{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EYYQ5HGSNICRBV3U4KSZANP2ZI","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":"c7324f1d14d408fc9da64947c8b68c777ec12635a29ee4bc7567b88cdb3accbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T14:00:17Z","title_canon_sha256":"ac68e24515fd2d8cc205d2fd91d9d23ffb5a52aac25e1b0f9a87cdb5514245a6"},"schema_version":"1.0","source":{"id":"2509.02332","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02332","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02332v1","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02332","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"pith_short_12","alias_value":"EYYQ5HGSNICR","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"pith_short_16","alias_value":"EYYQ5HGSNICRBV3U","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"pith_short_8","alias_value":"EYYQ5HGS","created_at":"2026-07-05T12:03:36Z"}],"graph_snapshots":[{"event_id":"sha256:0cd1a25e2ad8e7c113e86fe0e9be96076c3e0e14b2a74f45726d7f1beba4d1f3","target":"graph","created_at":"2026-07-05T12:03:36Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.02332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Aleksi Avela, Pauliina Ilmonen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T14:00:17Z","title":"Extrapolated Markov Chain Oversampling Method for Imbalanced Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02332","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":"sha256:14647fed29a84d3892e910e74c44d9f8f6a38e06911a46fdf141d5580bbcf67b","target":"record","created_at":"2026-07-05T12:03:36Z","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":"c7324f1d14d408fc9da64947c8b68c777ec12635a29ee4bc7567b88cdb3accbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T14:00:17Z","title_canon_sha256":"ac68e24515fd2d8cc205d2fd91d9d23ffb5a52aac25e1b0f9a87cdb5514245a6"},"schema_version":"1.0","source":{"id":"2509.02332","kind":"arxiv","version":1}},"canonical_sha256":"26310e9cd26a0510d774e2a59035faca35c54c9b6be179adeb57cf06f729f9e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26310e9cd26a0510d774e2a59035faca35c54c9b6be179adeb57cf06f729f9e5","first_computed_at":"2026-07-05T12:03:36.440110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:36.440110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"onAUd88K4GoR9BfTS05v91J3PTgsLVFaOaGf4t1fgCLNmu5KdShYiDWM2c38mn5c/ft2nPP96aTGk4svltMIAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:36.440604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02332","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14647fed29a84d3892e910e74c44d9f8f6a38e06911a46fdf141d5580bbcf67b","sha256:0cd1a25e2ad8e7c113e86fe0e9be96076c3e0e14b2a74f45726d7f1beba4d1f3"],"state_sha256":"90061542fcc014326cfb19d6eb1101d7418f03e5cc783bd7a97c99d5a9da2453"}