{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:AEH3AF6ON4EQX6YMBPTE6LDAUL","short_pith_number":"pith:AEH3AF6O","canonical_record":{"source":{"id":"2007.00875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-02T04:43:31Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"c9e0ea72bf50f7fea203c01a0b4506ec8fb1c2e9e3dbdad98bcd75970aa2429e","abstract_canon_sha256":"6413bbd7721c7bfbf75f57938b00b3340d6f8aae5e8d12f014563399249f9126"},"schema_version":"1.0"},"canonical_sha256":"010fb017ce6f090bfb0c0be64f2c60a2dd2d5776fe23bd0d1f6401aa86114cb0","source":{"kind":"arxiv","id":"2007.00875","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00875","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00875v1","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00875","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"AEH3AF6ON4EQ","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"AEH3AF6ON4EQX6YM","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"AEH3AF6O","created_at":"2026-07-05T01:15:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:AEH3AF6ON4EQX6YMBPTE6LDAUL","target":"record","payload":{"canonical_record":{"source":{"id":"2007.00875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-02T04:43:31Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"c9e0ea72bf50f7fea203c01a0b4506ec8fb1c2e9e3dbdad98bcd75970aa2429e","abstract_canon_sha256":"6413bbd7721c7bfbf75f57938b00b3340d6f8aae5e8d12f014563399249f9126"},"schema_version":"1.0"},"canonical_sha256":"010fb017ce6f090bfb0c0be64f2c60a2dd2d5776fe23bd0d1f6401aa86114cb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:42.060951Z","signature_b64":"1DtFzAdWVX4O2m9VcZeSPTn0cT3VWw3fcAAAypdh1bA6LqvJ2OK4h6X088Voa9sZQ85+iB5PrGWyHjvPFRBwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"010fb017ce6f090bfb0c0be64f2c60a2dd2d5776fe23bd0d1f6401aa86114cb0","last_reissued_at":"2026-07-05T01:15:42.060520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:42.060520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.00875","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":"2026-07-05T01:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VwDKB8r0M/Wb+WLDiGeY+brNHUAF7YIAjdbpWAiifZ894jeTdnKE9mR5FCH7NP7Uq5sBQCJ+54KjeM1ceqwpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:57:04.907530Z"},"content_sha256":"2d3a95397155ff9290cbdebf03013b8c16333a00909572a7fdf21d725db0b86b","schema_version":"1.0","event_id":"sha256:2d3a95397155ff9290cbdebf03013b8c16333a00909572a7fdf21d725db0b86b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:AEH3AF6ON4EQX6YMBPTE6LDAUL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can We Achieve More with Less? Exploring Data Augmentation for Toxic Comment Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chetanya Rastogi, Fang-I Hsiao, Nikka Mofid","submitted_at":"2020-07-02T04:43:31Z","abstract_excerpt":"This paper tackles one of the greatest limitations in Machine Learning: Data Scarcity. Specifically, we explore whether high accuracy classifiers can be built from small datasets, utilizing a combination of data augmentation techniques and machine learning algorithms. In this paper, we experiment with Easy Data Augmentation (EDA) and Backtranslation, as well as with three popular learning algorithms, Logistic Regression, Support Vector Machine (SVM), and Bidirectional Long Short-Term Memory Network (Bi-LSTM). For our experimentation, we utilize the Wikipedia Toxic Comments dataset so that in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00875","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.00875/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":"2026-07-05T01:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hsKHjQ7sUoqBswdMmhy2BgZ1P+8OF+B94HHbal2m4nLD3O9S805wCONrFomlgfdI/mRgZH6fsQwls7Lnwb0JBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:57:04.907906Z"},"content_sha256":"7120177ec92febcc5022f4bacc1239b5d3f50d613cc11a7c79903588e2dd7bb4","schema_version":"1.0","event_id":"sha256:7120177ec92febcc5022f4bacc1239b5d3f50d613cc11a7c79903588e2dd7bb4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AEH3AF6ON4EQX6YMBPTE6LDAUL/bundle.json","state_url":"https://pith.science/pith/AEH3AF6ON4EQX6YMBPTE6LDAUL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AEH3AF6ON4EQX6YMBPTE6LDAUL/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":"2026-07-07T07:57:04Z","links":{"resolver":"https://pith.science/pith/AEH3AF6ON4EQX6YMBPTE6LDAUL","bundle":"https://pith.science/pith/AEH3AF6ON4EQX6YMBPTE6LDAUL/bundle.json","state":"https://pith.science/pith/AEH3AF6ON4EQX6YMBPTE6LDAUL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AEH3AF6ON4EQX6YMBPTE6LDAUL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AEH3AF6ON4EQX6YMBPTE6LDAUL","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":"6413bbd7721c7bfbf75f57938b00b3340d6f8aae5e8d12f014563399249f9126","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-02T04:43:31Z","title_canon_sha256":"c9e0ea72bf50f7fea203c01a0b4506ec8fb1c2e9e3dbdad98bcd75970aa2429e"},"schema_version":"1.0","source":{"id":"2007.00875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00875","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00875v1","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00875","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"AEH3AF6ON4EQ","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"AEH3AF6ON4EQX6YM","created_at":"2026-07-05T01:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"AEH3AF6O","created_at":"2026-07-05T01:15:42Z"}],"graph_snapshots":[{"event_id":"sha256:7120177ec92febcc5022f4bacc1239b5d3f50d613cc11a7c79903588e2dd7bb4","target":"graph","created_at":"2026-07-05T01:15:42Z","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/2007.00875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper tackles one of the greatest limitations in Machine Learning: Data Scarcity. Specifically, we explore whether high accuracy classifiers can be built from small datasets, utilizing a combination of data augmentation techniques and machine learning algorithms. In this paper, we experiment with Easy Data Augmentation (EDA) and Backtranslation, as well as with three popular learning algorithms, Logistic Regression, Support Vector Machine (SVM), and Bidirectional Long Short-Term Memory Network (Bi-LSTM). For our experimentation, we utilize the Wikipedia Toxic Comments dataset so that in t","authors_text":"Chetanya Rastogi, Fang-I Hsiao, Nikka Mofid","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-02T04:43:31Z","title":"Can We Achieve More with Less? Exploring Data Augmentation for Toxic Comment Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00875","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":"sha256:2d3a95397155ff9290cbdebf03013b8c16333a00909572a7fdf21d725db0b86b","target":"record","created_at":"2026-07-05T01:15:42Z","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":"6413bbd7721c7bfbf75f57938b00b3340d6f8aae5e8d12f014563399249f9126","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-02T04:43:31Z","title_canon_sha256":"c9e0ea72bf50f7fea203c01a0b4506ec8fb1c2e9e3dbdad98bcd75970aa2429e"},"schema_version":"1.0","source":{"id":"2007.00875","kind":"arxiv","version":1}},"canonical_sha256":"010fb017ce6f090bfb0c0be64f2c60a2dd2d5776fe23bd0d1f6401aa86114cb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"010fb017ce6f090bfb0c0be64f2c60a2dd2d5776fe23bd0d1f6401aa86114cb0","first_computed_at":"2026-07-05T01:15:42.060520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:15:42.060520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1DtFzAdWVX4O2m9VcZeSPTn0cT3VWw3fcAAAypdh1bA6LqvJ2OK4h6X088Voa9sZQ85+iB5PrGWyHjvPFRBwDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:15:42.060951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.00875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d3a95397155ff9290cbdebf03013b8c16333a00909572a7fdf21d725db0b86b","sha256:7120177ec92febcc5022f4bacc1239b5d3f50d613cc11a7c79903588e2dd7bb4"],"state_sha256":"9d407eb2aa52b5bdffe3320395706140db54c1ef096a72bec12d220739ce1ead"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G2PP4NPkCFRTXeVrKy4HUYfnFmtzqaSMbOSdwa+/7YPX0PxqxF+iBPBe4lwaJwDa3GB8YcjOGK0dkr3+F9I9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:57:04.910032Z","bundle_sha256":"9b717a662d37f889392d5fe4de050a236beb33dd9035a1ba8d84da6aa4af91d2"}}