{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZVQ6IK4HD5TTUQXYNU36B5CUTO","short_pith_number":"pith:ZVQ6IK4H","canonical_record":{"source":{"id":"2412.05882","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T10:15:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f95d7842f9d6f3b1e01aa72f9662a3dc1d3e755609a354eb82998f853df3179","abstract_canon_sha256":"a6acfec39d2cb56836b381b10a9a484be1c1fdf5e23c413118a0fe9371f1dd77"},"schema_version":"1.0"},"canonical_sha256":"cd61e42b871f673a42f86d37e0f4549bbcfbb2da95cc7de15526f03cfc7653b8","source":{"kind":"arxiv","id":"2412.05882","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05882","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05882v1","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05882","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZVQ6IK4HD5TT","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"pith_short_16","alias_value":"ZVQ6IK4HD5TTUQXY","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"pith_short_8","alias_value":"ZVQ6IK4H","created_at":"2026-07-05T09:46:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZVQ6IK4HD5TTUQXYNU36B5CUTO","target":"record","payload":{"canonical_record":{"source":{"id":"2412.05882","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T10:15:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f95d7842f9d6f3b1e01aa72f9662a3dc1d3e755609a354eb82998f853df3179","abstract_canon_sha256":"a6acfec39d2cb56836b381b10a9a484be1c1fdf5e23c413118a0fe9371f1dd77"},"schema_version":"1.0"},"canonical_sha256":"cd61e42b871f673a42f86d37e0f4549bbcfbb2da95cc7de15526f03cfc7653b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:11.091644Z","signature_b64":"HQB8UxKrpAf+cHCqB/OAI2oR1uLzpETMVUHP44jM5OdkJxkACvLyBXUy+DvYafnGcDLKgC58ufX82OsZm7mvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd61e42b871f673a42f86d37e0f4549bbcfbb2da95cc7de15526f03cfc7653b8","last_reissued_at":"2026-07-05T09:46:11.091219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:11.091219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.05882","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:46:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EkeTcIVMOd4CkPBKhKdITA28QyNTMTI/hD/4Su8hQLPNyaXBRRvgNO+s/m3Vl1frIR4n6FIwWrnOxp82by1mCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T08:30:33.953998Z"},"content_sha256":"87c8cb0b659dc93dc37e7a829c2d09ddd3bf65b193a39014d17e73c491ee6289","schema_version":"1.0","event_id":"sha256:87c8cb0b659dc93dc37e7a829c2d09ddd3bf65b193a39014d17e73c491ee6289"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZVQ6IK4HD5TTUQXYNU36B5CUTO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Modeling Data Quality and Machine Learning Model Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chris Trentman, Elrod Caden, Justin Zhan, Usman Anjum","submitted_at":"2024-12-08T10:15:10Z","abstract_excerpt":"Understanding the effect of uncertainty and noise in data on machine learning models (MLM) is crucial in developing trust and measuring performance. In this paper, a new model is proposed to quantify uncertainties and noise in data on MLMs. Using the concept of signal-to-noise ratio (SNR), a new metric called deterministic-non-deterministic ratio (DDR) is proposed to formulate performance of a model. Using synthetic data in experiments, we show how accuracy can change with DDR and how we can use DDR-accuracy curves to determine performance of a model."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05882","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/2412.05882/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:46:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7IJ9SazacdhNEOW29XzMRyLTM23Ey7nIEy4un3MBtl0OOHqo8/W7U3lpSDNdNixRks/U/8Cq1bXJqRPZnLOXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T08:30:33.954842Z"},"content_sha256":"c58fd8c06891824b49e9ccbc569f0ce019839ae6eac66c6fddb7fde1bc27d7a9","schema_version":"1.0","event_id":"sha256:c58fd8c06891824b49e9ccbc569f0ce019839ae6eac66c6fddb7fde1bc27d7a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZVQ6IK4HD5TTUQXYNU36B5CUTO/bundle.json","state_url":"https://pith.science/pith/ZVQ6IK4HD5TTUQXYNU36B5CUTO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZVQ6IK4HD5TTUQXYNU36B5CUTO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T08:30:33Z","links":{"resolver":"https://pith.science/pith/ZVQ6IK4HD5TTUQXYNU36B5CUTO","bundle":"https://pith.science/pith/ZVQ6IK4HD5TTUQXYNU36B5CUTO/bundle.json","state":"https://pith.science/pith/ZVQ6IK4HD5TTUQXYNU36B5CUTO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZVQ6IK4HD5TTUQXYNU36B5CUTO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZVQ6IK4HD5TTUQXYNU36B5CUTO","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":"a6acfec39d2cb56836b381b10a9a484be1c1fdf5e23c413118a0fe9371f1dd77","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T10:15:10Z","title_canon_sha256":"8f95d7842f9d6f3b1e01aa72f9662a3dc1d3e755609a354eb82998f853df3179"},"schema_version":"1.0","source":{"id":"2412.05882","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05882","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05882v1","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05882","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZVQ6IK4HD5TT","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"pith_short_16","alias_value":"ZVQ6IK4HD5TTUQXY","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"pith_short_8","alias_value":"ZVQ6IK4H","created_at":"2026-07-05T09:46:11Z"}],"graph_snapshots":[{"event_id":"sha256:c58fd8c06891824b49e9ccbc569f0ce019839ae6eac66c6fddb7fde1bc27d7a9","target":"graph","created_at":"2026-07-05T09:46:11Z","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/2412.05882/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the effect of uncertainty and noise in data on machine learning models (MLM) is crucial in developing trust and measuring performance. In this paper, a new model is proposed to quantify uncertainties and noise in data on MLMs. Using the concept of signal-to-noise ratio (SNR), a new metric called deterministic-non-deterministic ratio (DDR) is proposed to formulate performance of a model. Using synthetic data in experiments, we show how accuracy can change with DDR and how we can use DDR-accuracy curves to determine performance of a model.","authors_text":"Chris Trentman, Elrod Caden, Justin Zhan, Usman Anjum","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T10:15:10Z","title":"Towards Modeling Data Quality and Machine Learning Model Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05882","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":"sha256:87c8cb0b659dc93dc37e7a829c2d09ddd3bf65b193a39014d17e73c491ee6289","target":"record","created_at":"2026-07-05T09:46:11Z","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":"a6acfec39d2cb56836b381b10a9a484be1c1fdf5e23c413118a0fe9371f1dd77","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T10:15:10Z","title_canon_sha256":"8f95d7842f9d6f3b1e01aa72f9662a3dc1d3e755609a354eb82998f853df3179"},"schema_version":"1.0","source":{"id":"2412.05882","kind":"arxiv","version":1}},"canonical_sha256":"cd61e42b871f673a42f86d37e0f4549bbcfbb2da95cc7de15526f03cfc7653b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd61e42b871f673a42f86d37e0f4549bbcfbb2da95cc7de15526f03cfc7653b8","first_computed_at":"2026-07-05T09:46:11.091219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:11.091219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HQB8UxKrpAf+cHCqB/OAI2oR1uLzpETMVUHP44jM5OdkJxkACvLyBXUy+DvYafnGcDLKgC58ufX82OsZm7mvCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:11.091644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05882","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87c8cb0b659dc93dc37e7a829c2d09ddd3bf65b193a39014d17e73c491ee6289","sha256:c58fd8c06891824b49e9ccbc569f0ce019839ae6eac66c6fddb7fde1bc27d7a9"],"state_sha256":"a505040e8d724fd2c6b69cf7e193b2a476e13348afbf1dfdc50f9ed5cfaa00fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3LiTeQQDge8ZNMpvUjQip4XmyO++8mkORfUH7nihGJQIfT0WtAfllMOKtUQqF3PYVMA40gaDITFKSU2i46XnCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T08:30:33.961074Z","bundle_sha256":"33c18bb2ef98edc058712526803fb59f2e6525164574476104632f2b64b31d5a"}}