{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:J3LSCGR5BZI2TAL235RCC2SHNC","short_pith_number":"pith:J3LSCGR5","canonical_record":{"source":{"id":"2310.00840","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-02T01:30:27Z","cross_cats_sorted":[],"title_canon_sha256":"b09cce8a93bde1134d3cafceb51cf3055a66613af2f322641e1be0c6d97dc409","abstract_canon_sha256":"e470883c721cb3fb94137b70e7dc6d5917c7ae42a4bc22c84d7a5517f663493f"},"schema_version":"1.0"},"canonical_sha256":"4ed7211a3d0e51a9817adf62216a4768a877064b94242dd7a133ab33caef9edd","source":{"kind":"arxiv","id":"2310.00840","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00840","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00840v2","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00840","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"pith_short_12","alias_value":"J3LSCGR5BZI2","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"pith_short_16","alias_value":"J3LSCGR5BZI2TAL2","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"pith_short_8","alias_value":"J3LSCGR5","created_at":"2026-07-05T07:57:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:J3LSCGR5BZI2TAL235RCC2SHNC","target":"record","payload":{"canonical_record":{"source":{"id":"2310.00840","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-02T01:30:27Z","cross_cats_sorted":[],"title_canon_sha256":"b09cce8a93bde1134d3cafceb51cf3055a66613af2f322641e1be0c6d97dc409","abstract_canon_sha256":"e470883c721cb3fb94137b70e7dc6d5917c7ae42a4bc22c84d7a5517f663493f"},"schema_version":"1.0"},"canonical_sha256":"4ed7211a3d0e51a9817adf62216a4768a877064b94242dd7a133ab33caef9edd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:44.223431Z","signature_b64":"WR4qSTMyS6E9t0TUzgDZHy07ar9zgTGLVdxRRztxOUtbYCbc4yMdHYzrMhx39wsYKglvk7HmF9iS+gU9mJdpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ed7211a3d0e51a9817adf62216a4768a877064b94242dd7a133ab33caef9edd","last_reissued_at":"2026-07-05T07:57:44.222923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:44.222923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.00840","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":"2026-07-05T07:57:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3T83T/YERZK6Eg2mhrFYY4Z24XUQAUgIYqPFSOwRSfffQZaphojaU5QgSClUU6OxaXjnpdULIvfnwnxxkzXDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:56:49.083462Z"},"content_sha256":"dcd57b7a6aa0dc7be771d1d4aeebaa757399fd5c3961e9c023064ae78d81d41a","schema_version":"1.0","event_id":"sha256:dcd57b7a6aa0dc7be771d1d4aeebaa757399fd5c3961e9c023064ae78d81d41a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:J3LSCGR5BZI2TAL235RCC2SHNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Khashabi, Haoran Xu, Kenton Murray, Philipp Koehn, Tianjian Li","submitted_at":"2023-10-02T01:30:27Z","abstract_excerpt":"Text generation models are notoriously vulnerable to errors in the training data. With the wide-spread availability of massive amounts of web-crawled data becoming more commonplace, how can we enhance the robustness of models trained on a massive amount of noisy web-crawled text? In our work, we propose Error Norm Truncation (ENT), a robust enhancement method to the standard training objective that truncates noisy data. Compared to methods that only uses the negative log-likelihood loss to estimate data quality, our method provides a more accurate estimation by considering the distribution of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00840","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/2310.00840/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":"2026-07-05T07:57:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2tdm+dCL2fn/YNjmb6PxvC4FKRo0D5KSoMtOMolD8kvjhd0VOwDSs7YoKMchDbVOtVKa3tmbw+C+AZEqdD3QCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:56:49.083834Z"},"content_sha256":"7f5f1e005e3062e877803fd0a7580f404a84e9537c5fb9339a1c9b16cf096c32","schema_version":"1.0","event_id":"sha256:7f5f1e005e3062e877803fd0a7580f404a84e9537c5fb9339a1c9b16cf096c32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J3LSCGR5BZI2TAL235RCC2SHNC/bundle.json","state_url":"https://pith.science/pith/J3LSCGR5BZI2TAL235RCC2SHNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J3LSCGR5BZI2TAL235RCC2SHNC/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":"2026-07-09T03:56:49Z","links":{"resolver":"https://pith.science/pith/J3LSCGR5BZI2TAL235RCC2SHNC","bundle":"https://pith.science/pith/J3LSCGR5BZI2TAL235RCC2SHNC/bundle.json","state":"https://pith.science/pith/J3LSCGR5BZI2TAL235RCC2SHNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J3LSCGR5BZI2TAL235RCC2SHNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J3LSCGR5BZI2TAL235RCC2SHNC","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":"e470883c721cb3fb94137b70e7dc6d5917c7ae42a4bc22c84d7a5517f663493f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-02T01:30:27Z","title_canon_sha256":"b09cce8a93bde1134d3cafceb51cf3055a66613af2f322641e1be0c6d97dc409"},"schema_version":"1.0","source":{"id":"2310.00840","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00840","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00840v2","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00840","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"pith_short_12","alias_value":"J3LSCGR5BZI2","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"pith_short_16","alias_value":"J3LSCGR5BZI2TAL2","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"pith_short_8","alias_value":"J3LSCGR5","created_at":"2026-07-05T07:57:44Z"}],"graph_snapshots":[{"event_id":"sha256:7f5f1e005e3062e877803fd0a7580f404a84e9537c5fb9339a1c9b16cf096c32","target":"graph","created_at":"2026-07-05T07:57:44Z","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/2310.00840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text generation models are notoriously vulnerable to errors in the training data. With the wide-spread availability of massive amounts of web-crawled data becoming more commonplace, how can we enhance the robustness of models trained on a massive amount of noisy web-crawled text? In our work, we propose Error Norm Truncation (ENT), a robust enhancement method to the standard training objective that truncates noisy data. Compared to methods that only uses the negative log-likelihood loss to estimate data quality, our method provides a more accurate estimation by considering the distribution of ","authors_text":"Daniel Khashabi, Haoran Xu, Kenton Murray, Philipp Koehn, Tianjian Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-02T01:30:27Z","title":"Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00840","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:dcd57b7a6aa0dc7be771d1d4aeebaa757399fd5c3961e9c023064ae78d81d41a","target":"record","created_at":"2026-07-05T07:57:44Z","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":"e470883c721cb3fb94137b70e7dc6d5917c7ae42a4bc22c84d7a5517f663493f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-02T01:30:27Z","title_canon_sha256":"b09cce8a93bde1134d3cafceb51cf3055a66613af2f322641e1be0c6d97dc409"},"schema_version":"1.0","source":{"id":"2310.00840","kind":"arxiv","version":2}},"canonical_sha256":"4ed7211a3d0e51a9817adf62216a4768a877064b94242dd7a133ab33caef9edd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ed7211a3d0e51a9817adf62216a4768a877064b94242dd7a133ab33caef9edd","first_computed_at":"2026-07-05T07:57:44.222923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:44.222923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WR4qSTMyS6E9t0TUzgDZHy07ar9zgTGLVdxRRztxOUtbYCbc4yMdHYzrMhx39wsYKglvk7HmF9iS+gU9mJdpDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:44.223431Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00840","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcd57b7a6aa0dc7be771d1d4aeebaa757399fd5c3961e9c023064ae78d81d41a","sha256:7f5f1e005e3062e877803fd0a7580f404a84e9537c5fb9339a1c9b16cf096c32"],"state_sha256":"b6d7ead33341f142e26b7d3416c773971c643cae05183b9b4c7262d7d9c839bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BNx/9H0oegoR4i/lx6vVZjAojRXXVJDSLZ6tSdiIKQF/LepCA87ov0pOjb/bkZEci/7LSczNiffM/goxzrTRBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:56:49.085775Z","bundle_sha256":"823a5cb277ee7be088c0338d8238875de67f77c43ad67efe593b1de409a5670b"}}