{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TKJYEMGFUNTHSJUSM5WBUXXKJP","short_pith_number":"pith:TKJYEMGF","canonical_record":{"source":{"id":"2009.10195","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T22:02:33Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"80e6a6b2721111ca793759a5e44c165af2c82e5d448bf0dcac049425198a080c","abstract_canon_sha256":"204095daaaa84ba04bbe392139e71c07b23ff8c66d6a1964baa008187ed05582"},"schema_version":"1.0"},"canonical_sha256":"9a938230c5a366792692676c1a5eea4be0579f56614bad10dcfe028dad32514e","source":{"kind":"arxiv","id":"2009.10195","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10195","created_at":"2026-07-05T01:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10195v2","created_at":"2026-07-05T01:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10195","created_at":"2026-07-05T01:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"TKJYEMGFUNTH","created_at":"2026-07-05T01:40:01Z"},{"alias_kind":"pith_short_16","alias_value":"TKJYEMGFUNTHSJUS","created_at":"2026-07-05T01:40:01Z"},{"alias_kind":"pith_short_8","alias_value":"TKJYEMGF","created_at":"2026-07-05T01:40:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TKJYEMGFUNTHSJUSM5WBUXXKJP","target":"record","payload":{"canonical_record":{"source":{"id":"2009.10195","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T22:02:33Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"80e6a6b2721111ca793759a5e44c165af2c82e5d448bf0dcac049425198a080c","abstract_canon_sha256":"204095daaaa84ba04bbe392139e71c07b23ff8c66d6a1964baa008187ed05582"},"schema_version":"1.0"},"canonical_sha256":"9a938230c5a366792692676c1a5eea4be0579f56614bad10dcfe028dad32514e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:01.590672Z","signature_b64":"AlgSmJvH/wFZ3bHzYhroWCC6tVYSYrLB4D8Dlrxjf/n3b68wsFbAbDefYQULm78gNInDUm+Ny0ZwiFWFy8GMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a938230c5a366792692676c1a5eea4be0579f56614bad10dcfe028dad32514e","last_reissued_at":"2026-07-05T01:40:01.590197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:01.590197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.10195","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":"2026-07-05T01:40:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T773+klROQaPIsFGz+aFCoMjTcWwTRcaCMaYd2iA1bY6mtic437+qz4tWR78UoWZpAUYdpljEqtwy3vtLwxZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:57:27.047544Z"},"content_sha256":"c27a8b69dff07d598d48b5e5b7e80f1947c478c331ceea0d72f41caf71139556","schema_version":"1.0","event_id":"sha256:c27a8b69dff07d598d48b5e5b7e80f1947c478c331ceea0d72f41caf71139556"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TKJYEMGFUNTHSJUSM5WBUXXKJP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Kyunghyun Cho, Marzyeh Ghassemi, Nathan Ng","submitted_at":"2020-09-21T22:02:33Z","abstract_excerpt":"Models that perform well on a training domain often fail to generalize to out-of-domain (OOD) examples. Data augmentation is a common method used to prevent overfitting and improve OOD generalization. However, in natural language, it is difficult to generate new examples that stay on the underlying data manifold. We introduce SSMBA, a data augmentation method for generating synthetic training examples by using a pair of corruption and reconstruction functions to move randomly on a data manifold. We investigate the use of SSMBA in the natural language domain, leveraging the manifold assumption "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10195","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/2009.10195/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":"2026-07-05T01:40:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SXqLMce9yb5jD9KRvMcbGwC5Q7iZbpeFDQTM92fQtls7UgSQ6/LCWJIw2Znf6eT06363V2OO0PAc4FxcsbnEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:57:27.048089Z"},"content_sha256":"cbe5864f63469b3bffb4e2ed6af096f2a3f5c6e720aa2c412b93470c6454bce8","schema_version":"1.0","event_id":"sha256:cbe5864f63469b3bffb4e2ed6af096f2a3f5c6e720aa2c412b93470c6454bce8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TKJYEMGFUNTHSJUSM5WBUXXKJP/bundle.json","state_url":"https://pith.science/pith/TKJYEMGFUNTHSJUSM5WBUXXKJP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TKJYEMGFUNTHSJUSM5WBUXXKJP/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":"2026-08-04T04:57:27Z","links":{"resolver":"https://pith.science/pith/TKJYEMGFUNTHSJUSM5WBUXXKJP","bundle":"https://pith.science/pith/TKJYEMGFUNTHSJUSM5WBUXXKJP/bundle.json","state":"https://pith.science/pith/TKJYEMGFUNTHSJUSM5WBUXXKJP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TKJYEMGFUNTHSJUSM5WBUXXKJP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TKJYEMGFUNTHSJUSM5WBUXXKJP","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":"204095daaaa84ba04bbe392139e71c07b23ff8c66d6a1964baa008187ed05582","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T22:02:33Z","title_canon_sha256":"80e6a6b2721111ca793759a5e44c165af2c82e5d448bf0dcac049425198a080c"},"schema_version":"1.0","source":{"id":"2009.10195","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10195","created_at":"2026-07-05T01:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10195v2","created_at":"2026-07-05T01:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10195","created_at":"2026-07-05T01:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"TKJYEMGFUNTH","created_at":"2026-07-05T01:40:01Z"},{"alias_kind":"pith_short_16","alias_value":"TKJYEMGFUNTHSJUS","created_at":"2026-07-05T01:40:01Z"},{"alias_kind":"pith_short_8","alias_value":"TKJYEMGF","created_at":"2026-07-05T01:40:01Z"}],"graph_snapshots":[{"event_id":"sha256:cbe5864f63469b3bffb4e2ed6af096f2a3f5c6e720aa2c412b93470c6454bce8","target":"graph","created_at":"2026-07-05T01:40:01Z","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/2009.10195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Models that perform well on a training domain often fail to generalize to out-of-domain (OOD) examples. Data augmentation is a common method used to prevent overfitting and improve OOD generalization. However, in natural language, it is difficult to generate new examples that stay on the underlying data manifold. We introduce SSMBA, a data augmentation method for generating synthetic training examples by using a pair of corruption and reconstruction functions to move randomly on a data manifold. We investigate the use of SSMBA in the natural language domain, leveraging the manifold assumption ","authors_text":"Kyunghyun Cho, Marzyeh Ghassemi, Nathan Ng","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T22:02:33Z","title":"SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10195","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:c27a8b69dff07d598d48b5e5b7e80f1947c478c331ceea0d72f41caf71139556","target":"record","created_at":"2026-07-05T01:40:01Z","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":"204095daaaa84ba04bbe392139e71c07b23ff8c66d6a1964baa008187ed05582","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T22:02:33Z","title_canon_sha256":"80e6a6b2721111ca793759a5e44c165af2c82e5d448bf0dcac049425198a080c"},"schema_version":"1.0","source":{"id":"2009.10195","kind":"arxiv","version":2}},"canonical_sha256":"9a938230c5a366792692676c1a5eea4be0579f56614bad10dcfe028dad32514e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a938230c5a366792692676c1a5eea4be0579f56614bad10dcfe028dad32514e","first_computed_at":"2026-07-05T01:40:01.590197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:40:01.590197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AlgSmJvH/wFZ3bHzYhroWCC6tVYSYrLB4D8Dlrxjf/n3b68wsFbAbDefYQULm78gNInDUm+Ny0ZwiFWFy8GMAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:40:01.590672Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.10195","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c27a8b69dff07d598d48b5e5b7e80f1947c478c331ceea0d72f41caf71139556","sha256:cbe5864f63469b3bffb4e2ed6af096f2a3f5c6e720aa2c412b93470c6454bce8"],"state_sha256":"8fa60071db5bcd221f897a33ad36b6f3b0a90b46729ac2da85382d3275fd816b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O2OSt1ob+JFu7K0rPfzr06Dqq1m6kdXrbMQtBlAZ6vhFKOZrDB62fe3920pPqQ7egFzZWSzFYAErCOpffgd6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:57:27.052891Z","bundle_sha256":"1f20873172b2284060848b3fb08499d0b5a56f2dd519f180def0669002f687e1"}}