{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KLD4OV2WR3MMMQM6EQK6KFC7I2","short_pith_number":"pith:KLD4OV2W","schema_version":"1.0","canonical_sha256":"52c7c757568ed8c6419e2415e5145f4682b5a8bd0f13705a0a3773dbf7b3fba1","source":{"kind":"arxiv","id":"2010.11998","version":2},"attestation_state":"computed","paper":{"title":"Mapping Machine-Learned Physics into a Human-Readable Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["hep-ex","physics.data-an"],"primary_cat":"hep-ph","authors_text":"Daniel Whiteson, Jesse Thaler, Taylor Faucett","submitted_at":"2020-10-22T19:18:19Z","abstract_excerpt":"We present a technique for translating a black-box machine-learned classifier operating on a high-dimensional input space into a small set of human-interpretable observables that can be combined to make the same classification decisions. We iteratively select these observables from a large space of high-level discriminants by finding those with the highest decision similarity relative to the black box, quantified via a metric we introduce that evaluates the relative ordering of pairs of inputs. Successive iterations focus only on the subset of input pairs that are misordered by the current set"},"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":"2010.11998","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-ph","submitted_at":"2020-10-22T19:18:19Z","cross_cats_sorted":["hep-ex","physics.data-an"],"title_canon_sha256":"fb3a51c61442ed6141ca0ad97b823d461911e5da89f28820d2d15b22d5dbe135","abstract_canon_sha256":"d5cfb94929955f1c95c627f113970ec7112f51e1ce0382a8ad4038ff93998f0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:21.576220Z","signature_b64":"3xNz4LvyhPrph8iqC/BtjWjeCpM0sy9voK8SPIZj+Qgyb5+/Gx2NqKyPpo9ZWMlFrZyH7f3YI9zIKd+VYZ7qAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52c7c757568ed8c6419e2415e5145f4682b5a8bd0f13705a0a3773dbf7b3fba1","last_reissued_at":"2026-07-05T02:33:21.575762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:21.575762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mapping Machine-Learned Physics into a Human-Readable Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["hep-ex","physics.data-an"],"primary_cat":"hep-ph","authors_text":"Daniel Whiteson, Jesse Thaler, Taylor Faucett","submitted_at":"2020-10-22T19:18:19Z","abstract_excerpt":"We present a technique for translating a black-box machine-learned classifier operating on a high-dimensional input space into a small set of human-interpretable observables that can be combined to make the same classification decisions. We iteratively select these observables from a large space of high-level discriminants by finding those with the highest decision similarity relative to the black box, quantified via a metric we introduce that evaluates the relative ordering of pairs of inputs. Successive iterations focus only on the subset of input pairs that are misordered by the current set"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11998","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/2010.11998/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":"2010.11998","created_at":"2026-07-05T02:33:21.575820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.11998v2","created_at":"2026-07-05T02:33:21.575820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11998","created_at":"2026-07-05T02:33:21.575820+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLD4OV2WR3MM","created_at":"2026-07-05T02:33:21.575820+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLD4OV2WR3MMMQM6","created_at":"2026-07-05T02:33:21.575820+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLD4OV2W","created_at":"2026-07-05T02:33:21.575820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.10915","citing_title":"Optimizing The Cut And Count Method In Phenomenological Studies","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLD4OV2WR3MMMQM6EQK6KFC7I2","json":"https://pith.science/pith/KLD4OV2WR3MMMQM6EQK6KFC7I2.json","graph_json":"https://pith.science/api/pith-number/KLD4OV2WR3MMMQM6EQK6KFC7I2/graph.json","events_json":"https://pith.science/api/pith-number/KLD4OV2WR3MMMQM6EQK6KFC7I2/events.json","paper":"https://pith.science/paper/KLD4OV2W"},"agent_actions":{"view_html":"https://pith.science/pith/KLD4OV2WR3MMMQM6EQK6KFC7I2","download_json":"https://pith.science/pith/KLD4OV2WR3MMMQM6EQK6KFC7I2.json","view_paper":"https://pith.science/paper/KLD4OV2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.11998&json=true","fetch_graph":"https://pith.science/api/pith-number/KLD4OV2WR3MMMQM6EQK6KFC7I2/graph.json","fetch_events":"https://pith.science/api/pith-number/KLD4OV2WR3MMMQM6EQK6KFC7I2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLD4OV2WR3MMMQM6EQK6KFC7I2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLD4OV2WR3MMMQM6EQK6KFC7I2/action/storage_attestation","attest_author":"https://pith.science/pith/KLD4OV2WR3MMMQM6EQK6KFC7I2/action/author_attestation","sign_citation":"https://pith.science/pith/KLD4OV2WR3MMMQM6EQK6KFC7I2/action/citation_signature","submit_replication":"https://pith.science/pith/KLD4OV2WR3MMMQM6EQK6KFC7I2/action/replication_record"}},"created_at":"2026-07-05T02:33:21.575820+00:00","updated_at":"2026-07-05T02:33:21.575820+00:00"}