{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:UAYK5VTL5IUSBNZXYD7GMIKJK4","short_pith_number":"pith:UAYK5VTL","canonical_record":{"source":{"id":"1605.07725","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-25T04:25:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"240e3739137fdd1df8ec2dbaba47f3626be420cd1e2d42be2494b0a6ed41d75b","abstract_canon_sha256":"29b927726ab1b27c365787e3ebc18d1a1793890396f61fb5ed51e21d0ea43b5c"},"schema_version":"1.0"},"canonical_sha256":"a030aed66bea2920b737c0fe662149572f343106399f21e2ebd731cd6ba30f19","source":{"kind":"arxiv","id":"1605.07725","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.07725","created_at":"2026-07-05T03:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"1605.07725v4","created_at":"2026-07-05T03:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07725","created_at":"2026-07-05T03:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"UAYK5VTL5IUS","created_at":"2026-07-05T03:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"UAYK5VTL5IUSBNZX","created_at":"2026-07-05T03:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"UAYK5VTL","created_at":"2026-07-05T03:31:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:UAYK5VTL5IUSBNZXYD7GMIKJK4","target":"record","payload":{"canonical_record":{"source":{"id":"1605.07725","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-25T04:25:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"240e3739137fdd1df8ec2dbaba47f3626be420cd1e2d42be2494b0a6ed41d75b","abstract_canon_sha256":"29b927726ab1b27c365787e3ebc18d1a1793890396f61fb5ed51e21d0ea43b5c"},"schema_version":"1.0"},"canonical_sha256":"a030aed66bea2920b737c0fe662149572f343106399f21e2ebd731cd6ba30f19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:50.479575Z","signature_b64":"+cL1Xkajqu2Yl/IOFXPDI32gWyokgCY2X3KT3FenClAl1R4SMiJ6gcwqmX3K2Ne00Cj9EOhku64e9AD/GEhXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a030aed66bea2920b737c0fe662149572f343106399f21e2ebd731cd6ba30f19","last_reissued_at":"2026-07-05T03:31:50.479121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:50.479121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.07725","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:31:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MtqeubX2hKrDmJ8bza3nsmeuZbKIOZ+FRdy77zZqkF/UhkBLkvO1co0sMIp7NB/nNNnakya3/A5AUrZp5iZUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:24:29.547187Z"},"content_sha256":"b3ad640d8ad21cb7ded7bc72e945d0c9dcc5f5797a9a664f9f401b785b3cbda8","schema_version":"1.0","event_id":"sha256:b3ad640d8ad21cb7ded7bc72e945d0c9dcc5f5797a9a664f9f401b785b3cbda8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:UAYK5VTL5IUSBNZXYD7GMIKJK4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Training Methods for Semi-Supervised Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew M. Dai, Ian Goodfellow, Takeru Miyato","submitted_at":"2016-05-25T04:25:45Z","abstract_excerpt":"Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making small perturbations to numerous entries of the input vector, which is inappropriate for sparse high-dimensional inputs such as one-hot word representations. We extend adversarial and virtual adversarial training to the text domain by applying perturbations to the word embeddings in a recurrent neural network rather than to the original input itself. The propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07725","kind":"arxiv","version":4},"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/1605.07725/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":"2026-07-05T03:31:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jbLtVrnOuU0vmFbb31GPsiU6szwyqImciTLh80/qplf7znW1wLNM7iAyyFIiqfoevkZ16mowKbq222NIcSe9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:24:29.547692Z"},"content_sha256":"664f2870861318544e9896efd75874fa89f8d4c5ebbf49036d4f9507f775d826","schema_version":"1.0","event_id":"sha256:664f2870861318544e9896efd75874fa89f8d4c5ebbf49036d4f9507f775d826"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UAYK5VTL5IUSBNZXYD7GMIKJK4/bundle.json","state_url":"https://pith.science/pith/UAYK5VTL5IUSBNZXYD7GMIKJK4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UAYK5VTL5IUSBNZXYD7GMIKJK4/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":"2026-08-07T01:24:29Z","links":{"resolver":"https://pith.science/pith/UAYK5VTL5IUSBNZXYD7GMIKJK4","bundle":"https://pith.science/pith/UAYK5VTL5IUSBNZXYD7GMIKJK4/bundle.json","state":"https://pith.science/pith/UAYK5VTL5IUSBNZXYD7GMIKJK4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UAYK5VTL5IUSBNZXYD7GMIKJK4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:UAYK5VTL5IUSBNZXYD7GMIKJK4","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":"29b927726ab1b27c365787e3ebc18d1a1793890396f61fb5ed51e21d0ea43b5c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-25T04:25:45Z","title_canon_sha256":"240e3739137fdd1df8ec2dbaba47f3626be420cd1e2d42be2494b0a6ed41d75b"},"schema_version":"1.0","source":{"id":"1605.07725","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.07725","created_at":"2026-07-05T03:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"1605.07725v4","created_at":"2026-07-05T03:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07725","created_at":"2026-07-05T03:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"UAYK5VTL5IUS","created_at":"2026-07-05T03:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"UAYK5VTL5IUSBNZX","created_at":"2026-07-05T03:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"UAYK5VTL","created_at":"2026-07-05T03:31:50Z"}],"graph_snapshots":[{"event_id":"sha256:664f2870861318544e9896efd75874fa89f8d4c5ebbf49036d4f9507f775d826","target":"graph","created_at":"2026-07-05T03:31:50Z","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/1605.07725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making small perturbations to numerous entries of the input vector, which is inappropriate for sparse high-dimensional inputs such as one-hot word representations. We extend adversarial and virtual adversarial training to the text domain by applying perturbations to the word embeddings in a recurrent neural network rather than to the original input itself. The propos","authors_text":"Andrew M. Dai, Ian Goodfellow, Takeru Miyato","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-25T04:25:45Z","title":"Adversarial Training Methods for Semi-Supervised Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07725","kind":"arxiv","version":4},"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:b3ad640d8ad21cb7ded7bc72e945d0c9dcc5f5797a9a664f9f401b785b3cbda8","target":"record","created_at":"2026-07-05T03:31:50Z","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":"29b927726ab1b27c365787e3ebc18d1a1793890396f61fb5ed51e21d0ea43b5c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-25T04:25:45Z","title_canon_sha256":"240e3739137fdd1df8ec2dbaba47f3626be420cd1e2d42be2494b0a6ed41d75b"},"schema_version":"1.0","source":{"id":"1605.07725","kind":"arxiv","version":4}},"canonical_sha256":"a030aed66bea2920b737c0fe662149572f343106399f21e2ebd731cd6ba30f19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a030aed66bea2920b737c0fe662149572f343106399f21e2ebd731cd6ba30f19","first_computed_at":"2026-07-05T03:31:50.479121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:31:50.479121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+cL1Xkajqu2Yl/IOFXPDI32gWyokgCY2X3KT3FenClAl1R4SMiJ6gcwqmX3K2Ne00Cj9EOhku64e9AD/GEhXDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:31:50.479575Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.07725","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3ad640d8ad21cb7ded7bc72e945d0c9dcc5f5797a9a664f9f401b785b3cbda8","sha256:664f2870861318544e9896efd75874fa89f8d4c5ebbf49036d4f9507f775d826"],"state_sha256":"2ca2809c7b6d7bef655c2f08e8ff85c3a0dec2c21ad88b91248528219aed79f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"erKpmzRdGNhkElnvIck/nOxrKJoRC2HDYDhZngzDfveYqjbZJyi0eR7g2hymY04eo0SQfvOSy0xG7CwhMeZMAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:24:29.551596Z","bundle_sha256":"a8a6a6193628923e50e971db2a6fe5ae1289baaaf4ddf086a657aa5dc56722bc"}}