{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WSCOY4SDXBLOFBHBDZRZ32VD23","short_pith_number":"pith:WSCOY4SD","canonical_record":{"source":{"id":"2405.08217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T22:10:00Z","cross_cats_sorted":["q-bio.GN","q-bio.QM","stat.ML"],"title_canon_sha256":"3dbd4efb26273183f479653ef5674c1a5605caa3dc310c03b4511c985fa7230a","abstract_canon_sha256":"7c9e3e5edbece26da9888f0c61b647e358236baa0a5da46d41736112225c78f6"},"schema_version":"1.0"},"canonical_sha256":"b484ec7243b856e284e11e639deaa3d6c0f18235762457ed473d6283c9717fc3","source":{"kind":"arxiv","id":"2405.08217","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08217","created_at":"2026-07-05T08:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08217v1","created_at":"2026-07-05T08:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08217","created_at":"2026-07-05T08:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"WSCOY4SDXBLO","created_at":"2026-07-05T08:18:57Z"},{"alias_kind":"pith_short_16","alias_value":"WSCOY4SDXBLOFBHB","created_at":"2026-07-05T08:18:57Z"},{"alias_kind":"pith_short_8","alias_value":"WSCOY4SD","created_at":"2026-07-05T08:18:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WSCOY4SDXBLOFBHBDZRZ32VD23","target":"record","payload":{"canonical_record":{"source":{"id":"2405.08217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T22:10:00Z","cross_cats_sorted":["q-bio.GN","q-bio.QM","stat.ML"],"title_canon_sha256":"3dbd4efb26273183f479653ef5674c1a5605caa3dc310c03b4511c985fa7230a","abstract_canon_sha256":"7c9e3e5edbece26da9888f0c61b647e358236baa0a5da46d41736112225c78f6"},"schema_version":"1.0"},"canonical_sha256":"b484ec7243b856e284e11e639deaa3d6c0f18235762457ed473d6283c9717fc3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:57.122061Z","signature_b64":"y40RbzcivBiXk1MXfSj/Op8J4sMyEnD62xmSRfLv0yHYwD2/MyaWLl7UQbA81dVs0V226+HByfkTSoIZYeLtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b484ec7243b856e284e11e639deaa3d6c0f18235762457ed473d6283c9717fc3","last_reissued_at":"2026-07-05T08:18:57.121643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:57.121643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.08217","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":"2026-07-05T08:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+RcfGUZpovrAiV/aj3FG32dvRcZwmQEmMrDh2zB77z+FkorX1nAu0YfVtB7Cghcn8oJXrk+jlU5UeafxVDK/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:56:07.052043Z"},"content_sha256":"26bb566110e7f2c7da62da71ed2bb81ae6a07f6d816422c7ed7f475606754aae","schema_version":"1.0","event_id":"sha256:26bb566110e7f2c7da62da71ed2bb81ae6a07f6d816422c7ed7f475606754aae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WSCOY4SDXBLOFBHBDZRZ32VD23","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Valuation with Gradient Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.GN","q-bio.QM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gordon B. Mills, Guanming Wu, Nathaniel J. Evans, Shannon McWeeney, Xubo Song","submitted_at":"2024-05-13T22:10:00Z","abstract_excerpt":"High-quality data is crucial for accurate machine learning and actionable analytics, however, mislabeled or noisy data is a common problem in many domains. Distinguishing low- from high-quality data can be challenging, often requiring expert knowledge and considerable manual intervention. Data Valuation algorithms are a class of methods that seek to quantify the value of each sample in a dataset based on its contribution or importance to a given predictive task. These data values have shown an impressive ability to identify mislabeled observations, and filtering low-value data can boost machin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08217","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/2405.08217/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":"2026-07-05T08:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MdoX41BcBYnPs950YCq/AAU0QHP9GeZdJGhTAvOdfi099HowLGxEy22emhQXERkGeG4biOLwoYesanMAa0vQBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:56:07.052437Z"},"content_sha256":"65c761a1f09ea734d19bba5a433a7d362c410f7ecb441549fb613611c8df1131","schema_version":"1.0","event_id":"sha256:65c761a1f09ea734d19bba5a433a7d362c410f7ecb441549fb613611c8df1131"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WSCOY4SDXBLOFBHBDZRZ32VD23/bundle.json","state_url":"https://pith.science/pith/WSCOY4SDXBLOFBHBDZRZ32VD23/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WSCOY4SDXBLOFBHBDZRZ32VD23/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":"2026-07-08T23:56:07Z","links":{"resolver":"https://pith.science/pith/WSCOY4SDXBLOFBHBDZRZ32VD23","bundle":"https://pith.science/pith/WSCOY4SDXBLOFBHBDZRZ32VD23/bundle.json","state":"https://pith.science/pith/WSCOY4SDXBLOFBHBDZRZ32VD23/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WSCOY4SDXBLOFBHBDZRZ32VD23/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WSCOY4SDXBLOFBHBDZRZ32VD23","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":"7c9e3e5edbece26da9888f0c61b647e358236baa0a5da46d41736112225c78f6","cross_cats_sorted":["q-bio.GN","q-bio.QM","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T22:10:00Z","title_canon_sha256":"3dbd4efb26273183f479653ef5674c1a5605caa3dc310c03b4511c985fa7230a"},"schema_version":"1.0","source":{"id":"2405.08217","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08217","created_at":"2026-07-05T08:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08217v1","created_at":"2026-07-05T08:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08217","created_at":"2026-07-05T08:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"WSCOY4SDXBLO","created_at":"2026-07-05T08:18:57Z"},{"alias_kind":"pith_short_16","alias_value":"WSCOY4SDXBLOFBHB","created_at":"2026-07-05T08:18:57Z"},{"alias_kind":"pith_short_8","alias_value":"WSCOY4SD","created_at":"2026-07-05T08:18:57Z"}],"graph_snapshots":[{"event_id":"sha256:65c761a1f09ea734d19bba5a433a7d362c410f7ecb441549fb613611c8df1131","target":"graph","created_at":"2026-07-05T08:18:57Z","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/2405.08217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality data is crucial for accurate machine learning and actionable analytics, however, mislabeled or noisy data is a common problem in many domains. Distinguishing low- from high-quality data can be challenging, often requiring expert knowledge and considerable manual intervention. Data Valuation algorithms are a class of methods that seek to quantify the value of each sample in a dataset based on its contribution or importance to a given predictive task. These data values have shown an impressive ability to identify mislabeled observations, and filtering low-value data can boost machin","authors_text":"Gordon B. Mills, Guanming Wu, Nathaniel J. Evans, Shannon McWeeney, Xubo Song","cross_cats":["q-bio.GN","q-bio.QM","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T22:10:00Z","title":"Data Valuation with Gradient Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08217","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":"sha256:26bb566110e7f2c7da62da71ed2bb81ae6a07f6d816422c7ed7f475606754aae","target":"record","created_at":"2026-07-05T08:18:57Z","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":"7c9e3e5edbece26da9888f0c61b647e358236baa0a5da46d41736112225c78f6","cross_cats_sorted":["q-bio.GN","q-bio.QM","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T22:10:00Z","title_canon_sha256":"3dbd4efb26273183f479653ef5674c1a5605caa3dc310c03b4511c985fa7230a"},"schema_version":"1.0","source":{"id":"2405.08217","kind":"arxiv","version":1}},"canonical_sha256":"b484ec7243b856e284e11e639deaa3d6c0f18235762457ed473d6283c9717fc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b484ec7243b856e284e11e639deaa3d6c0f18235762457ed473d6283c9717fc3","first_computed_at":"2026-07-05T08:18:57.121643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:57.121643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y40RbzcivBiXk1MXfSj/Op8J4sMyEnD62xmSRfLv0yHYwD2/MyaWLl7UQbA81dVs0V226+HByfkTSoIZYeLtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:57.122061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.08217","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26bb566110e7f2c7da62da71ed2bb81ae6a07f6d816422c7ed7f475606754aae","sha256:65c761a1f09ea734d19bba5a433a7d362c410f7ecb441549fb613611c8df1131"],"state_sha256":"95c4f70bad30ce90ae94cab186b4e7a2764a3b9ab3416ff10f6713578128d77c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UooCqx5wjA+57iZBDA1iKWtErY/jcPua/sR3RKj5jhvp10xWcWfiW8p6HIdU2kxA49HcYhRoCroWy5jgRvrXCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T23:56:07.054506Z","bundle_sha256":"945c0e23750a926ec7fddadbc09bb54d9f585c170c3064acbc3bf9fbe55aabfa"}}