{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7K7KQWZCO4ZSWHTKWNSER45JYL","short_pith_number":"pith:7K7KQWZC","canonical_record":{"source":{"id":"2210.16168","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-28T14:43:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9c9b6ad45c879eb6434541b65286aca1f9cae3476dbbcee9e66880c57f2e7e79","abstract_canon_sha256":"738bf6981335f64effaa4d6636e27b00d61fbd0f9ccb4956b9e977605d0de2ce"},"schema_version":"1.0"},"canonical_sha256":"fabea85b2277332b1e6ab36448f3a9c2c427929706651002ac89b852690c3f5f","source":{"kind":"arxiv","id":"2210.16168","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.16168","created_at":"2026-07-05T05:11:31Z"},{"alias_kind":"arxiv_version","alias_value":"2210.16168v1","created_at":"2026-07-05T05:11:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16168","created_at":"2026-07-05T05:11:31Z"},{"alias_kind":"pith_short_12","alias_value":"7K7KQWZCO4ZS","created_at":"2026-07-05T05:11:31Z"},{"alias_kind":"pith_short_16","alias_value":"7K7KQWZCO4ZSWHTK","created_at":"2026-07-05T05:11:31Z"},{"alias_kind":"pith_short_8","alias_value":"7K7KQWZC","created_at":"2026-07-05T05:11:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7K7KQWZCO4ZSWHTKWNSER45JYL","target":"record","payload":{"canonical_record":{"source":{"id":"2210.16168","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-28T14:43:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9c9b6ad45c879eb6434541b65286aca1f9cae3476dbbcee9e66880c57f2e7e79","abstract_canon_sha256":"738bf6981335f64effaa4d6636e27b00d61fbd0f9ccb4956b9e977605d0de2ce"},"schema_version":"1.0"},"canonical_sha256":"fabea85b2277332b1e6ab36448f3a9c2c427929706651002ac89b852690c3f5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:31.116335Z","signature_b64":"q4pAMyL1fTNmfxzl+d8vDC01lrAuwaODS/MviVoWqABlG3E4VdX7umP4wc0UOrxm8cP3yH+RRLeYhWOFbFpKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fabea85b2277332b1e6ab36448f3a9c2c427929706651002ac89b852690c3f5f","last_reissued_at":"2026-07-05T05:11:31.115931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:31.115931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.16168","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":"2026-07-05T05:11:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Skfl9xUDy83goZItoU0XgnOTC/bB52fWP/C3KNqKIrzZzoS719jhxKwkG2NpKrmB39OmQyZwanW4NyUT26RvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:18:58.911917Z"},"content_sha256":"21cd7a75091a452d42a26caa50f082b9eb4d562beff09d2558ff8421ea948014","schema_version":"1.0","event_id":"sha256:21cd7a75091a452d42a26caa50f082b9eb4d562beff09d2558ff8421ea948014"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7K7KQWZCO4ZSWHTKWNSER45JYL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Feature Engineering vs BERT on Twitter Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Lisa Chalaguine, Ryiaadh Gani","submitted_at":"2022-10-28T14:43:13Z","abstract_excerpt":"In this paper, we compare the performances of traditional machine learning models using feature engineering and word vectors and the state-of-the-art language model BERT using word embeddings on three datasets. We also consider the time and cost efficiency of feature engineering compared to BERT. From our results we conclude that the use of the BERT model was only worth the time and cost trade-off for one of the three datasets we used for comparison, where the BERT model significantly outperformed any kind of traditional classifier that uses feature vectors, instead of embeddings. Using the BE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16168","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/2210.16168/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":"2026-07-05T05:11:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QI3a6jYi8vgBTkj5uE9y+/1w/4/6rTzPdaLClofJNk2Sfd96magS0nzc2AGD8ka3yrcBuycUFPdYP6K9kOO/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:18:58.912525Z"},"content_sha256":"66bff4d539df9a2bda466a995331c25e6e44c3e0adc9c5e22c25549393cc7106","schema_version":"1.0","event_id":"sha256:66bff4d539df9a2bda466a995331c25e6e44c3e0adc9c5e22c25549393cc7106"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7K7KQWZCO4ZSWHTKWNSER45JYL/bundle.json","state_url":"https://pith.science/pith/7K7KQWZCO4ZSWHTKWNSER45JYL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7K7KQWZCO4ZSWHTKWNSER45JYL/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":"2026-08-04T10:18:58Z","links":{"resolver":"https://pith.science/pith/7K7KQWZCO4ZSWHTKWNSER45JYL","bundle":"https://pith.science/pith/7K7KQWZCO4ZSWHTKWNSER45JYL/bundle.json","state":"https://pith.science/pith/7K7KQWZCO4ZSWHTKWNSER45JYL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7K7KQWZCO4ZSWHTKWNSER45JYL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7K7KQWZCO4ZSWHTKWNSER45JYL","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":"738bf6981335f64effaa4d6636e27b00d61fbd0f9ccb4956b9e977605d0de2ce","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-28T14:43:13Z","title_canon_sha256":"9c9b6ad45c879eb6434541b65286aca1f9cae3476dbbcee9e66880c57f2e7e79"},"schema_version":"1.0","source":{"id":"2210.16168","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.16168","created_at":"2026-07-05T05:11:31Z"},{"alias_kind":"arxiv_version","alias_value":"2210.16168v1","created_at":"2026-07-05T05:11:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16168","created_at":"2026-07-05T05:11:31Z"},{"alias_kind":"pith_short_12","alias_value":"7K7KQWZCO4ZS","created_at":"2026-07-05T05:11:31Z"},{"alias_kind":"pith_short_16","alias_value":"7K7KQWZCO4ZSWHTK","created_at":"2026-07-05T05:11:31Z"},{"alias_kind":"pith_short_8","alias_value":"7K7KQWZC","created_at":"2026-07-05T05:11:31Z"}],"graph_snapshots":[{"event_id":"sha256:66bff4d539df9a2bda466a995331c25e6e44c3e0adc9c5e22c25549393cc7106","target":"graph","created_at":"2026-07-05T05:11:31Z","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/2210.16168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we compare the performances of traditional machine learning models using feature engineering and word vectors and the state-of-the-art language model BERT using word embeddings on three datasets. We also consider the time and cost efficiency of feature engineering compared to BERT. From our results we conclude that the use of the BERT model was only worth the time and cost trade-off for one of the three datasets we used for comparison, where the BERT model significantly outperformed any kind of traditional classifier that uses feature vectors, instead of embeddings. Using the BE","authors_text":"Lisa Chalaguine, Ryiaadh Gani","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-28T14:43:13Z","title":"Feature Engineering vs BERT on Twitter Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16168","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":"sha256:21cd7a75091a452d42a26caa50f082b9eb4d562beff09d2558ff8421ea948014","target":"record","created_at":"2026-07-05T05:11:31Z","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":"738bf6981335f64effaa4d6636e27b00d61fbd0f9ccb4956b9e977605d0de2ce","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-28T14:43:13Z","title_canon_sha256":"9c9b6ad45c879eb6434541b65286aca1f9cae3476dbbcee9e66880c57f2e7e79"},"schema_version":"1.0","source":{"id":"2210.16168","kind":"arxiv","version":1}},"canonical_sha256":"fabea85b2277332b1e6ab36448f3a9c2c427929706651002ac89b852690c3f5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fabea85b2277332b1e6ab36448f3a9c2c427929706651002ac89b852690c3f5f","first_computed_at":"2026-07-05T05:11:31.115931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:31.115931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q4pAMyL1fTNmfxzl+d8vDC01lrAuwaODS/MviVoWqABlG3E4VdX7umP4wc0UOrxm8cP3yH+RRLeYhWOFbFpKAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:31.116335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.16168","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21cd7a75091a452d42a26caa50f082b9eb4d562beff09d2558ff8421ea948014","sha256:66bff4d539df9a2bda466a995331c25e6e44c3e0adc9c5e22c25549393cc7106"],"state_sha256":"13e47d8131feb2ba90a7a60259649be7fcfdeb213e64ff80390c268aa898aa0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aDr27qHVoWY/h5YrEUvmhHzmSSkCslHUTQ91XXEqChe3+5GE+OeFIHUK4rKTaHZ+OMYTjq2Oh6qgk4PemeV1BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:18:58.918573Z","bundle_sha256":"14b1de1fd5f915a94d07d815f138a89709c60d65f7a16630205f29e7569bca01"}}