{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3GXOXWYUYPPSXZXGARCEDYFZ5F","short_pith_number":"pith:3GXOXWYU","schema_version":"1.0","canonical_sha256":"d9aeebdb14c3df2be6e6044441e0b9e962f329590cab421b89f376bf95c75f59","source":{"kind":"arxiv","id":"2503.23616","version":1},"attestation_state":"computed","paper":{"title":"Interpretable Machine Learning in Physics: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"physics.comp-ph","authors_text":"Miriam Klopotek, Raban Iten, Sebastian Johann Wetzel, Seungwoong Ha, Ziming Liu","submitted_at":"2025-03-30T22:44:40Z","abstract_excerpt":"Machine learning is increasingly transforming various scientific fields, enabled by advancements in computational power and access to large data sets from experiments and simulations. As artificial intelligence (AI) continues to grow in capability, these algorithms will enable many scientific discoveries beyond human capabilities. Since the primary goal of science is to understand the world around us, fully leveraging machine learning in scientific discovery requires models that are interpretable -- allowing experts to comprehend the concepts underlying machine-learned predictions. Successful "},"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":"2503.23616","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.comp-ph","submitted_at":"2025-03-30T22:44:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c18477c1bb73f3e1ad9357a6552fc3e933c206bebe03855b97f9f7115e006ab2","abstract_canon_sha256":"f6edc5e9dd0eab31920eddfda5640fa0d03ab5be7e16f60bd5698982e7a41b38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:56.450179Z","signature_b64":"zdLxdv3PYrh+2reWXlSTC68uestPzkRzJDy2IWCfDLVWGTiwX7Qu2D229UVjJX8xmeuLcZZjwuhGEAPnXHx0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9aeebdb14c3df2be6e6044441e0b9e962f329590cab421b89f376bf95c75f59","last_reissued_at":"2026-07-05T10:41:56.449717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:56.449717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Machine Learning in Physics: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"physics.comp-ph","authors_text":"Miriam Klopotek, Raban Iten, Sebastian Johann Wetzel, Seungwoong Ha, Ziming Liu","submitted_at":"2025-03-30T22:44:40Z","abstract_excerpt":"Machine learning is increasingly transforming various scientific fields, enabled by advancements in computational power and access to large data sets from experiments and simulations. As artificial intelligence (AI) continues to grow in capability, these algorithms will enable many scientific discoveries beyond human capabilities. Since the primary goal of science is to understand the world around us, fully leveraging machine learning in scientific discovery requires models that are interpretable -- allowing experts to comprehend the concepts underlying machine-learned predictions. Successful "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23616","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/2503.23616/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":"2503.23616","created_at":"2026-07-05T10:41:56.449772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23616v1","created_at":"2026-07-05T10:41:56.449772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23616","created_at":"2026-07-05T10:41:56.449772+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GXOXWYUYPPS","created_at":"2026-07-05T10:41:56.449772+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GXOXWYUYPPSXZXG","created_at":"2026-07-05T10:41:56.449772+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GXOXWYU","created_at":"2026-07-05T10:41:56.449772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11657","citing_title":"Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13821","citing_title":"Learning Minimal Representations of Many-Body Physics from Snapshots of a Quantum Simulator","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07420","citing_title":"KIGNet: Physics-Motivated Multi-Graph Representation Learning for Explainable Jet Tagging","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13913","citing_title":"Capturing reduced-order quantum many-body dynamics out of equilibrium via neural ordinary differential equations","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25885","citing_title":"Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GXOXWYUYPPSXZXGARCEDYFZ5F","json":"https://pith.science/pith/3GXOXWYUYPPSXZXGARCEDYFZ5F.json","graph_json":"https://pith.science/api/pith-number/3GXOXWYUYPPSXZXGARCEDYFZ5F/graph.json","events_json":"https://pith.science/api/pith-number/3GXOXWYUYPPSXZXGARCEDYFZ5F/events.json","paper":"https://pith.science/paper/3GXOXWYU"},"agent_actions":{"view_html":"https://pith.science/pith/3GXOXWYUYPPSXZXGARCEDYFZ5F","download_json":"https://pith.science/pith/3GXOXWYUYPPSXZXGARCEDYFZ5F.json","view_paper":"https://pith.science/paper/3GXOXWYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23616&json=true","fetch_graph":"https://pith.science/api/pith-number/3GXOXWYUYPPSXZXGARCEDYFZ5F/graph.json","fetch_events":"https://pith.science/api/pith-number/3GXOXWYUYPPSXZXGARCEDYFZ5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GXOXWYUYPPSXZXGARCEDYFZ5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GXOXWYUYPPSXZXGARCEDYFZ5F/action/storage_attestation","attest_author":"https://pith.science/pith/3GXOXWYUYPPSXZXGARCEDYFZ5F/action/author_attestation","sign_citation":"https://pith.science/pith/3GXOXWYUYPPSXZXGARCEDYFZ5F/action/citation_signature","submit_replication":"https://pith.science/pith/3GXOXWYUYPPSXZXGARCEDYFZ5F/action/replication_record"}},"created_at":"2026-07-05T10:41:56.449772+00:00","updated_at":"2026-07-05T10:41:56.449772+00:00"}