{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7XZZNGIJFUIHH4FQZIFUJRP3FM","short_pith_number":"pith:7XZZNGIJ","canonical_record":{"source":{"id":"1812.04718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T03:59:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"19570e34f50424250ba84ed6a6b7d6a83f68f79e8e020276866d5566b691430f","abstract_canon_sha256":"a1f5a22162f3ef97961ca6a634a115317dce4ec584db1d200cc9bc6738532beb"},"schema_version":"1.0"},"canonical_sha256":"fdf39699092d1073f0b0ca0b44c5fb2b0d5bf91b8219b28e4b0b7641e2890d48","source":{"kind":"arxiv","id":"1812.04718","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.04718","created_at":"2026-05-17T23:58:29Z"},{"alias_kind":"arxiv_version","alias_value":"1812.04718v1","created_at":"2026-05-17T23:58:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04718","created_at":"2026-05-17T23:58:29Z"},{"alias_kind":"pith_short_12","alias_value":"7XZZNGIJFUIH","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"7XZZNGIJFUIHH4FQ","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"7XZZNGIJ","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7XZZNGIJFUIHH4FQZIFUJRP3FM","target":"record","payload":{"canonical_record":{"source":{"id":"1812.04718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T03:59:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"19570e34f50424250ba84ed6a6b7d6a83f68f79e8e020276866d5566b691430f","abstract_canon_sha256":"a1f5a22162f3ef97961ca6a634a115317dce4ec584db1d200cc9bc6738532beb"},"schema_version":"1.0"},"canonical_sha256":"fdf39699092d1073f0b0ca0b44c5fb2b0d5bf91b8219b28e4b0b7641e2890d48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:29.725522Z","signature_b64":"fFD/WnaKylkpf3Jl0sN4u2c0zhjOKQoDzYdXIVVGid9p5wwUAwthJQJFQ4Bsn85OVwZ3xepWf0ekfXeuJwQxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdf39699092d1073f0b0ca0b44c5fb2b0d5bf91b8219b28e4b0b7641e2890d48","last_reissued_at":"2026-05-17T23:58:29.724675Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:29.724675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.04718","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1WzDdD8s8iYO1mnl8T9FhjJP9+ecwKmwvtwL6VdQ2JSTdxR4Po3bRi3EPZbIF8bEgLYnQ8AbfIybFmGDOkk+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:57:30.243280Z"},"content_sha256":"ee09cfd5bcea87cd20fd3e6a56611e7a1b72db8db1b5ce6b7e4241d7468c5755","schema_version":"1.0","event_id":"sha256:ee09cfd5bcea87cd20fd3e6a56611e7a1b72db8db1b5ce6b7e4241d7468c5755"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7XZZNGIJFUIHH4FQZIFUJRP3FM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Data Augmentation Made Simple By Leveraging NLP Cloud APIs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Claude Coulombe","submitted_at":"2018-12-05T03:59:41Z","abstract_excerpt":"In practice, it is common to find oneself with far too little text data to train a deep neural network. This \"Big Data Wall\" represents a challenge for minority language communities on the Internet, organizations, laboratories and companies that compete the GAFAM (Google, Amazon, Facebook, Apple, Microsoft). While most of the research effort in text data augmentation aims on the long-term goal of finding end-to-end learning solutions, which is equivalent to \"using neural networks to feed neural networks\", this engineering work focuses on the use of practical, robust, scalable and easy-to-imple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04718","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:58:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kx4nlUvaj3ty6azHyNLlYj4OSRKPGHbvJ3BfeuEoTZuPVYDTx61DgWVBGBFwFfBrYHVdV59uSx3Ma9mN6/wkCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:57:30.243750Z"},"content_sha256":"e14a280dcf9f396bb095a0a2c3003e079ca1014311aa7ebc1ea8977ea9456c70","schema_version":"1.0","event_id":"sha256:e14a280dcf9f396bb095a0a2c3003e079ca1014311aa7ebc1ea8977ea9456c70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7XZZNGIJFUIHH4FQZIFUJRP3FM/bundle.json","state_url":"https://pith.science/pith/7XZZNGIJFUIHH4FQZIFUJRP3FM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7XZZNGIJFUIHH4FQZIFUJRP3FM/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":"2026-08-08T12:57:30Z","links":{"resolver":"https://pith.science/pith/7XZZNGIJFUIHH4FQZIFUJRP3FM","bundle":"https://pith.science/pith/7XZZNGIJFUIHH4FQZIFUJRP3FM/bundle.json","state":"https://pith.science/pith/7XZZNGIJFUIHH4FQZIFUJRP3FM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7XZZNGIJFUIHH4FQZIFUJRP3FM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7XZZNGIJFUIHH4FQZIFUJRP3FM","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":"a1f5a22162f3ef97961ca6a634a115317dce4ec584db1d200cc9bc6738532beb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T03:59:41Z","title_canon_sha256":"19570e34f50424250ba84ed6a6b7d6a83f68f79e8e020276866d5566b691430f"},"schema_version":"1.0","source":{"id":"1812.04718","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.04718","created_at":"2026-05-17T23:58:29Z"},{"alias_kind":"arxiv_version","alias_value":"1812.04718v1","created_at":"2026-05-17T23:58:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04718","created_at":"2026-05-17T23:58:29Z"},{"alias_kind":"pith_short_12","alias_value":"7XZZNGIJFUIH","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"7XZZNGIJFUIHH4FQ","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"7XZZNGIJ","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:e14a280dcf9f396bb095a0a2c3003e079ca1014311aa7ebc1ea8977ea9456c70","target":"graph","created_at":"2026-05-17T23:58:29Z","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"},"paper":{"abstract_excerpt":"In practice, it is common to find oneself with far too little text data to train a deep neural network. This \"Big Data Wall\" represents a challenge for minority language communities on the Internet, organizations, laboratories and companies that compete the GAFAM (Google, Amazon, Facebook, Apple, Microsoft). While most of the research effort in text data augmentation aims on the long-term goal of finding end-to-end learning solutions, which is equivalent to \"using neural networks to feed neural networks\", this engineering work focuses on the use of practical, robust, scalable and easy-to-imple","authors_text":"Claude Coulombe","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T03:59:41Z","title":"Text Data Augmentation Made Simple By Leveraging NLP Cloud APIs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04718","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:ee09cfd5bcea87cd20fd3e6a56611e7a1b72db8db1b5ce6b7e4241d7468c5755","target":"record","created_at":"2026-05-17T23:58:29Z","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":"a1f5a22162f3ef97961ca6a634a115317dce4ec584db1d200cc9bc6738532beb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T03:59:41Z","title_canon_sha256":"19570e34f50424250ba84ed6a6b7d6a83f68f79e8e020276866d5566b691430f"},"schema_version":"1.0","source":{"id":"1812.04718","kind":"arxiv","version":1}},"canonical_sha256":"fdf39699092d1073f0b0ca0b44c5fb2b0d5bf91b8219b28e4b0b7641e2890d48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdf39699092d1073f0b0ca0b44c5fb2b0d5bf91b8219b28e4b0b7641e2890d48","first_computed_at":"2026-05-17T23:58:29.724675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:29.724675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fFD/WnaKylkpf3Jl0sN4u2c0zhjOKQoDzYdXIVVGid9p5wwUAwthJQJFQ4Bsn85OVwZ3xepWf0ekfXeuJwQxDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:29.725522Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.04718","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee09cfd5bcea87cd20fd3e6a56611e7a1b72db8db1b5ce6b7e4241d7468c5755","sha256:e14a280dcf9f396bb095a0a2c3003e079ca1014311aa7ebc1ea8977ea9456c70"],"state_sha256":"ceae0f12ecc7e3928ecdb2ff12407278c5a4b435ef28cd3534532297438d0600"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PLw7gC6pZC6XiV+uprwt7KLuXq9Rh0tjLIohIUj9ycetd04DWa+RsSfW5tTgKmBv+ZRbQmSOdKOWg9DwZ0ptDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:57:30.247584Z","bundle_sha256":"7d08d54019be6bd2d766e4ef8aec27d539e7133deaba2c413335979825dcb281"}}