{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XGI6TVYBBADFT6WFVBSE3E5CE2","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":"6def5f5175b699698b1da520a3b8f6e72ef3537cbf66302ff24db9829b8aad40","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T19:31:20Z","title_canon_sha256":"767fa3afd37f68dec1a1251a4994076cceac46e2e5e98d817cef65775d902924"},"schema_version":"1.0","source":{"id":"2409.03046","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03046","created_at":"2026-07-05T09:03:25Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03046v1","created_at":"2026-07-05T09:03:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03046","created_at":"2026-07-05T09:03:25Z"},{"alias_kind":"pith_short_12","alias_value":"XGI6TVYBBADF","created_at":"2026-07-05T09:03:25Z"},{"alias_kind":"pith_short_16","alias_value":"XGI6TVYBBADFT6WF","created_at":"2026-07-05T09:03:25Z"},{"alias_kind":"pith_short_8","alias_value":"XGI6TVYB","created_at":"2026-07-05T09:03:25Z"}],"graph_snapshots":[{"event_id":"sha256:808f2c468f92e9c48d337a32c0dabb419eb3bd4a6c38647fabbb476a8979db06","target":"graph","created_at":"2026-07-05T09:03:25Z","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/2409.03046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a new method to detect anomalies in texts (in general: in sequences of any data), using language models, in a totally unsupervised manner. The method considers probabilities (likelihoods) generated by a language model, but instead of focusing on low-likelihood tokens, it considers a new metric introduced in this paper: oddballness. Oddballness measures how ``strange'' a given token is according to the language model. We demonstrate in grammatical error detection tasks (a specific case of text anomaly detection) that oddballness is better than just considering low-likelihood events, ","authors_text":"Filip Grali\\'nski, Krzysztof Jurkiewicz, Ryszard Staruch","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T19:31:20Z","title":"Oddballness: universal anomaly detection with language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03046","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":"sha256:223b6ab69568dd10e0508cd528c29fa9ade72edc50fae5da583a83687a6ba9b8","target":"record","created_at":"2026-07-05T09:03:25Z","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":"6def5f5175b699698b1da520a3b8f6e72ef3537cbf66302ff24db9829b8aad40","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T19:31:20Z","title_canon_sha256":"767fa3afd37f68dec1a1251a4994076cceac46e2e5e98d817cef65775d902924"},"schema_version":"1.0","source":{"id":"2409.03046","kind":"arxiv","version":1}},"canonical_sha256":"b991e9d701080659fac5a8644d93a226ba91e0c9b2ff870fd7b509807026401d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b991e9d701080659fac5a8644d93a226ba91e0c9b2ff870fd7b509807026401d","first_computed_at":"2026-07-05T09:03:25.417302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:25.417302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fV6DVguQbBBcDwcDD+OV9ze4+wPrfI1Iy+mgyH96n2qoIS1mRnZ/ODqdA2YwoiZqB44K1vv380ab8Bp4EL7TDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:25.417789Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.03046","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:223b6ab69568dd10e0508cd528c29fa9ade72edc50fae5da583a83687a6ba9b8","sha256:808f2c468f92e9c48d337a32c0dabb419eb3bd4a6c38647fabbb476a8979db06"],"state_sha256":"01ce9e6b64f23a9c0ad3eb383ed97ad67106f5af6fa7a9165969a6554d01214c"}