{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:BGUVGWSCEOGVSOFQOX7ZS4QKJW","short_pith_number":"pith:BGUVGWSC","canonical_record":{"source":{"id":"2202.05797","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-11T17:46:24Z","cross_cats_sorted":[],"title_canon_sha256":"6804dfc82994c220539edd7e33d91f01174aa05da4a7f738d8b874bbd6ba584b","abstract_canon_sha256":"d6346b712d8939b626e3e5f7d22b90ca3ab6098c732a09ed4a76cd97abd67839"},"schema_version":"1.0"},"canonical_sha256":"09a9535a42238d5938b075ff99720a4db8839a6c7180b0cc079f4715c767be0d","source":{"kind":"arxiv","id":"2202.05797","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.05797","created_at":"2026-07-05T06:20:34Z"},{"alias_kind":"arxiv_version","alias_value":"2202.05797v2","created_at":"2026-07-05T06:20:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.05797","created_at":"2026-07-05T06:20:34Z"},{"alias_kind":"pith_short_12","alias_value":"BGUVGWSCEOGV","created_at":"2026-07-05T06:20:34Z"},{"alias_kind":"pith_short_16","alias_value":"BGUVGWSCEOGVSOFQ","created_at":"2026-07-05T06:20:34Z"},{"alias_kind":"pith_short_8","alias_value":"BGUVGWSC","created_at":"2026-07-05T06:20:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:BGUVGWSCEOGVSOFQOX7ZS4QKJW","target":"record","payload":{"canonical_record":{"source":{"id":"2202.05797","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-11T17:46:24Z","cross_cats_sorted":[],"title_canon_sha256":"6804dfc82994c220539edd7e33d91f01174aa05da4a7f738d8b874bbd6ba584b","abstract_canon_sha256":"d6346b712d8939b626e3e5f7d22b90ca3ab6098c732a09ed4a76cd97abd67839"},"schema_version":"1.0"},"canonical_sha256":"09a9535a42238d5938b075ff99720a4db8839a6c7180b0cc079f4715c767be0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:34.421146Z","signature_b64":"K4shANYdAjjeI6waeGCz1bzxLhRXkz6AUFU6zCtw577akAtWGtoR6q/A33gokXzwwIracYTcBXuAXMM1HXjDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09a9535a42238d5938b075ff99720a4db8839a6c7180b0cc079f4715c767be0d","last_reissued_at":"2026-07-05T06:20:34.420655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:34.420655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.05797","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":"2026-07-05T06:20:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eDBYpLbK7eJDJDLOSHykiRr5eED4SZ4PxebDdc/osO5VJYCX5ecSVx3gnJWNl9nmbZxyltS1bAGOQ19P0LkEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:21:45.300271Z"},"content_sha256":"60fc246f2788ccb1d393929dba527c804a6be7d968d45ee0b428dfff8920d071","schema_version":"1.0","event_id":"sha256:60fc246f2788ccb1d393929dba527c804a6be7d968d45ee0b428dfff8920d071"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:BGUVGWSCEOGVSOFQOX7ZS4QKJW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributionally Robust Data Join","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christopher Jung, Jamie Morgenstern, Pranjal Awasthi","submitted_at":"2022-02-11T17:46:24Z","abstract_excerpt":"Suppose we are given two datasets: a labeled dataset and unlabeled dataset which also has additional auxiliary features not present in the first dataset. What is the most principled way to use these datasets together to construct a predictor?\n  The answer should depend upon whether these datasets are generated by the same or different distributions over their mutual feature sets, and how similar the test distribution will be to either of those distributions. In many applications, the two datasets will likely follow different distributions, but both may be close to the test distribution. We int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.05797","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/2202.05797/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":"2026-07-05T06:20:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XR96eLyI9j5dbprb9zG5jNeD8a50pS3yjXC9jFyxIVPJyE2EAGEuCbJNORqOCSBB7lzEkxtHrLdpHGvBu3t0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:21:45.300891Z"},"content_sha256":"1a01479cb89750f6ce20bf2c48c7a19bc7024f09267a09891f5f5f416b9c468a","schema_version":"1.0","event_id":"sha256:1a01479cb89750f6ce20bf2c48c7a19bc7024f09267a09891f5f5f416b9c468a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BGUVGWSCEOGVSOFQOX7ZS4QKJW/bundle.json","state_url":"https://pith.science/pith/BGUVGWSCEOGVSOFQOX7ZS4QKJW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BGUVGWSCEOGVSOFQOX7ZS4QKJW/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":"2026-07-31T17:21:45Z","links":{"resolver":"https://pith.science/pith/BGUVGWSCEOGVSOFQOX7ZS4QKJW","bundle":"https://pith.science/pith/BGUVGWSCEOGVSOFQOX7ZS4QKJW/bundle.json","state":"https://pith.science/pith/BGUVGWSCEOGVSOFQOX7ZS4QKJW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BGUVGWSCEOGVSOFQOX7ZS4QKJW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BGUVGWSCEOGVSOFQOX7ZS4QKJW","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":"d6346b712d8939b626e3e5f7d22b90ca3ab6098c732a09ed4a76cd97abd67839","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-11T17:46:24Z","title_canon_sha256":"6804dfc82994c220539edd7e33d91f01174aa05da4a7f738d8b874bbd6ba584b"},"schema_version":"1.0","source":{"id":"2202.05797","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.05797","created_at":"2026-07-05T06:20:34Z"},{"alias_kind":"arxiv_version","alias_value":"2202.05797v2","created_at":"2026-07-05T06:20:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.05797","created_at":"2026-07-05T06:20:34Z"},{"alias_kind":"pith_short_12","alias_value":"BGUVGWSCEOGV","created_at":"2026-07-05T06:20:34Z"},{"alias_kind":"pith_short_16","alias_value":"BGUVGWSCEOGVSOFQ","created_at":"2026-07-05T06:20:34Z"},{"alias_kind":"pith_short_8","alias_value":"BGUVGWSC","created_at":"2026-07-05T06:20:34Z"}],"graph_snapshots":[{"event_id":"sha256:1a01479cb89750f6ce20bf2c48c7a19bc7024f09267a09891f5f5f416b9c468a","target":"graph","created_at":"2026-07-05T06:20:34Z","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/2202.05797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Suppose we are given two datasets: a labeled dataset and unlabeled dataset which also has additional auxiliary features not present in the first dataset. What is the most principled way to use these datasets together to construct a predictor?\n  The answer should depend upon whether these datasets are generated by the same or different distributions over their mutual feature sets, and how similar the test distribution will be to either of those distributions. In many applications, the two datasets will likely follow different distributions, but both may be close to the test distribution. We int","authors_text":"Christopher Jung, Jamie Morgenstern, Pranjal Awasthi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-11T17:46:24Z","title":"Distributionally Robust Data Join"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.05797","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":"sha256:60fc246f2788ccb1d393929dba527c804a6be7d968d45ee0b428dfff8920d071","target":"record","created_at":"2026-07-05T06:20:34Z","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":"d6346b712d8939b626e3e5f7d22b90ca3ab6098c732a09ed4a76cd97abd67839","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-11T17:46:24Z","title_canon_sha256":"6804dfc82994c220539edd7e33d91f01174aa05da4a7f738d8b874bbd6ba584b"},"schema_version":"1.0","source":{"id":"2202.05797","kind":"arxiv","version":2}},"canonical_sha256":"09a9535a42238d5938b075ff99720a4db8839a6c7180b0cc079f4715c767be0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09a9535a42238d5938b075ff99720a4db8839a6c7180b0cc079f4715c767be0d","first_computed_at":"2026-07-05T06:20:34.420655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:34.420655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K4shANYdAjjeI6waeGCz1bzxLhRXkz6AUFU6zCtw577akAtWGtoR6q/A33gokXzwwIracYTcBXuAXMM1HXjDAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:34.421146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.05797","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60fc246f2788ccb1d393929dba527c804a6be7d968d45ee0b428dfff8920d071","sha256:1a01479cb89750f6ce20bf2c48c7a19bc7024f09267a09891f5f5f416b9c468a"],"state_sha256":"8f96d464095eaa3fe394be29a900ab4f5a0d5d35b649915ca7d9917c50d09fac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/DnuHBjsCuVaGoxlQnfxqEj7H12gZarpdo+xOnth0gfA+i+hOxwhqVfoK2h40GpTzWPfTkbL30kl2T+zbaU/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T17:21:45.305805Z","bundle_sha256":"c5d6b20014a509c58eceebbaf7cad4514486a5ab7f6a80784f143b749c02f0d1"}}