{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LD73YBG6UH5POV7OO5IDINUK6O","short_pith_number":"pith:LD73YBG6","schema_version":"1.0","canonical_sha256":"58ffbc04dea1faf757ee775034368af3aa677b4db65cb77b0743f9c816d0f26f","source":{"kind":"arxiv","id":"2309.15187","version":1},"attestation_state":"computed","paper":{"title":"Monitoring Machine Learning Models: Online Detection of Relevant Deviations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Florian Heinrichs","submitted_at":"2023-09-26T18:46:37Z","abstract_excerpt":"Machine learning models are essential tools in various domains, but their performance can degrade over time due to changes in data distribution or other factors. On one hand, detecting and addressing such degradations is crucial for maintaining the models' reliability. On the other hand, given enough data, any arbitrary small change of quality can be detected. As interventions, such as model re-training or replacement, can be expensive, we argue that they should only be carried out when changes exceed a given threshold. We propose a sequential monitoring scheme to detect these relevant changes"},"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":"2309.15187","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-26T18:46:37Z","cross_cats_sorted":["stat.AP","stat.ML"],"title_canon_sha256":"e3efaf28fbe995b790d2d148b46026f6fbb92657ce1f5cc4345f83535dc46e7a","abstract_canon_sha256":"4b46432737e11788d70ecfef936bd36d75a806d817087780f0837d14d7637956"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:42.228698Z","signature_b64":"EbQ/m18EcVhZNImaGP4bCK5NcA5Ci47dLucfmOyjpRM50KVTLFeN4AWwJhWC9UTLHQqL8qk/QO14DvxwELuzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58ffbc04dea1faf757ee775034368af3aa677b4db65cb77b0743f9c816d0f26f","last_reissued_at":"2026-07-05T06:54:42.228273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:42.228273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monitoring Machine Learning Models: Online Detection of Relevant Deviations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Florian Heinrichs","submitted_at":"2023-09-26T18:46:37Z","abstract_excerpt":"Machine learning models are essential tools in various domains, but their performance can degrade over time due to changes in data distribution or other factors. On one hand, detecting and addressing such degradations is crucial for maintaining the models' reliability. On the other hand, given enough data, any arbitrary small change of quality can be detected. As interventions, such as model re-training or replacement, can be expensive, we argue that they should only be carried out when changes exceed a given threshold. We propose a sequential monitoring scheme to detect these relevant changes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15187","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/2309.15187/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":"2309.15187","created_at":"2026-07-05T06:54:42.228332+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15187v1","created_at":"2026-07-05T06:54:42.228332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15187","created_at":"2026-07-05T06:54:42.228332+00:00"},{"alias_kind":"pith_short_12","alias_value":"LD73YBG6UH5P","created_at":"2026-07-05T06:54:42.228332+00:00"},{"alias_kind":"pith_short_16","alias_value":"LD73YBG6UH5POV7O","created_at":"2026-07-05T06:54:42.228332+00:00"},{"alias_kind":"pith_short_8","alias_value":"LD73YBG6","created_at":"2026-07-05T06:54:42.228332+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.07112","citing_title":"Self-Normalization for CUSUM-based Change Detection in Locally Stationary Time Series","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LD73YBG6UH5POV7OO5IDINUK6O","json":"https://pith.science/pith/LD73YBG6UH5POV7OO5IDINUK6O.json","graph_json":"https://pith.science/api/pith-number/LD73YBG6UH5POV7OO5IDINUK6O/graph.json","events_json":"https://pith.science/api/pith-number/LD73YBG6UH5POV7OO5IDINUK6O/events.json","paper":"https://pith.science/paper/LD73YBG6"},"agent_actions":{"view_html":"https://pith.science/pith/LD73YBG6UH5POV7OO5IDINUK6O","download_json":"https://pith.science/pith/LD73YBG6UH5POV7OO5IDINUK6O.json","view_paper":"https://pith.science/paper/LD73YBG6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15187&json=true","fetch_graph":"https://pith.science/api/pith-number/LD73YBG6UH5POV7OO5IDINUK6O/graph.json","fetch_events":"https://pith.science/api/pith-number/LD73YBG6UH5POV7OO5IDINUK6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LD73YBG6UH5POV7OO5IDINUK6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LD73YBG6UH5POV7OO5IDINUK6O/action/storage_attestation","attest_author":"https://pith.science/pith/LD73YBG6UH5POV7OO5IDINUK6O/action/author_attestation","sign_citation":"https://pith.science/pith/LD73YBG6UH5POV7OO5IDINUK6O/action/citation_signature","submit_replication":"https://pith.science/pith/LD73YBG6UH5POV7OO5IDINUK6O/action/replication_record"}},"created_at":"2026-07-05T06:54:42.228332+00:00","updated_at":"2026-07-05T06:54:42.228332+00:00"}