{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:MATEKZG4DQFL4IUOMOAUVQG2XB","short_pith_number":"pith:MATEKZG4","canonical_record":{"source":{"id":"1707.01780","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-06T13:31:13Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"eb75b6d51de9ae01c465eecf44ea0929dfc002272491c501a43dcf81dab35fe7","abstract_canon_sha256":"ab1f9be507f036c44841b29fd95d16f05c2ae65129f872736acb9dfcc03064cf"},"schema_version":"1.0"},"canonical_sha256":"60264564dc1c0abe228e63814ac0dab8512d617edd178f94c4553a8d00cd7746","source":{"kind":"arxiv","id":"1707.01780","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.01780","created_at":"2026-05-18T00:07:28Z"},{"alias_kind":"arxiv_version","alias_value":"1707.01780v3","created_at":"2026-05-18T00:07:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.01780","created_at":"2026-05-18T00:07:28Z"},{"alias_kind":"pith_short_12","alias_value":"MATEKZG4DQFL","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MATEKZG4DQFL4IUO","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MATEKZG4","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:MATEKZG4DQFL4IUOMOAUVQG2XB","target":"record","payload":{"canonical_record":{"source":{"id":"1707.01780","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-06T13:31:13Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"eb75b6d51de9ae01c465eecf44ea0929dfc002272491c501a43dcf81dab35fe7","abstract_canon_sha256":"ab1f9be507f036c44841b29fd95d16f05c2ae65129f872736acb9dfcc03064cf"},"schema_version":"1.0"},"canonical_sha256":"60264564dc1c0abe228e63814ac0dab8512d617edd178f94c4553a8d00cd7746","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:28.350715Z","signature_b64":"6g+ordQlUiNAvs3OLrgPWdiyvXjAayTrcKpiXprfouDsLd0eqdbt/V7uSdg+A8Nh1sZdV7jkaBLDUqDTv4vKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60264564dc1c0abe228e63814ac0dab8512d617edd178f94c4553a8d00cd7746","last_reissued_at":"2026-05-18T00:07:28.350185Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:28.350185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.01780","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EE1UZ8VJ/clhCtHujpKXDDQNm3gdSvjRLpYfIH2fGnXD7ueT/m6nsx9oJRiTh7k8UhJtmZUJfJn4QegjmM6NBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:44:13.560513Z"},"content_sha256":"f225c17d842195f8f4b71927c2c24028d3a54bfc092794063b3f7e4196b9d1df","schema_version":"1.0","event_id":"sha256:f225c17d842195f8f4b71927c2c24028d3a54bfc092794063b3f7e4196b9d1df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:MATEKZG4DQFL4IUOMOAUVQG2XB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jose Camacho-Collados, Mohammad Taher Pilehvar","submitted_at":"2017-07-06T13:31:13Z","abstract_excerpt":"Text preprocessing is often the first step in the pipeline of a Natural Language Processing (NLP) system, with potential impact in its final performance. Despite its importance, text preprocessing has not received much attention in the deep learning literature. In this paper we investigate the impact of simple text preprocessing decisions (particularly tokenizing, lemmatizing, lowercasing and multiword grouping) on the performance of a standard neural text classifier. We perform an extensive evaluation on standard benchmarks from text categorization and sentiment analysis. While our experiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.01780","kind":"arxiv","version":3},"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":"2026-05-18T00:07:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v7JU4LPRYYIv9LrUa505k7tI/Bp5qIIUsmDqUVQG60DcaT5jsyv9XQ9J4eZlD30fmd/eMYSaDaLyYG0+EpVVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:44:13.561131Z"},"content_sha256":"cdf08602dcc3618afb9aec7a05494f8ed9185cc5bc444e92fcdf6ddbde9c2652","schema_version":"1.0","event_id":"sha256:cdf08602dcc3618afb9aec7a05494f8ed9185cc5bc444e92fcdf6ddbde9c2652"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MATEKZG4DQFL4IUOMOAUVQG2XB/bundle.json","state_url":"https://pith.science/pith/MATEKZG4DQFL4IUOMOAUVQG2XB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MATEKZG4DQFL4IUOMOAUVQG2XB/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":"2026-08-10T08:44:13Z","links":{"resolver":"https://pith.science/pith/MATEKZG4DQFL4IUOMOAUVQG2XB","bundle":"https://pith.science/pith/MATEKZG4DQFL4IUOMOAUVQG2XB/bundle.json","state":"https://pith.science/pith/MATEKZG4DQFL4IUOMOAUVQG2XB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MATEKZG4DQFL4IUOMOAUVQG2XB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:MATEKZG4DQFL4IUOMOAUVQG2XB","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":"ab1f9be507f036c44841b29fd95d16f05c2ae65129f872736acb9dfcc03064cf","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-06T13:31:13Z","title_canon_sha256":"eb75b6d51de9ae01c465eecf44ea0929dfc002272491c501a43dcf81dab35fe7"},"schema_version":"1.0","source":{"id":"1707.01780","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.01780","created_at":"2026-05-18T00:07:28Z"},{"alias_kind":"arxiv_version","alias_value":"1707.01780v3","created_at":"2026-05-18T00:07:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.01780","created_at":"2026-05-18T00:07:28Z"},{"alias_kind":"pith_short_12","alias_value":"MATEKZG4DQFL","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MATEKZG4DQFL4IUO","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MATEKZG4","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:cdf08602dcc3618afb9aec7a05494f8ed9185cc5bc444e92fcdf6ddbde9c2652","target":"graph","created_at":"2026-05-18T00:07:28Z","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":"Text preprocessing is often the first step in the pipeline of a Natural Language Processing (NLP) system, with potential impact in its final performance. Despite its importance, text preprocessing has not received much attention in the deep learning literature. In this paper we investigate the impact of simple text preprocessing decisions (particularly tokenizing, lemmatizing, lowercasing and multiword grouping) on the performance of a standard neural text classifier. We perform an extensive evaluation on standard benchmarks from text categorization and sentiment analysis. While our experiment","authors_text":"Jose Camacho-Collados, Mohammad Taher Pilehvar","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-06T13:31:13Z","title":"On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.01780","kind":"arxiv","version":3},"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:f225c17d842195f8f4b71927c2c24028d3a54bfc092794063b3f7e4196b9d1df","target":"record","created_at":"2026-05-18T00:07:28Z","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":"ab1f9be507f036c44841b29fd95d16f05c2ae65129f872736acb9dfcc03064cf","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-06T13:31:13Z","title_canon_sha256":"eb75b6d51de9ae01c465eecf44ea0929dfc002272491c501a43dcf81dab35fe7"},"schema_version":"1.0","source":{"id":"1707.01780","kind":"arxiv","version":3}},"canonical_sha256":"60264564dc1c0abe228e63814ac0dab8512d617edd178f94c4553a8d00cd7746","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60264564dc1c0abe228e63814ac0dab8512d617edd178f94c4553a8d00cd7746","first_computed_at":"2026-05-18T00:07:28.350185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:28.350185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6g+ordQlUiNAvs3OLrgPWdiyvXjAayTrcKpiXprfouDsLd0eqdbt/V7uSdg+A8Nh1sZdV7jkaBLDUqDTv4vKDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:28.350715Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.01780","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f225c17d842195f8f4b71927c2c24028d3a54bfc092794063b3f7e4196b9d1df","sha256:cdf08602dcc3618afb9aec7a05494f8ed9185cc5bc444e92fcdf6ddbde9c2652"],"state_sha256":"b68068f0654a99e4118ee72c6d92a2073cc525946e8948dc90b01e42b1322d5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tCYN9u84RipKCeX5Wu+8DGbQJhMuijI7mF6CGdIMXq0Z5+nYsN9OjZhSpFvZ38wtyj4zTpaea3kE+eSL/WCiDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:44:13.567982Z","bundle_sha256":"8fbceb3d020969360109b56a8ef8a1267df931abeb86e5d7f0d6df83fb8ead9d"}}