{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FZDMPNTXWMTYFCG5ARMHRMZXVB","short_pith_number":"pith:FZDMPNTX","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"},"canonical_sha256":"2e46c7b677b3278288dd045878b337a85eaf7ee6bf5da0671863ce675fd2e2cb","source":{"kind":"arxiv","id":"1801.04554","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.04554","created_at":"2026-05-18T00:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"1801.04554v1","created_at":"2026-05-18T00:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.04554","created_at":"2026-05-18T00:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"FZDMPNTXWMTY","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FZDMPNTXWMTYFCG5","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FZDMPNTX","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FZDMPNTXWMTYFCG5ARMHRMZXVB","target":"record","payload":{"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"},"canonical_sha256":"2e46c7b677b3278288dd045878b337a85eaf7ee6bf5da0671863ce675fd2e2cb","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"},"source_kind":"arxiv","source_id":"1801.04554","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":"2026-05-18T00:26:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E94Tn8oUGFUWm/7jOLYcFWdA1Le7umHV8uFowZa8+pg+1v6sXIuqI3uisqWtkT+Hp2bxTXmE4SxKNEJgxZioBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T22:46:16.914092Z"},"content_sha256":"513269a78ab5a92a16295eca975fee458c6667d952929e91f415f99160221bab","schema_version":"1.0","event_id":"sha256:513269a78ab5a92a16295eca975fee458c6667d952929e91f415f99160221bab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FZDMPNTXWMTYFCG5ARMHRMZXVB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:26:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fx8b/vTkZ7frMuUqLTqAvZF9ESjPHT2lsXkHYLqJNrNv4OJfI8Fl+2p1lgUZONcIARtXUKwI9NSDrvWRjO3tAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T22:46:16.914453Z"},"content_sha256":"d3ba6b573298554f6705014e1ea6f5d283e267efe886145865cf6119ec0e286e","schema_version":"1.0","event_id":"sha256:d3ba6b573298554f6705014e1ea6f5d283e267efe886145865cf6119ec0e286e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB/bundle.json","state_url":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB/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":"2026-07-08T22:46:16Z","links":{"resolver":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB","bundle":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB/bundle.json","state":"https://pith.science/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FZDMPNTXWMTYFCG5ARMHRMZXVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FZDMPNTXWMTYFCG5ARMHRMZXVB","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":"62c06f8a56935e75bd8be9b93e39f46b2186a79f88efc1147fc244d7d68b3f57","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-01-14T13:28:19Z","title_canon_sha256":"67a838a60db80fe6a369d912e67f6fd3c6f3d5b23d580b7a6099555ff65fa1f1"},"schema_version":"1.0","source":{"id":"1801.04554","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.04554","created_at":"2026-05-18T00:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"1801.04554v1","created_at":"2026-05-18T00:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.04554","created_at":"2026-05-18T00:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"FZDMPNTXWMTY","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FZDMPNTXWMTYFCG5","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FZDMPNTX","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:d3ba6b573298554f6705014e1ea6f5d283e267efe886145865cf6119ec0e286e","target":"graph","created_at":"2026-05-18T00:26:04Z","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 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","authors_text":"Charles Henrique Porto Ferreira, Debora Maria Rossi de Medeiros, Fabricio Olivetti de Fran\\c{c}a","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-01-14T13:28:19Z","title":"DCDistance: A Supervised Text Document Feature extraction based on class labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.04554","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":"sha256:513269a78ab5a92a16295eca975fee458c6667d952929e91f415f99160221bab","target":"record","created_at":"2026-05-18T00:26:04Z","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":"62c06f8a56935e75bd8be9b93e39f46b2186a79f88efc1147fc244d7d68b3f57","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-01-14T13:28:19Z","title_canon_sha256":"67a838a60db80fe6a369d912e67f6fd3c6f3d5b23d580b7a6099555ff65fa1f1"},"schema_version":"1.0","source":{"id":"1801.04554","kind":"arxiv","version":1}},"canonical_sha256":"2e46c7b677b3278288dd045878b337a85eaf7ee6bf5da0671863ce675fd2e2cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e46c7b677b3278288dd045878b337a85eaf7ee6bf5da0671863ce675fd2e2cb","first_computed_at":"2026-05-18T00:26:04.044928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:26:04.044928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8xg5s0aiQ/Elg6WZh+o62PunyZ15RDLmSh823M/LMbw6cfVz1m9/AAp9ys/4WkkmaS0FNcNME/v/p6sQBZvxAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:26:04.045643Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.04554","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:513269a78ab5a92a16295eca975fee458c6667d952929e91f415f99160221bab","sha256:d3ba6b573298554f6705014e1ea6f5d283e267efe886145865cf6119ec0e286e"],"state_sha256":"63d68b5e64334000d251132aab8aa7ea6f22c19dcdaed31325616ba95edf67b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SmdwE5mTytOJI1jKJoDV04dfvF5AO/n3bCkxeliLX6FN/gsp7LVMku7EL8+011j48kQsMCFg0FAagtxx4yPsBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T22:46:16.916393Z","bundle_sha256":"6c1e6dff92c76b60e9a7787965c1334160d7b1147158f7e858afbae410b01956"}}