02ea98308c04fc78658cc110585aaa7f350","schema_version":"1.0","event_id":"sha256:c1fae3e51738fe69d2e9e3332c9ad02ea98308c04fc78658cc110585aaa7f350"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LAM3G2AVOMBXYFTNXAZLVM7XS5/bundle.json","state_url":"https://pith.science/pith/LAM3G2AVOMBXYFTNXAZLVM7XS5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LAM3G2AVOMBXYFTNXAZLVM7XS5/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":"2026-08-08T13:16:23Z","links":{"resolver":"https://pith.science/pith/LAM3G2AVOMBXYFTNXAZLVM7XS5","bundle":"https://pith.science/pith/LAM3G2AVOMBXYFTNXAZLVM7XS5/bundle.json","state":"https://pith.science/pith/LAM3G2AVOMBXYFTNXAZLVM7XS5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LAM3G2AVOMBXYFTNXAZLVM7XS5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LAM3G2AVOMBXYFTNXAZLVM7XS5","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":"651ec98a618fd75d7aa95aec887dbe3f7fbcad0273c5d2f77cf7835f858c8ad4","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-11T23:01:12Z","title_canon_sha256":"fb4cbc19c827bddb059fcaab7a70a67c98332b829f4b251a67320c7edacfefb3"},"schema_version":"1.0","source":{"id":"2201.04234","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.04234","created_at":"2026-07-05T05:06:54Z"},{"alias_kind":"arxiv_version","alias_value":"2201.04234v3","created_at":"2026-07-05T05:06:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04234","created_at":"2026-07-05T05:06:54Z"},{"alias_kind":"pith_short_12","alias_value":"LAM3G2AVOMBX","created_at":"2026-07-05T05:06:54Z"},{"alias_kind":"pith_short_16","alias_value":"LAM3G2AVOMBXYFTN","created_at":"2026-07-05T05:06:54Z"},{"alias_kind":"pith_short_8","alias_value":"LAM3G2AV","created_at":"2026-07-05T05:06:54Z"}],"graph_snapshots":[{"event_id":"sha256:c1fae3e51738fe69d2e9e3332c9ad02ea98308c04fc78658cc110585aaa7f350","target":"graph","created_at":"2026-07-05T05:06:54Z","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/2201.04234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions that may cause performance drops. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples for which model confidence exceeds that threshold. ATC outperforms previous methods across several model architectures","authors_text":"Behnam Neyshabur, Hanie Sedghi, Saurabh Garg, Sivaraman Balakrishnan, Zachary C. Lipton","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-11T23:01:12Z","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04234","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":"sha256:18f8b6d4171ea01ef831f0c7c8b5d03d7b3fdff8a73823d9affc859c75a1233d","target":"record","created_at":"2026-07-05T05:06:54Z","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":"651ec98a618fd75d7aa95aec887dbe3f7fbcad0273c5d2f77cf7835f858c8ad4","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-11T23:01:12Z","title_canon_sha256":"fb4cbc19c827bddb059fcaab7a70a67c98332b829f4b251a67320c7edacfefb3"},"schema_version":"1.0","source":{"id":"2201.04234","kind":"arxiv","version":3}},"canonical_sha256":"5819b3681573037c166db832bab3f7976746216ac5ef01d54cbc31b1799ecc63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5819b3681573037c166db832bab3f7976746216ac5ef01d54cbc31b1799ecc63","first_computed_at":"2026-07-05T05:06:54.208333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:54.208333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PjX60Mp96FtLWa8s/aaZsRR68zmWR8DNKHnlPc2eBr4shDQwoLDyz0heMQMU5DiBEiCO5NTo1ES6RbHP3GgrAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:54.208873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.04234","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18f8b6d4171ea01ef831f0c7c8b5d03d7b3fdff8a73823d9affc859c75a1233d","sha256:c1fae3e51738fe69d2e9e3332c9ad02ea98308c04fc78658cc110585aaa7f350"],"state_sha256":"bed60445218659b83bf2beddc047a2657a069af4a2178fbc4fb35bd006723601"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k4FCB8QJ9M7NA62m4Dd7jSq1VNpQkTZlegLs89vIQhiNuvxR/waTHqGldLb8rZSzKi2Pu0KlxeyzKsn6FWVsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:16:23.959980Z","bundle_sha256":"6d46569b76d5957e63b275acedbbb0c2bb1f5f26f6abf80b7724c90f9743decc"}}