{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LFBIKO36NKZC7OQEJBUOMMIUTC","short_pith_number":"pith:LFBIKO36","canonical_record":{"source":{"id":"2004.14109","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T12:06:42Z","cross_cats_sorted":[],"title_canon_sha256":"c3d416961691b6037e6748916dc8f3cb936b7437b48df5a99a27a76ba9e48a12","abstract_canon_sha256":"5993fe8fdb3a6045f3cce0d5c258261e453bf49d20c1e8c80a198eefc6def035"},"schema_version":"1.0"},"canonical_sha256":"5942853b7e6ab22fba044868e6311498baacd0f22615d27edb1c37bdb2beec1f","source":{"kind":"arxiv","id":"2004.14109","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14109","created_at":"2026-07-05T01:41:18Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14109v2","created_at":"2026-07-05T01:41:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14109","created_at":"2026-07-05T01:41:18Z"},{"alias_kind":"pith_short_12","alias_value":"LFBIKO36NKZC","created_at":"2026-07-05T01:41:18Z"},{"alias_kind":"pith_short_16","alias_value":"LFBIKO36NKZC7OQE","created_at":"2026-07-05T01:41:18Z"},{"alias_kind":"pith_short_8","alias_value":"LFBIKO36","created_at":"2026-07-05T01:41:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LFBIKO36NKZC7OQEJBUOMMIUTC","target":"record","payload":{"canonical_record":{"source":{"id":"2004.14109","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T12:06:42Z","cross_cats_sorted":[],"title_canon_sha256":"c3d416961691b6037e6748916dc8f3cb936b7437b48df5a99a27a76ba9e48a12","abstract_canon_sha256":"5993fe8fdb3a6045f3cce0d5c258261e453bf49d20c1e8c80a198eefc6def035"},"schema_version":"1.0"},"canonical_sha256":"5942853b7e6ab22fba044868e6311498baacd0f22615d27edb1c37bdb2beec1f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:18.057194Z","signature_b64":"XcsJmA7VI77229IquJQUOEDCUbnHr1ICmzDV+ziyjjsX+1TYUeJmz+BYiy+IY+ohN2IYacoepeyyqOSTru5UCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5942853b7e6ab22fba044868e6311498baacd0f22615d27edb1c37bdb2beec1f","last_reissued_at":"2026-07-05T01:41:18.056689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:18.056689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.14109","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":"2026-07-05T01:41:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TigsSpmwKl0J3zTjB4Wuglmhg4OfHzpYx2QT1UjNgKLhU3pFqRouMqhfzeXiTqdI7gHekD50F8DQhqYKTfxHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:32:18.823311Z"},"content_sha256":"0607a39bc432b3d91bdda45aabb7837f3fb0739b638ab743ffa399ee5dc31679","schema_version":"1.0","event_id":"sha256:0607a39bc432b3d91bdda45aabb7837f3fb0739b638ab743ffa399ee5dc31679"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LFBIKO36NKZC7OQEJBUOMMIUTC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Subword Regularization for Robust Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jaewoo Kang, Jinhyuk Lee, Jungsoo Park, Mujeen Sung","submitted_at":"2020-04-29T12:06:42Z","abstract_excerpt":"Exposing diverse subword segmentations to neural machine translation (NMT) models often improves the robustness of machine translation as NMT models can experience various subword candidates. However, the diversification of subword segmentations mostly relies on the pre-trained subword language models from which erroneous segmentations of unseen words are less likely to be sampled. In this paper, we present adversarial subword regularization (ADVSR) to study whether gradient signals during training can be a substitute criterion for exposing diverse subword segmentations. We experimentally show"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14109","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/2004.14109/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":"2026-07-05T01:41:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hCODFTia+8OW/peNrQCYR1DFdEhrXDpNBaJbDqrUYxlPqMvXmIdFkuTfnah3ke7BJBwMgrO3FfFe0x84avMBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:32:18.823776Z"},"content_sha256":"314285b001ae124cb70d501ac4f42c8725cc4783d2b815eaa366cecf1946abd3","schema_version":"1.0","event_id":"sha256:314285b001ae124cb70d501ac4f42c8725cc4783d2b815eaa366cecf1946abd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LFBIKO36NKZC7OQEJBUOMMIUTC/bundle.json","state_url":"https://pith.science/pith/LFBIKO36NKZC7OQEJBUOMMIUTC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LFBIKO36NKZC7OQEJBUOMMIUTC/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":"2026-08-05T10:32:18Z","links":{"resolver":"https://pith.science/pith/LFBIKO36NKZC7OQEJBUOMMIUTC","bundle":"https://pith.science/pith/LFBIKO36NKZC7OQEJBUOMMIUTC/bundle.json","state":"https://pith.science/pith/LFBIKO36NKZC7OQEJBUOMMIUTC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LFBIKO36NKZC7OQEJBUOMMIUTC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LFBIKO36NKZC7OQEJBUOMMIUTC","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":"5993fe8fdb3a6045f3cce0d5c258261e453bf49d20c1e8c80a198eefc6def035","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T12:06:42Z","title_canon_sha256":"c3d416961691b6037e6748916dc8f3cb936b7437b48df5a99a27a76ba9e48a12"},"schema_version":"1.0","source":{"id":"2004.14109","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14109","created_at":"2026-07-05T01:41:18Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14109v2","created_at":"2026-07-05T01:41:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14109","created_at":"2026-07-05T01:41:18Z"},{"alias_kind":"pith_short_12","alias_value":"LFBIKO36NKZC","created_at":"2026-07-05T01:41:18Z"},{"alias_kind":"pith_short_16","alias_value":"LFBIKO36NKZC7OQE","created_at":"2026-07-05T01:41:18Z"},{"alias_kind":"pith_short_8","alias_value":"LFBIKO36","created_at":"2026-07-05T01:41:18Z"}],"graph_snapshots":[{"event_id":"sha256:314285b001ae124cb70d501ac4f42c8725cc4783d2b815eaa366cecf1946abd3","target":"graph","created_at":"2026-07-05T01:41:18Z","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/2004.14109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exposing diverse subword segmentations to neural machine translation (NMT) models often improves the robustness of machine translation as NMT models can experience various subword candidates. However, the diversification of subword segmentations mostly relies on the pre-trained subword language models from which erroneous segmentations of unseen words are less likely to be sampled. In this paper, we present adversarial subword regularization (ADVSR) to study whether gradient signals during training can be a substitute criterion for exposing diverse subword segmentations. We experimentally show","authors_text":"Jaewoo Kang, Jinhyuk Lee, Jungsoo Park, Mujeen Sung","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T12:06:42Z","title":"Adversarial Subword Regularization for Robust Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14109","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":"sha256:0607a39bc432b3d91bdda45aabb7837f3fb0739b638ab743ffa399ee5dc31679","target":"record","created_at":"2026-07-05T01:41:18Z","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":"5993fe8fdb3a6045f3cce0d5c258261e453bf49d20c1e8c80a198eefc6def035","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T12:06:42Z","title_canon_sha256":"c3d416961691b6037e6748916dc8f3cb936b7437b48df5a99a27a76ba9e48a12"},"schema_version":"1.0","source":{"id":"2004.14109","kind":"arxiv","version":2}},"canonical_sha256":"5942853b7e6ab22fba044868e6311498baacd0f22615d27edb1c37bdb2beec1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5942853b7e6ab22fba044868e6311498baacd0f22615d27edb1c37bdb2beec1f","first_computed_at":"2026-07-05T01:41:18.056689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:18.056689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XcsJmA7VI77229IquJQUOEDCUbnHr1ICmzDV+ziyjjsX+1TYUeJmz+BYiy+IY+ohN2IYacoepeyyqOSTru5UCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:18.057194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14109","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0607a39bc432b3d91bdda45aabb7837f3fb0739b638ab743ffa399ee5dc31679","sha256:314285b001ae124cb70d501ac4f42c8725cc4783d2b815eaa366cecf1946abd3"],"state_sha256":"19ddaf864587179440ad8eec972da47f3580b36a7175aa3d125ac96527fc46d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a7/NLO5pSMTG8IcOkZAgDGEAIBmSxm2GZ6pT8MBA4x3QGfGdiOwe21HdrHyQ5u6td4gRHG7+wxqRMKRk/f5kDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:32:18.828116Z","bundle_sha256":"763592b7daab16dae9fcb70ef838e6ad011e4b40d269bf5bf9fac829a65ffb22"}}