{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6M2L2UYGJ7GI4JVKGSRH4M44TA","short_pith_number":"pith:6M2L2UYG","canonical_record":{"source":{"id":"2007.02033","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-04T07:45:04Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"cecdd78c7b126a90edc4edd14811f505d2296fb409df2385680e51a995d1d780","abstract_canon_sha256":"b60abd14a707ee14cc1d4581596d0c8b7dd52c479c1568b3fefd0797caf6f599"},"schema_version":"1.0"},"canonical_sha256":"f334bd53064fcc8e26aa34a27e339c98320b6091dd7cdc7175526accaf581836","source":{"kind":"arxiv","id":"2007.02033","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.02033","created_at":"2026-07-05T02:26:12Z"},{"alias_kind":"arxiv_version","alias_value":"2007.02033v2","created_at":"2026-07-05T02:26:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02033","created_at":"2026-07-05T02:26:12Z"},{"alias_kind":"pith_short_12","alias_value":"6M2L2UYGJ7GI","created_at":"2026-07-05T02:26:12Z"},{"alias_kind":"pith_short_16","alias_value":"6M2L2UYGJ7GI4JVK","created_at":"2026-07-05T02:26:12Z"},{"alias_kind":"pith_short_8","alias_value":"6M2L2UYG","created_at":"2026-07-05T02:26:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6M2L2UYGJ7GI4JVKGSRH4M44TA","target":"record","payload":{"canonical_record":{"source":{"id":"2007.02033","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-04T07:45:04Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"cecdd78c7b126a90edc4edd14811f505d2296fb409df2385680e51a995d1d780","abstract_canon_sha256":"b60abd14a707ee14cc1d4581596d0c8b7dd52c479c1568b3fefd0797caf6f599"},"schema_version":"1.0"},"canonical_sha256":"f334bd53064fcc8e26aa34a27e339c98320b6091dd7cdc7175526accaf581836","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:12.955031Z","signature_b64":"7JQJ9dERJkILyaGE6OMqm6af2tER0shYBG2dNSzE2FxbqAOybqkuUS/46xucvNOmnqpbn6P83Yrq7LM0b9mcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f334bd53064fcc8e26aa34a27e339c98320b6091dd7cdc7175526accaf581836","last_reissued_at":"2026-07-05T02:26:12.954579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:12.954579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.02033","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":"2026-07-05T02:26:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"he1v97p8yd1Ot24hLFsr4ls7cTk7DQidHz9WgTV2OiS6XGi6revxVcl6sjtlwLuPT4rtnbSxNhEn3bY3/51OBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:54:15.190733Z"},"content_sha256":"38b0841dec284558c5ad7944fc7a10dc9aa263361bf0ca4a9e12c10d37b0e2ba","schema_version":"1.0","event_id":"sha256:38b0841dec284558c5ad7944fc7a10dc9aa263361bf0ca4a9e12c10d37b0e2ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6M2L2UYGJ7GI4JVKGSRH4M44TA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Data Augmentation: Towards better detection of spear-phishing emails","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Maxime Meyer, Mehdi Regina, S\\'ebastien Goutal","submitted_at":"2020-07-04T07:45:04Z","abstract_excerpt":"Text data augmentation, i.e., the creation of new textual data from an existing text, is challenging. Indeed, augmentation transformations should take into account language complexity while being relevant to the target Natural Language Processing (NLP) task (e.g., Machine Translation, Text Classification). Initially motivated by an application of Business Email Compromise (BEC) detection, we propose a corpus and task agnostic augmentation framework used as a service to augment English texts within our company. Our proposal combines different methods, utilizing BERT language model, multi-step b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.02033","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/2007.02033/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":"2026-07-05T02:26:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MvNZH6x5bSNmEXbOZ5DOAW83HYloOTFNNn2ZsSR8m2+iyMmpb7NnDlRqKCx55RB35mt0fCP2/xzHu5KAnqv5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:54:15.191291Z"},"content_sha256":"64cffa06e21bb0d8f333712a51547ae14b0ce902e477adb1ceaffa6a5db7a779","schema_version":"1.0","event_id":"sha256:64cffa06e21bb0d8f333712a51547ae14b0ce902e477adb1ceaffa6a5db7a779"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6M2L2UYGJ7GI4JVKGSRH4M44TA/bundle.json","state_url":"https://pith.science/pith/6M2L2UYGJ7GI4JVKGSRH4M44TA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6M2L2UYGJ7GI4JVKGSRH4M44TA/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":"2026-08-15T14:54:15Z","links":{"resolver":"https://pith.science/pith/6M2L2UYGJ7GI4JVKGSRH4M44TA","bundle":"https://pith.science/pith/6M2L2UYGJ7GI4JVKGSRH4M44TA/bundle.json","state":"https://pith.science/pith/6M2L2UYGJ7GI4JVKGSRH4M44TA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6M2L2UYGJ7GI4JVKGSRH4M44TA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6M2L2UYGJ7GI4JVKGSRH4M44TA","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":"b60abd14a707ee14cc1d4581596d0c8b7dd52c479c1568b3fefd0797caf6f599","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-04T07:45:04Z","title_canon_sha256":"cecdd78c7b126a90edc4edd14811f505d2296fb409df2385680e51a995d1d780"},"schema_version":"1.0","source":{"id":"2007.02033","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.02033","created_at":"2026-07-05T02:26:12Z"},{"alias_kind":"arxiv_version","alias_value":"2007.02033v2","created_at":"2026-07-05T02:26:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02033","created_at":"2026-07-05T02:26:12Z"},{"alias_kind":"pith_short_12","alias_value":"6M2L2UYGJ7GI","created_at":"2026-07-05T02:26:12Z"},{"alias_kind":"pith_short_16","alias_value":"6M2L2UYGJ7GI4JVK","created_at":"2026-07-05T02:26:12Z"},{"alias_kind":"pith_short_8","alias_value":"6M2L2UYG","created_at":"2026-07-05T02:26:12Z"}],"graph_snapshots":[{"event_id":"sha256:64cffa06e21bb0d8f333712a51547ae14b0ce902e477adb1ceaffa6a5db7a779","target":"graph","created_at":"2026-07-05T02:26:12Z","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/2007.02033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text data augmentation, i.e., the creation of new textual data from an existing text, is challenging. Indeed, augmentation transformations should take into account language complexity while being relevant to the target Natural Language Processing (NLP) task (e.g., Machine Translation, Text Classification). Initially motivated by an application of Business Email Compromise (BEC) detection, we propose a corpus and task agnostic augmentation framework used as a service to augment English texts within our company. Our proposal combines different methods, utilizing BERT language model, multi-step b","authors_text":"Maxime Meyer, Mehdi Regina, S\\'ebastien Goutal","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-04T07:45:04Z","title":"Text Data Augmentation: Towards better detection of spear-phishing emails"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.02033","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":"sha256:38b0841dec284558c5ad7944fc7a10dc9aa263361bf0ca4a9e12c10d37b0e2ba","target":"record","created_at":"2026-07-05T02:26:12Z","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":"b60abd14a707ee14cc1d4581596d0c8b7dd52c479c1568b3fefd0797caf6f599","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-04T07:45:04Z","title_canon_sha256":"cecdd78c7b126a90edc4edd14811f505d2296fb409df2385680e51a995d1d780"},"schema_version":"1.0","source":{"id":"2007.02033","kind":"arxiv","version":2}},"canonical_sha256":"f334bd53064fcc8e26aa34a27e339c98320b6091dd7cdc7175526accaf581836","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f334bd53064fcc8e26aa34a27e339c98320b6091dd7cdc7175526accaf581836","first_computed_at":"2026-07-05T02:26:12.954579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:12.954579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7JQJ9dERJkILyaGE6OMqm6af2tER0shYBG2dNSzE2FxbqAOybqkuUS/46xucvNOmnqpbn6P83Yrq7LM0b9mcDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:12.955031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.02033","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38b0841dec284558c5ad7944fc7a10dc9aa263361bf0ca4a9e12c10d37b0e2ba","sha256:64cffa06e21bb0d8f333712a51547ae14b0ce902e477adb1ceaffa6a5db7a779"],"state_sha256":"2d4a04061d6d7738b465ae66e10d9fccf00b84733df20ce0491b5ce9630072f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UXoFfcdQaejNLSSgKCUqZ4JQLVd4SXIiqHaPSDem6FZxRkDiiTsWqalYrOaRz3TdJt8qPJHTICLAiqBS3xPUDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T14:54:15.196646Z","bundle_sha256":"309a09a936b369e5098301523325eb91ac51651eea7f97f2fa0d97d76a0e3ecd"}}