{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RLKKXGDLR2J4J5MF3EANDTOB75","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":"878d19ced14a1847b221373381539be162a436d3ffb8bf327627d3aae3a3e0ec","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T19:07:33Z","title_canon_sha256":"d33a61fcae38e28546fca4eb63fd1788371b8abade19da63d76c0690572de4c0"},"schema_version":"1.0","source":{"id":"1909.02060","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02060","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02060v1","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02060","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"RLKKXGDLR2J4","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"pith_short_16","alias_value":"RLKKXGDLR2J4J5MF","created_at":"2026-07-05T00:02:29Z"},{"alias_kind":"pith_short_8","alias_value":"RLKKXGDL","created_at":"2026-07-05T00:02:29Z"}],"graph_snapshots":[{"event_id":"sha256:47ab8c58fe15b635fb26b899eedd778ed4e41d6fe4b084351c6ea69e74640ab6","target":"graph","created_at":"2026-07-05T00:02:29Z","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/1909.02060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models are generally trained on data spanning a wide range of topics (e.g., news, reviews, fiction), but they might be applied to an a priori unknown target distribution (e.g., restaurant reviews). In this paper, we first show that training on text outside the test distribution can degrade test performance when using standard maximum likelihood (MLE) training. To remedy this without the knowledge of the test distribution, we propose an approach which trains a model that performs well over a wide range of potential test distributions. In particular, we derive a new distributionally rob","authors_text":"Percy Liang, Shiori Sagawa, Tatsunori B. Hashimoto, Yonatan Oren","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T19:07:33Z","title":"Distributionally Robust Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02060","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:e5e3f09700ccb6c124b5fc0b616d5025da76f6147d1c09c72191f28a4bd31a86","target":"record","created_at":"2026-07-05T00:02:29Z","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":"878d19ced14a1847b221373381539be162a436d3ffb8bf327627d3aae3a3e0ec","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T19:07:33Z","title_canon_sha256":"d33a61fcae38e28546fca4eb63fd1788371b8abade19da63d76c0690572de4c0"},"schema_version":"1.0","source":{"id":"1909.02060","kind":"arxiv","version":1}},"canonical_sha256":"8ad4ab986b8e93c4f585d900d1cdc1ff7d6e3351a1d90eaba69a4221df69a7a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ad4ab986b8e93c4f585d900d1cdc1ff7d6e3351a1d90eaba69a4221df69a7a5","first_computed_at":"2026-07-05T00:02:29.883916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:29.883916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P4lUYLXBfrJYKuL+ZYdnqNkQ255aWtrMW1VshpB4FXXJD5J/oUIX134vAmc6Es/wJnXz9R7tMxXR/7w3TQC4Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:29.884379Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.02060","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5e3f09700ccb6c124b5fc0b616d5025da76f6147d1c09c72191f28a4bd31a86","sha256:47ab8c58fe15b635fb26b899eedd778ed4e41d6fe4b084351c6ea69e74640ab6"],"state_sha256":"bff2755c2bd07ecd15aed1cfa53a5e08bcec8fbdd14eaa08e1ae162b55424935"}