{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EYYQ5HGSNICRBV3U4KSZANP2ZI","short_pith_number":"pith:EYYQ5HGS","schema_version":"1.0","canonical_sha256":"26310e9cd26a0510d774e2a59035faca35c54c9b6be179adeb57cf06f729f9e5","source":{"kind":"arxiv","id":"2509.02332","version":1},"attestation_state":"computed","paper":{"title":"Extrapolated Markov Chain Oversampling Method for Imbalanced Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksi Avela, Pauliina Ilmonen","submitted_at":"2025-09-02T14:00:17Z","abstract_excerpt":"Text classification is the task of automatically assigning text documents correct labels from a predefined set of categories. In real-life (text) classification tasks, observations and misclassification costs are often unevenly distributed between the classes - known as the problem of imbalanced data. Synthetic oversampling is a popular approach to imbalanced classification. The idea is to generate synthetic observations in the minority class to balance the classes in the training set. Many general-purpose oversampling methods can be applied to text data; however, imbalanced text data poses a "},"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":"2509.02332","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T14:00:17Z","cross_cats_sorted":[],"title_canon_sha256":"ac68e24515fd2d8cc205d2fd91d9d23ffb5a52aac25e1b0f9a87cdb5514245a6","abstract_canon_sha256":"c7324f1d14d408fc9da64947c8b68c777ec12635a29ee4bc7567b88cdb3accbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:36.440604Z","signature_b64":"onAUd88K4GoR9BfTS05v91J3PTgsLVFaOaGf4t1fgCLNmu5KdShYiDWM2c38mn5c/ft2nPP96aTGk4svltMIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26310e9cd26a0510d774e2a59035faca35c54c9b6be179adeb57cf06f729f9e5","last_reissued_at":"2026-07-05T12:03:36.440110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:36.440110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extrapolated Markov Chain Oversampling Method for Imbalanced Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksi Avela, Pauliina Ilmonen","submitted_at":"2025-09-02T14:00:17Z","abstract_excerpt":"Text classification is the task of automatically assigning text documents correct labels from a predefined set of categories. In real-life (text) classification tasks, observations and misclassification costs are often unevenly distributed between the classes - known as the problem of imbalanced data. Synthetic oversampling is a popular approach to imbalanced classification. The idea is to generate synthetic observations in the minority class to balance the classes in the training set. Many general-purpose oversampling methods can be applied to text data; however, imbalanced text data poses a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02332","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/2509.02332/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.02332","created_at":"2026-07-05T12:03:36.440169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02332v1","created_at":"2026-07-05T12:03:36.440169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02332","created_at":"2026-07-05T12:03:36.440169+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYYQ5HGSNICR","created_at":"2026-07-05T12:03:36.440169+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYYQ5HGSNICRBV3U","created_at":"2026-07-05T12:03:36.440169+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYYQ5HGS","created_at":"2026-07-05T12:03:36.440169+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/EYYQ5HGSNICRBV3U4KSZANP2ZI","json":"https://pith.science/pith/EYYQ5HGSNICRBV3U4KSZANP2ZI.json","graph_json":"https://pith.science/api/pith-number/EYYQ5HGSNICRBV3U4KSZANP2ZI/graph.json","events_json":"https://pith.science/api/pith-number/EYYQ5HGSNICRBV3U4KSZANP2ZI/events.json","paper":"https://pith.science/paper/EYYQ5HGS"},"agent_actions":{"view_html":"https://pith.science/pith/EYYQ5HGSNICRBV3U4KSZANP2ZI","download_json":"https://pith.science/pith/EYYQ5HGSNICRBV3U4KSZANP2ZI.json","view_paper":"https://pith.science/paper/EYYQ5HGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02332&json=true","fetch_graph":"https://pith.science/api/pith-number/EYYQ5HGSNICRBV3U4KSZANP2ZI/graph.json","fetch_events":"https://pith.science/api/pith-number/EYYQ5HGSNICRBV3U4KSZANP2ZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYYQ5HGSNICRBV3U4KSZANP2ZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYYQ5HGSNICRBV3U4KSZANP2ZI/action/storage_attestation","attest_author":"https://pith.science/pith/EYYQ5HGSNICRBV3U4KSZANP2ZI/action/author_attestation","sign_citation":"https://pith.science/pith/EYYQ5HGSNICRBV3U4KSZANP2ZI/action/citation_signature","submit_replication":"https://pith.science/pith/EYYQ5HGSNICRBV3U4KSZANP2ZI/action/replication_record"}},"created_at":"2026-07-05T12:03:36.440169+00:00","updated_at":"2026-07-05T12:03:36.440169+00:00"}