{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZHGVGSYVNFDE5BWFBQY53OJLXP","short_pith_number":"pith:ZHGVGSYV","canonical_record":{"source":{"id":"2204.06340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-13T12:43:12Z","cross_cats_sorted":[],"title_canon_sha256":"40a74725a582495919056457ccdd589e823167fca7beb29e1b1eb0e701fff79b","abstract_canon_sha256":"b996573fedb4c6e6b2e663f6a7d3c37489a2593fda5bb226173de4d41ec2caa1"},"schema_version":"1.0"},"canonical_sha256":"c9cd534b1569464e86c50c31ddb92bbbfba7e21535c84db23913d7c4b816c050","source":{"kind":"arxiv","id":"2204.06340","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.06340","created_at":"2026-07-05T04:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2204.06340v1","created_at":"2026-07-05T04:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06340","created_at":"2026-07-05T04:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZHGVGSYVNFDE","created_at":"2026-07-05T04:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"ZHGVGSYVNFDE5BWF","created_at":"2026-07-05T04:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"ZHGVGSYV","created_at":"2026-07-05T04:14:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZHGVGSYVNFDE5BWFBQY53OJLXP","target":"record","payload":{"canonical_record":{"source":{"id":"2204.06340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-13T12:43:12Z","cross_cats_sorted":[],"title_canon_sha256":"40a74725a582495919056457ccdd589e823167fca7beb29e1b1eb0e701fff79b","abstract_canon_sha256":"b996573fedb4c6e6b2e663f6a7d3c37489a2593fda5bb226173de4d41ec2caa1"},"schema_version":"1.0"},"canonical_sha256":"c9cd534b1569464e86c50c31ddb92bbbfba7e21535c84db23913d7c4b816c050","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:32.839389Z","signature_b64":"//k2g7VrAUF0IJ1Xg+reJhsJJJCCHCDGkR9GLK63RPIZhgOYaU8U5wVp0Zg3imVyZkHrKImhScAZUhx8B2WMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9cd534b1569464e86c50c31ddb92bbbfba7e21535c84db23913d7c4b816c050","last_reissued_at":"2026-07-05T04:14:32.839001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:32.839001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.06340","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:14:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"purFIo7RI4h6F5tLYf79dbofqDgO35pqxCIZ82bDKiGnuH8FX6em81YQ/gW6nNujQuIYmNCk9CZ5gQ6YBI6gCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T02:57:51.335438Z"},"content_sha256":"e92530ce3c0659c4a6425560ace70a3c030c49c9cf6e2ba420d7384c669a6eab","schema_version":"1.0","event_id":"sha256:e92530ce3c0659c4a6425560ace70a3c030c49c9cf6e2ba420d7384c669a6eab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZHGVGSYVNFDE5BWFBQY53OJLXP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributionally Robust Models with Parametric Likelihood Ratios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Graham Neubig, Paul Michel, Tatsunori Hashimoto","submitted_at":"2022-04-13T12:43:12Z","abstract_excerpt":"As machine learning models are deployed ever more broadly, it becomes increasingly important that they are not only able to perform well on their training distribution, but also yield accurate predictions when confronted with distribution shift. The Distributionally Robust Optimization (DRO) framework proposes to address this issue by training models to minimize their expected risk under a collection of distributions, to imitate test-time shifts. This is most commonly achieved by instance-level re-weighting of the training objective to emulate the likelihood ratio with possible test distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06340","kind":"arxiv","version":1},"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/2204.06340/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":"2026-07-05T04:14:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s3D6Eek8FVak9/frFGh+qJ57zMxOkO99wzARnx/XQ/lLklgTJo+uRS//mRIOkeGA+yIVHak+xP4UaagfEw1UCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T02:57:51.336248Z"},"content_sha256":"113ccd5e788ffb3eeb98ed8ee44b496609b3dceb2dc1a4e619294bcdea995276","schema_version":"1.0","event_id":"sha256:113ccd5e788ffb3eeb98ed8ee44b496609b3dceb2dc1a4e619294bcdea995276"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZHGVGSYVNFDE5BWFBQY53OJLXP/bundle.json","state_url":"https://pith.science/pith/ZHGVGSYVNFDE5BWFBQY53OJLXP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZHGVGSYVNFDE5BWFBQY53OJLXP/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":"2026-08-14T02:57:51Z","links":{"resolver":"https://pith.science/pith/ZHGVGSYVNFDE5BWFBQY53OJLXP","bundle":"https://pith.science/pith/ZHGVGSYVNFDE5BWFBQY53OJLXP/bundle.json","state":"https://pith.science/pith/ZHGVGSYVNFDE5BWFBQY53OJLXP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZHGVGSYVNFDE5BWFBQY53OJLXP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZHGVGSYVNFDE5BWFBQY53OJLXP","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":"b996573fedb4c6e6b2e663f6a7d3c37489a2593fda5bb226173de4d41ec2caa1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-13T12:43:12Z","title_canon_sha256":"40a74725a582495919056457ccdd589e823167fca7beb29e1b1eb0e701fff79b"},"schema_version":"1.0","source":{"id":"2204.06340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.06340","created_at":"2026-07-05T04:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2204.06340v1","created_at":"2026-07-05T04:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06340","created_at":"2026-07-05T04:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZHGVGSYVNFDE","created_at":"2026-07-05T04:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"ZHGVGSYVNFDE5BWF","created_at":"2026-07-05T04:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"ZHGVGSYV","created_at":"2026-07-05T04:14:32Z"}],"graph_snapshots":[{"event_id":"sha256:113ccd5e788ffb3eeb98ed8ee44b496609b3dceb2dc1a4e619294bcdea995276","target":"graph","created_at":"2026-07-05T04:14:32Z","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/2204.06340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As machine learning models are deployed ever more broadly, it becomes increasingly important that they are not only able to perform well on their training distribution, but also yield accurate predictions when confronted with distribution shift. The Distributionally Robust Optimization (DRO) framework proposes to address this issue by training models to minimize their expected risk under a collection of distributions, to imitate test-time shifts. This is most commonly achieved by instance-level re-weighting of the training objective to emulate the likelihood ratio with possible test distributi","authors_text":"Graham Neubig, Paul Michel, Tatsunori Hashimoto","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-13T12:43:12Z","title":"Distributionally Robust Models with Parametric Likelihood Ratios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06340","kind":"arxiv","version":1},"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:e92530ce3c0659c4a6425560ace70a3c030c49c9cf6e2ba420d7384c669a6eab","target":"record","created_at":"2026-07-05T04:14:32Z","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":"b996573fedb4c6e6b2e663f6a7d3c37489a2593fda5bb226173de4d41ec2caa1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-13T12:43:12Z","title_canon_sha256":"40a74725a582495919056457ccdd589e823167fca7beb29e1b1eb0e701fff79b"},"schema_version":"1.0","source":{"id":"2204.06340","kind":"arxiv","version":1}},"canonical_sha256":"c9cd534b1569464e86c50c31ddb92bbbfba7e21535c84db23913d7c4b816c050","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9cd534b1569464e86c50c31ddb92bbbfba7e21535c84db23913d7c4b816c050","first_computed_at":"2026-07-05T04:14:32.839001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:32.839001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"//k2g7VrAUF0IJ1Xg+reJhsJJJCCHCDGkR9GLK63RPIZhgOYaU8U5wVp0Zg3imVyZkHrKImhScAZUhx8B2WMDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:32.839389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.06340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e92530ce3c0659c4a6425560ace70a3c030c49c9cf6e2ba420d7384c669a6eab","sha256:113ccd5e788ffb3eeb98ed8ee44b496609b3dceb2dc1a4e619294bcdea995276"],"state_sha256":"bfe81799cd9879581c4aa01d92b23ce96c4722c7f9f76e1dd74a3d2b031d9a28"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eHrVvA7BO9sGftcd6kMLm03kSgiaOiYBuWTMmv3+J3lPzfZoslB4cgk00A7DdEacwWG5heAmac14XhJx5OqLCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T02:57:51.342176Z","bundle_sha256":"21df99c48e208097d27cdbf7b6dc1ba0077bfc09c53fb96378fb03ae3465d740"}}