{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FCMN6Z5JVM4LPJBTRCNWUN5FFM","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":"6dbb19e0b89d7bee73f96bb877efa09fd649ae6106e5adb9d1c9304247946e87","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-14T20:06:28Z","title_canon_sha256":"90ffa1792b1fb1d4a70e5215c838e429ea269d5ba24e1de46111b208cfce77d7"},"schema_version":"1.0","source":{"id":"2010.07384","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07384","created_at":"2026-07-05T03:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07384v2","created_at":"2026-07-05T03:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07384","created_at":"2026-07-05T03:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"FCMN6Z5JVM4L","created_at":"2026-07-05T03:41:57Z"},{"alias_kind":"pith_short_16","alias_value":"FCMN6Z5JVM4LPJBT","created_at":"2026-07-05T03:41:57Z"},{"alias_kind":"pith_short_8","alias_value":"FCMN6Z5J","created_at":"2026-07-05T03:41:57Z"}],"graph_snapshots":[{"event_id":"sha256:60f5bd90cb3f83ba3fadb8f5293ded56212b3bc6d58c531c351805af06ac76ae","target":"graph","created_at":"2026-07-05T03:41:57Z","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/2010.07384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The importance of explainability in machine learning continues to grow, as both neural-network architectures and the data they model become increasingly complex. Unique challenges arise when a model's input features become high dimensional: on one hand, principled model-agnostic approaches to explainability become too computationally expensive; on the other, more efficient explainability algorithms lack natural interpretations for general users. In this work, we introduce a framework for human-interpretable explainability on high-dimensional data, consisting of two modules. First, we apply a s","authors_text":"Christopher Frye, Damien de Mijolla, Ilya Feige, John Mansir, Markus Kunesch","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-14T20:06:28Z","title":"Human-interpretable model explainability on high-dimensional data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07384","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":"sha256:10fa0dfb5fcad89fbf9327125782acade37e6a425ecc8f5c07ae92443a63a1f5","target":"record","created_at":"2026-07-05T03:41:57Z","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":"6dbb19e0b89d7bee73f96bb877efa09fd649ae6106e5adb9d1c9304247946e87","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-14T20:06:28Z","title_canon_sha256":"90ffa1792b1fb1d4a70e5215c838e429ea269d5ba24e1de46111b208cfce77d7"},"schema_version":"1.0","source":{"id":"2010.07384","kind":"arxiv","version":2}},"canonical_sha256":"2898df67a9ab38b7a433889b6a37a52b3522849c9f1e99c67cfa65c6fdafe0d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2898df67a9ab38b7a433889b6a37a52b3522849c9f1e99c67cfa65c6fdafe0d6","first_computed_at":"2026-07-05T03:41:57.925089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:41:57.925089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jD9kY5s4kV9kV4NQaf5nUdezq/8tarm0UuyiMcEIqspg0YhZzhTgtohtKvy2jdnOLlMsdfLk7XAYuxXsoeYXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:41:57.925545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.07384","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10fa0dfb5fcad89fbf9327125782acade37e6a425ecc8f5c07ae92443a63a1f5","sha256:60f5bd90cb3f83ba3fadb8f5293ded56212b3bc6d58c531c351805af06ac76ae"],"state_sha256":"9da2f610017890d6f536cc8f454225f89786783fbd0b0da7fea2d2baaf413680"}