{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FZDMPNTXWMTYFCG5ARMHRMZXVB","short_pith_number":"pith:FZDMPNTX","schema_version":"1.0","canonical_sha256":"2e46c7b677b3278288dd045878b337a85eaf7ee6bf5da0671863ce675fd2e2cb","source":{"kind":"arxiv","id":"1801.04554","version":1},"attestation_state":"computed","paper":{"title":"DCDistance: A Supervised Text Document Feature extraction based on class labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Charles Henrique Porto Ferreira, Debora Maria Rossi de Medeiros, Fabricio Olivetti de Fran\\c{c}a","submitted_at":"2018-01-14T13:28:19Z","abstract_excerpt":"Text Mining is a field that aims at extracting information from textual data. One of the challenges of such field of study comes from the pre-processing stage in which a vector (and structured) representation should be extracted from unstructured data. The common extraction creates large and sparse vectors representing the importance of each term to a document. As such, this usually leads to the curse-of-dimensionality that plagues most machine learning algorithms. To cope with this issue, in this paper we propose a new supervised feature extraction and reduction algorithm, named DCDistance, t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1801.04554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-01-14T13:28:19Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"67a838a60db80fe6a369d912e67f6fd3c6f3d5b23d580b7a6099555ff65fa1f1","abstract_canon_sha256":"62c06f8a56935e75bd8be9b93e39f46b2186a79f88efc1147fc244d7d68b3f57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:04.045643Z","signature_b64":"8xg5s0aiQ/Elg6WZh+o62PunyZ15RDLmSh823M/LMbw6cfVz1m9/AAp9ys/4WkkmaS0FNcNME/v/p6sQBZvxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e46c7b677b3278288dd045878b337a85eaf7ee6bf5da0671863ce675fd2e2cb","last_reissued_at":"2026-05-18T00:26:04.044928Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:04.044928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DCDistance: A Supervised Text Document Feature extraction based on class labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Charles Henrique Porto Ferreira, Debora Maria Rossi de Medeiros, Fabricio Olivetti de Fran\\c{c}a","submitted_at":"2018-01-14T13:28:19Z","abstract_excerpt":"Text Mining is a field that aims at extracting information from textual data. One of the challenges of such field of study comes from the pre-processing stage in which a vector (and structured) representation should be extracted from unstructured data. The common extraction creates large and sparse vectors representing the importance of each term to a document. As such, this usually leads to the curse-of-dimensionality that plagues most machine learning algorithms. To cope with this issue, in this paper we propose a new supervised feature extraction and reduction algorithm, named DCDistance, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.04554","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1801.04554","created_at":"2026-05-18T00:26:04.045044+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.04554v1","created_at":"2026-05-18T00:26:04.045044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.04554","created_at":"2026-05-18T00:26:04.045044+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZDMPNTXWMTY","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZDMPNTXWMTYFCG5","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZDMPNTX","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB","json":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB.json","graph_json":"https://pith.science/api/pith-number/FZDMPNTXWMTYFCG5ARMHRMZXVB/graph.json","events_json":"https://pith.science/api/pith-number/FZDMPNTXWMTYFCG5ARMHRMZXVB/events.json","paper":"https://pith.science/paper/FZDMPNTX"},"agent_actions":{"view_html":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB","download_json":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB.json","view_paper":"https://pith.science/paper/FZDMPNTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.04554&json=true","fetch_graph":"https://pith.science/api/pith-number/FZDMPNTXWMTYFCG5ARMHRMZXVB/graph.json","fetch_events":"https://pith.science/api/pith-number/FZDMPNTXWMTYFCG5ARMHRMZXVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB/action/storage_attestation","attest_author":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB/action/author_attestation","sign_citation":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB/action/citation_signature","submit_replication":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB/action/replication_record"}},"created_at":"2026-05-18T00:26:04.045044+00:00","updated_at":"2026-05-18T00:26:04.045044+00:00"}