{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:MRCRZOIGPH2RECRLWBLDDFN6ET","short_pith_number":"pith:MRCRZOIG","canonical_record":{"source":{"id":"2012.04550","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T16:43:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9e36ec86c943426c5de33fc0ac0b937998705a488a7c6b7349b7b7519ea2ae67","abstract_canon_sha256":"614b201678f6049960d9a288b2ed742d7dd1f4920e55c27484e6f7d5b66ad2ad"},"schema_version":"1.0"},"canonical_sha256":"64451cb90679f5120a2bb0563195be24d8dcbb2257b427b9ecccc719b3d9803c","source":{"kind":"arxiv","id":"2012.04550","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04550","created_at":"2026-07-05T02:30:08Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04550v3","created_at":"2026-07-05T02:30:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04550","created_at":"2026-07-05T02:30:08Z"},{"alias_kind":"pith_short_12","alias_value":"MRCRZOIGPH2R","created_at":"2026-07-05T02:30:08Z"},{"alias_kind":"pith_short_16","alias_value":"MRCRZOIGPH2RECRL","created_at":"2026-07-05T02:30:08Z"},{"alias_kind":"pith_short_8","alias_value":"MRCRZOIG","created_at":"2026-07-05T02:30:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:MRCRZOIGPH2RECRLWBLDDFN6ET","target":"record","payload":{"canonical_record":{"source":{"id":"2012.04550","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T16:43:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9e36ec86c943426c5de33fc0ac0b937998705a488a7c6b7349b7b7519ea2ae67","abstract_canon_sha256":"614b201678f6049960d9a288b2ed742d7dd1f4920e55c27484e6f7d5b66ad2ad"},"schema_version":"1.0"},"canonical_sha256":"64451cb90679f5120a2bb0563195be24d8dcbb2257b427b9ecccc719b3d9803c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:08.949306Z","signature_b64":"pN3JAeoigVA6Si/Mwvy95HUfSlzmyip/3JRtt5lcqAvNlDeMl4G4fNk0uwPlhskRmXWy6PfP535ADW/MbrTNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64451cb90679f5120a2bb0563195be24d8dcbb2257b427b9ecccc719b3d9803c","last_reissued_at":"2026-07-05T02:30:08.948831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:08.948831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.04550","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":"2026-07-05T02:30:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MYcSvLLkgNspBSIde43Wal0o0F2rgiLNr5qbEBIQrQz4cK2dJjatFn7AZkA/cDEpDJNj4QJRaGySEe58MHPUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T12:25:42.305544Z"},"content_sha256":"dee06dbb8633f5a76eba6137e09f4e58c5649b4785cf374446669d6815ad788d","schema_version":"1.0","event_id":"sha256:dee06dbb8633f5a76eba6137e09f4e58c5649b4785cf374446669d6815ad788d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:MRCRZOIGPH2RECRLWBLDDFN6ET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ananya Kumar, Fereshte Khani, Percy Liang, Robbie Jones, Sang Michael Xie, Tengyu Ma","submitted_at":"2020-12-08T16:43:07Z","abstract_excerpt":"Consider a prediction setting with few in-distribution labeled examples and many unlabeled examples both in- and out-of-distribution (OOD). The goal is to learn a model which performs well both in-distribution and OOD. In these settings, auxiliary information is often cheaply available for every input. How should we best leverage this auxiliary information for the prediction task? Empirically across three image and time-series datasets, and theoretically in a multi-task linear regression setting, we show that (i) using auxiliary information as input features improves in-distribution error but "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04550","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/2012.04550/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":"2026-07-05T02:30:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cRSYPnI4phgX376i483LS4ZXcZ7RnIprumzXlSH9W9DjZRvQk7Uv66PHqSS2rCiA8e0L1dF/OflyIqqypLePAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T12:25:42.305922Z"},"content_sha256":"d333caac24c5a6c9d8d186823db40e4b796bc70a777f8d7779d67f665f1dc0f8","schema_version":"1.0","event_id":"sha256:d333caac24c5a6c9d8d186823db40e4b796bc70a777f8d7779d67f665f1dc0f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MRCRZOIGPH2RECRLWBLDDFN6ET/bundle.json","state_url":"https://pith.science/pith/MRCRZOIGPH2RECRLWBLDDFN6ET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MRCRZOIGPH2RECRLWBLDDFN6ET/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":"2026-07-08T12:25:42Z","links":{"resolver":"https://pith.science/pith/MRCRZOIGPH2RECRLWBLDDFN6ET","bundle":"https://pith.science/pith/MRCRZOIGPH2RECRLWBLDDFN6ET/bundle.json","state":"https://pith.science/pith/MRCRZOIGPH2RECRLWBLDDFN6ET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MRCRZOIGPH2RECRLWBLDDFN6ET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MRCRZOIGPH2RECRLWBLDDFN6ET","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":"614b201678f6049960d9a288b2ed742d7dd1f4920e55c27484e6f7d5b66ad2ad","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T16:43:07Z","title_canon_sha256":"9e36ec86c943426c5de33fc0ac0b937998705a488a7c6b7349b7b7519ea2ae67"},"schema_version":"1.0","source":{"id":"2012.04550","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04550","created_at":"2026-07-05T02:30:08Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04550v3","created_at":"2026-07-05T02:30:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04550","created_at":"2026-07-05T02:30:08Z"},{"alias_kind":"pith_short_12","alias_value":"MRCRZOIGPH2R","created_at":"2026-07-05T02:30:08Z"},{"alias_kind":"pith_short_16","alias_value":"MRCRZOIGPH2RECRL","created_at":"2026-07-05T02:30:08Z"},{"alias_kind":"pith_short_8","alias_value":"MRCRZOIG","created_at":"2026-07-05T02:30:08Z"}],"graph_snapshots":[{"event_id":"sha256:d333caac24c5a6c9d8d186823db40e4b796bc70a777f8d7779d67f665f1dc0f8","target":"graph","created_at":"2026-07-05T02:30:08Z","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/2012.04550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consider a prediction setting with few in-distribution labeled examples and many unlabeled examples both in- and out-of-distribution (OOD). The goal is to learn a model which performs well both in-distribution and OOD. In these settings, auxiliary information is often cheaply available for every input. How should we best leverage this auxiliary information for the prediction task? Empirically across three image and time-series datasets, and theoretically in a multi-task linear regression setting, we show that (i) using auxiliary information as input features improves in-distribution error but ","authors_text":"Ananya Kumar, Fereshte Khani, Percy Liang, Robbie Jones, Sang Michael Xie, Tengyu Ma","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T16:43:07Z","title":"In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04550","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:dee06dbb8633f5a76eba6137e09f4e58c5649b4785cf374446669d6815ad788d","target":"record","created_at":"2026-07-05T02:30:08Z","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":"614b201678f6049960d9a288b2ed742d7dd1f4920e55c27484e6f7d5b66ad2ad","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T16:43:07Z","title_canon_sha256":"9e36ec86c943426c5de33fc0ac0b937998705a488a7c6b7349b7b7519ea2ae67"},"schema_version":"1.0","source":{"id":"2012.04550","kind":"arxiv","version":3}},"canonical_sha256":"64451cb90679f5120a2bb0563195be24d8dcbb2257b427b9ecccc719b3d9803c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64451cb90679f5120a2bb0563195be24d8dcbb2257b427b9ecccc719b3d9803c","first_computed_at":"2026-07-05T02:30:08.948831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:30:08.948831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pN3JAeoigVA6Si/Mwvy95HUfSlzmyip/3JRtt5lcqAvNlDeMl4G4fNk0uwPlhskRmXWy6PfP535ADW/MbrTNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:30:08.949306Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.04550","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dee06dbb8633f5a76eba6137e09f4e58c5649b4785cf374446669d6815ad788d","sha256:d333caac24c5a6c9d8d186823db40e4b796bc70a777f8d7779d67f665f1dc0f8"],"state_sha256":"e987a248ad99be92542356f45a0de3839a2885ef1cf49cf7d357e30662e0378d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xxt2/2JOumLIBw+s3cHWz0is2CGCao6cw92D0elmLJq1KFL8IHpffQpWyhtDTN5H683GTXrGCjZ7XuNmzlbKCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T12:25:42.308075Z","bundle_sha256":"8e6611fa236c432d5884380a5387a4654192fd68e1b4e06a6f0a50f2aea83e7c"}}