{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:G4B4RJ3Q5SFU64GJWAWQJPKDYH","short_pith_number":"pith:G4B4RJ3Q","canonical_record":{"source":{"id":"2503.18497","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-24T09:52:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db5052626752ebd1c71154523c31a484b515739ee5bb04b6a68e60c2d4bd184b","abstract_canon_sha256":"34c7ae5d361fe3ea4cd3b30de12bdc2ed496fd453195a2b384874a6f81afc437"},"schema_version":"1.0"},"canonical_sha256":"3703c8a770ec8b4f70c9b02d04bd43c1d882a81ae2122bcbcc2b808b7364915a","source":{"kind":"arxiv","id":"2503.18497","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18497","created_at":"2026-07-05T10:42:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18497v2","created_at":"2026-07-05T10:42:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18497","created_at":"2026-07-05T10:42:45Z"},{"alias_kind":"pith_short_12","alias_value":"G4B4RJ3Q5SFU","created_at":"2026-07-05T10:42:45Z"},{"alias_kind":"pith_short_16","alias_value":"G4B4RJ3Q5SFU64GJ","created_at":"2026-07-05T10:42:45Z"},{"alias_kind":"pith_short_8","alias_value":"G4B4RJ3Q","created_at":"2026-07-05T10:42:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:G4B4RJ3Q5SFU64GJWAWQJPKDYH","target":"record","payload":{"canonical_record":{"source":{"id":"2503.18497","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-24T09:52:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db5052626752ebd1c71154523c31a484b515739ee5bb04b6a68e60c2d4bd184b","abstract_canon_sha256":"34c7ae5d361fe3ea4cd3b30de12bdc2ed496fd453195a2b384874a6f81afc437"},"schema_version":"1.0"},"canonical_sha256":"3703c8a770ec8b4f70c9b02d04bd43c1d882a81ae2122bcbcc2b808b7364915a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:45.207925Z","signature_b64":"V/f1CjDvgS50wbLEGJdTJHJEDmhuSxd41TqPmRMCGLUiy8VPpvFhO9/eERQxonMDx1wKe7z+Ki6aa+Vn8uWBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3703c8a770ec8b4f70c9b02d04bd43c1d882a81ae2122bcbcc2b808b7364915a","last_reissued_at":"2026-07-05T10:42:45.207439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:45.207439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.18497","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:42:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jAh/uN9jWdNyCu9I+shGebuOrl+1POALObDQk3TcJQuXMQjGs+VOGugYI6HJFAkypnoCN4vxR9jUWJgegpiQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:04:42.661220Z"},"content_sha256":"240734c5ae0d116fd14e8f9daa5126a60e77cada6dac2525f4bfc87206d894ac","schema_version":"1.0","event_id":"sha256:240734c5ae0d116fd14e8f9daa5126a60e77cada6dac2525f4bfc87206d894ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:G4B4RJ3Q5SFU64GJWAWQJPKDYH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Statistically Testing Training Data for Unwanted Error Patterns using Rule-Oriented Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Martin Dallinger, Stefan Rass","submitted_at":"2025-03-24T09:52:36Z","abstract_excerpt":"Artificial intelligence models trained from data can only be as good as the underlying data is. Biases in training data propagating through to the output of a machine learning model are a well-documented and well-understood phenomenon, but the machinery to prevent these undesired effects is much less developed. Efforts to ensure data is clean during collection, such as using bias-aware sampling, are most effective when the entity controlling data collection also trains the AI. In cases where the data is already available, how do we find out if the data was already manipulated, i.e., ``poisoned"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18497","kind":"arxiv","version":2},"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/2503.18497/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":"2026-07-05T10:42:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F/Uv2eqeaGCfS6PAQOLFyxEE+iH/aj1/6mwAud1uU85v7AdjsTmeNnBXGJIVZOZ98CGdamnVBFilo4kk3tXKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:04:42.661558Z"},"content_sha256":"056eff0356f3b376ba9b40942b63c616dd1ee12bfb4ee09bd4f90bf201b3463f","schema_version":"1.0","event_id":"sha256:056eff0356f3b376ba9b40942b63c616dd1ee12bfb4ee09bd4f90bf201b3463f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G4B4RJ3Q5SFU64GJWAWQJPKDYH/bundle.json","state_url":"https://pith.science/pith/G4B4RJ3Q5SFU64GJWAWQJPKDYH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G4B4RJ3Q5SFU64GJWAWQJPKDYH/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":"2026-08-14T12:04:42Z","links":{"resolver":"https://pith.science/pith/G4B4RJ3Q5SFU64GJWAWQJPKDYH","bundle":"https://pith.science/pith/G4B4RJ3Q5SFU64GJWAWQJPKDYH/bundle.json","state":"https://pith.science/pith/G4B4RJ3Q5SFU64GJWAWQJPKDYH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G4B4RJ3Q5SFU64GJWAWQJPKDYH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G4B4RJ3Q5SFU64GJWAWQJPKDYH","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":"34c7ae5d361fe3ea4cd3b30de12bdc2ed496fd453195a2b384874a6f81afc437","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-24T09:52:36Z","title_canon_sha256":"db5052626752ebd1c71154523c31a484b515739ee5bb04b6a68e60c2d4bd184b"},"schema_version":"1.0","source":{"id":"2503.18497","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18497","created_at":"2026-07-05T10:42:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18497v2","created_at":"2026-07-05T10:42:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18497","created_at":"2026-07-05T10:42:45Z"},{"alias_kind":"pith_short_12","alias_value":"G4B4RJ3Q5SFU","created_at":"2026-07-05T10:42:45Z"},{"alias_kind":"pith_short_16","alias_value":"G4B4RJ3Q5SFU64GJ","created_at":"2026-07-05T10:42:45Z"},{"alias_kind":"pith_short_8","alias_value":"G4B4RJ3Q","created_at":"2026-07-05T10:42:45Z"}],"graph_snapshots":[{"event_id":"sha256:056eff0356f3b376ba9b40942b63c616dd1ee12bfb4ee09bd4f90bf201b3463f","target":"graph","created_at":"2026-07-05T10:42:45Z","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/2503.18497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Artificial intelligence models trained from data can only be as good as the underlying data is. Biases in training data propagating through to the output of a machine learning model are a well-documented and well-understood phenomenon, but the machinery to prevent these undesired effects is much less developed. Efforts to ensure data is clean during collection, such as using bias-aware sampling, are most effective when the entity controlling data collection also trains the AI. In cases where the data is already available, how do we find out if the data was already manipulated, i.e., ``poisoned","authors_text":"Martin Dallinger, Stefan Rass","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-24T09:52:36Z","title":"Statistically Testing Training Data for Unwanted Error Patterns using Rule-Oriented Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18497","kind":"arxiv","version":2},"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":"sha256:240734c5ae0d116fd14e8f9daa5126a60e77cada6dac2525f4bfc87206d894ac","target":"record","created_at":"2026-07-05T10:42:45Z","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":"34c7ae5d361fe3ea4cd3b30de12bdc2ed496fd453195a2b384874a6f81afc437","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-24T09:52:36Z","title_canon_sha256":"db5052626752ebd1c71154523c31a484b515739ee5bb04b6a68e60c2d4bd184b"},"schema_version":"1.0","source":{"id":"2503.18497","kind":"arxiv","version":2}},"canonical_sha256":"3703c8a770ec8b4f70c9b02d04bd43c1d882a81ae2122bcbcc2b808b7364915a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3703c8a770ec8b4f70c9b02d04bd43c1d882a81ae2122bcbcc2b808b7364915a","first_computed_at":"2026-07-05T10:42:45.207439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:45.207439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V/f1CjDvgS50wbLEGJdTJHJEDmhuSxd41TqPmRMCGLUiy8VPpvFhO9/eERQxonMDx1wKe7z+Ki6aa+Vn8uWBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:45.207925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.18497","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:240734c5ae0d116fd14e8f9daa5126a60e77cada6dac2525f4bfc87206d894ac","sha256:056eff0356f3b376ba9b40942b63c616dd1ee12bfb4ee09bd4f90bf201b3463f"],"state_sha256":"8e2d5908829e321461a0f7d8dba67bdcfd89558f0e7e8fb07d0432cfa04ab0c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nexk9aIZu+npY9NESCqHUDE0kM36mTSKbqEohRtsYXeydb9ocJog4HzskNccyqEAM6uwlApbmTTjhX2QAOWmCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T12:04:42.664905Z","bundle_sha256":"69f3f93aa63182241dc75806bf83c32f5c199f03fff04576b82a5caf3e360283"}}