{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LV5O3UZHGWLT7MV2O7LBSPZP35","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":"a59e36a69ca87f0c80beda1529c43f106d180349d00e234ae65f911e341c2414","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-05T11:09:31Z","title_canon_sha256":"0848feeeec7f605d8eafa568ef9d9371931f05282cd247c3694a6c13eb18abc6"},"schema_version":"1.0","source":{"id":"1707.01321","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.01321","created_at":"2026-05-18T00:40:53Z"},{"alias_kind":"arxiv_version","alias_value":"1707.01321v1","created_at":"2026-05-18T00:40:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.01321","created_at":"2026-05-18T00:40:53Z"},{"alias_kind":"pith_short_12","alias_value":"LV5O3UZHGWLT","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LV5O3UZHGWLT7MV2","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LV5O3UZH","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:7667908c76f7bf71bc769d1c979c85601eff0245b7da5a53a4b320cda2262e57","target":"graph","created_at":"2026-05-18T00:40:53Z","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":"In this paper we perform a comparative analysis of three models for feature representation of text documents in the context of document classification. In particular, we consider the most often used family of models bag-of-words, recently proposed continuous space models word2vec and doc2vec, and the model based on the representation of text documents as language networks. While the bag-of-word models have been extensively used for the document classification task, the performance of the other two models for the same task have not been well understood. This is especially true for the network-b","authors_text":"Ljup\\v{c}o Todorovski, Sanda Martin\\v{c}i\\'c-Ip\\v{s}i\\'c, Tanja Mili\\v{c}i\\'c","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-05T11:09:31Z","title":"The Influence of Feature Representation of Text on the Performance of Document Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.01321","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":"sha256:8bf21eac3ecca63e23ed50fcaef3f8a5aef4df51bb31efd1b193aecfe07e01b5","target":"record","created_at":"2026-05-18T00:40:53Z","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":"a59e36a69ca87f0c80beda1529c43f106d180349d00e234ae65f911e341c2414","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-05T11:09:31Z","title_canon_sha256":"0848feeeec7f605d8eafa568ef9d9371931f05282cd247c3694a6c13eb18abc6"},"schema_version":"1.0","source":{"id":"1707.01321","kind":"arxiv","version":1}},"canonical_sha256":"5d7aedd32735973fb2ba77d6193f2fdf6b1d39bebfa54e5a8132120b3c1e5a1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d7aedd32735973fb2ba77d6193f2fdf6b1d39bebfa54e5a8132120b3c1e5a1b","first_computed_at":"2026-05-18T00:40:53.160418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:53.160418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RTAF/RjeiL8FD/PZLuUdKF1TFRdcQklEna1i36mjS25rdkf7nSiV0Tu28xCAcVUHGci34uVSk3vPgvHnI7vuDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:53.160957Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.01321","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bf21eac3ecca63e23ed50fcaef3f8a5aef4df51bb31efd1b193aecfe07e01b5","sha256:7667908c76f7bf71bc769d1c979c85601eff0245b7da5a53a4b320cda2262e57"],"state_sha256":"709fecc0a656d8f2a3c509d8341dadfadfd74bc5df7503570a8a4ba3d6fcf118"}