{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZOLH4YBBXIFUQKNPA4VE2MR77Z","short_pith_number":"pith:ZOLH4YBB","canonical_record":{"source":{"id":"2009.12344","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-25T17:04:17Z","cross_cats_sorted":[],"title_canon_sha256":"6b5693850f7f3dbbbee029ffe92531fd795d0ece088c0a53a113e771c659ecd9","abstract_canon_sha256":"9726c8de4cb7bbbddcd3710b81f8a69d321f1ac6c7283d09079116e4f4fab2a7"},"schema_version":"1.0"},"canonical_sha256":"cb967e6021ba0b4829af072a4d323ffe5f3d652e914b3f8d947befec437a1185","source":{"kind":"arxiv","id":"2009.12344","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12344","created_at":"2026-07-05T01:45:45Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12344v2","created_at":"2026-07-05T01:45:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12344","created_at":"2026-07-05T01:45:45Z"},{"alias_kind":"pith_short_12","alias_value":"ZOLH4YBBXIFU","created_at":"2026-07-05T01:45:45Z"},{"alias_kind":"pith_short_16","alias_value":"ZOLH4YBBXIFUQKNP","created_at":"2026-07-05T01:45:45Z"},{"alias_kind":"pith_short_8","alias_value":"ZOLH4YBB","created_at":"2026-07-05T01:45:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZOLH4YBBXIFUQKNPA4VE2MR77Z","target":"record","payload":{"canonical_record":{"source":{"id":"2009.12344","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-25T17:04:17Z","cross_cats_sorted":[],"title_canon_sha256":"6b5693850f7f3dbbbee029ffe92531fd795d0ece088c0a53a113e771c659ecd9","abstract_canon_sha256":"9726c8de4cb7bbbddcd3710b81f8a69d321f1ac6c7283d09079116e4f4fab2a7"},"schema_version":"1.0"},"canonical_sha256":"cb967e6021ba0b4829af072a4d323ffe5f3d652e914b3f8d947befec437a1185","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:45.186520Z","signature_b64":"7IrlE5Q5MRhiHB2GWmGh3Q208i6gvVlopNdVFgFm4IY2GEZdyHVZdZisDTrxBXekyqvYjrdkFi/Cwblmja7uAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb967e6021ba0b4829af072a4d323ffe5f3d652e914b3f8d947befec437a1185","last_reissued_at":"2026-07-05T01:45:45.186115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:45.186115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.12344","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":"2026-07-05T01:45:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lkiYxKHrXeFeSpvP7v6nwgr8JN2njZ/lCSSPii4BgdrDZt+f2sKtPzEL2uZtHIy8ZNlkg0DhzY8zHzeyOmbRDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:03:28.616575Z"},"content_sha256":"d39685b0dcd5d265b9b36ba88d9ed3aac3c4500cd47f015400eeb17c2a237c3d","schema_version":"1.0","event_id":"sha256:d39685b0dcd5d265b9b36ba88d9ed3aac3c4500cd47f015400eeb17c2a237c3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZOLH4YBBXIFUQKNPA4VE2MR77Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A little goes a long way: Improving toxic language classification despite data scarcity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adrian Flanagan, Mika Juuti, N. Asokan, Tommi Gr\\\"ondahl","submitted_at":"2020-09-25T17:04:17Z","abstract_excerpt":"Detection of some types of toxic language is hampered by extreme scarcity of labeled training data. Data augmentation - generating new synthetic data from a labeled seed dataset - can help. The efficacy of data augmentation on toxic language classification has not been fully explored. We present the first systematic study on how data augmentation techniques impact performance across toxic language classifiers, ranging from shallow logistic regression architectures to BERT - a state-of-the-art pre-trained Transformer network. We compare the performance of eight techniques on very scarce seed da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12344","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/2009.12344/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":"2026-07-05T01:45:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tRq1pimrxLGV/9/WrcXhTI3OpFw14bpH+nAs5U9NtgQjdZliAHcCtksZMSTQMCL5wU/35FxnWIRX18/2OdMWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:03:28.617069Z"},"content_sha256":"81abde06001403fbde44fbb3132ba5618d626ac4114bbb728db62dd460e13e89","schema_version":"1.0","event_id":"sha256:81abde06001403fbde44fbb3132ba5618d626ac4114bbb728db62dd460e13e89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZOLH4YBBXIFUQKNPA4VE2MR77Z/bundle.json","state_url":"https://pith.science/pith/ZOLH4YBBXIFUQKNPA4VE2MR77Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZOLH4YBBXIFUQKNPA4VE2MR77Z/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":"2026-08-04T01:03:28Z","links":{"resolver":"https://pith.science/pith/ZOLH4YBBXIFUQKNPA4VE2MR77Z","bundle":"https://pith.science/pith/ZOLH4YBBXIFUQKNPA4VE2MR77Z/bundle.json","state":"https://pith.science/pith/ZOLH4YBBXIFUQKNPA4VE2MR77Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZOLH4YBBXIFUQKNPA4VE2MR77Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZOLH4YBBXIFUQKNPA4VE2MR77Z","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":"9726c8de4cb7bbbddcd3710b81f8a69d321f1ac6c7283d09079116e4f4fab2a7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-25T17:04:17Z","title_canon_sha256":"6b5693850f7f3dbbbee029ffe92531fd795d0ece088c0a53a113e771c659ecd9"},"schema_version":"1.0","source":{"id":"2009.12344","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12344","created_at":"2026-07-05T01:45:45Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12344v2","created_at":"2026-07-05T01:45:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12344","created_at":"2026-07-05T01:45:45Z"},{"alias_kind":"pith_short_12","alias_value":"ZOLH4YBBXIFU","created_at":"2026-07-05T01:45:45Z"},{"alias_kind":"pith_short_16","alias_value":"ZOLH4YBBXIFUQKNP","created_at":"2026-07-05T01:45:45Z"},{"alias_kind":"pith_short_8","alias_value":"ZOLH4YBB","created_at":"2026-07-05T01:45:45Z"}],"graph_snapshots":[{"event_id":"sha256:81abde06001403fbde44fbb3132ba5618d626ac4114bbb728db62dd460e13e89","target":"graph","created_at":"2026-07-05T01:45:45Z","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/2009.12344/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detection of some types of toxic language is hampered by extreme scarcity of labeled training data. Data augmentation - generating new synthetic data from a labeled seed dataset - can help. The efficacy of data augmentation on toxic language classification has not been fully explored. We present the first systematic study on how data augmentation techniques impact performance across toxic language classifiers, ranging from shallow logistic regression architectures to BERT - a state-of-the-art pre-trained Transformer network. We compare the performance of eight techniques on very scarce seed da","authors_text":"Adrian Flanagan, Mika Juuti, N. Asokan, Tommi Gr\\\"ondahl","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-25T17:04:17Z","title":"A little goes a long way: Improving toxic language classification despite data scarcity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12344","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:d39685b0dcd5d265b9b36ba88d9ed3aac3c4500cd47f015400eeb17c2a237c3d","target":"record","created_at":"2026-07-05T01:45:45Z","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":"9726c8de4cb7bbbddcd3710b81f8a69d321f1ac6c7283d09079116e4f4fab2a7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-25T17:04:17Z","title_canon_sha256":"6b5693850f7f3dbbbee029ffe92531fd795d0ece088c0a53a113e771c659ecd9"},"schema_version":"1.0","source":{"id":"2009.12344","kind":"arxiv","version":2}},"canonical_sha256":"cb967e6021ba0b4829af072a4d323ffe5f3d652e914b3f8d947befec437a1185","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb967e6021ba0b4829af072a4d323ffe5f3d652e914b3f8d947befec437a1185","first_computed_at":"2026-07-05T01:45:45.186115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:45.186115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7IrlE5Q5MRhiHB2GWmGh3Q208i6gvVlopNdVFgFm4IY2GEZdyHVZdZisDTrxBXekyqvYjrdkFi/Cwblmja7uAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:45.186520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.12344","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d39685b0dcd5d265b9b36ba88d9ed3aac3c4500cd47f015400eeb17c2a237c3d","sha256:81abde06001403fbde44fbb3132ba5618d626ac4114bbb728db62dd460e13e89"],"state_sha256":"c1a52e7e204d252d3897e1a336f06701d04d60ab6caad6bca47ff2f14fe21aeb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I1bxadIz4hJyU9tkUhCLhq2CPuvGpMp/rfeKzx+eWwRjdMe4ZQvRnNNtq5p+3K9nGmfZy+bmkzab0U356sCdCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T01:03:28.622430Z","bundle_sha256":"9387bae94652ec62a9338ed0bbcb9c2fe5259f3458dc64805e87195aa80733a9"}}