{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BWDXYN46JWWCFE267T3TOKPIKL","short_pith_number":"pith:BWDXYN46","schema_version":"1.0","canonical_sha256":"0d877c379e4dac22935efcf73729e852c2f63d7cea7435e65e529a88c44e3f3b","source":{"kind":"arxiv","id":"2108.02214","version":2},"attestation_state":"computed","paper":{"title":"A FAIR and AI-ready Higgs boson decay dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","hep-ph"],"primary_cat":"hep-ex","authors_text":"Daniel Diaz, Daniel S. Katz, E. A. Huerta, Farouk Mokhtar, Javier Duarte, Mark S. Neubauer, Philip Harris, Raghav Kansal, Roger Rusack, Sang Eon Park, Volodymyr V. Kindratenko, Yifan Chen, Zhizhen Zhao","submitted_at":"2021-08-04T18:00:03Z","abstract_excerpt":"To enable the reusability of massive scientific datasets by humans and machines, researchers aim to adhere to the principles of findability, accessibility, interoperability, and reusability (FAIR) for data and artificial intelligence (AI) models. This article provides a domain-agnostic, step-by-step assessment guide to evaluate whether or not a given dataset meets these principles. We demonstrate how to use this guide to evaluate the FAIRness of an open simulated dataset produced by the CMS Collaboration at the CERN Large Hadron Collider. This dataset consists of Higgs boson decays and quark a"},"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":"2108.02214","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-ex","submitted_at":"2021-08-04T18:00:03Z","cross_cats_sorted":["cs.AI","cs.DB","hep-ph"],"title_canon_sha256":"0d894316d0bc8acb503e47a197191d2d1241307f78ad077dc5ce111c822ffb0b","abstract_canon_sha256":"9423c3d82320475d7cb211be4aae558714222de25a2222d1c1f73e11c271420a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:27.505018Z","signature_b64":"RdmZ1aXduTwffNMgH54KV9TPT1bBjaNBkVwPkZ11FRjxkLas4ScEb3DU7H+gPYL1zY7JOVCWfr51k/lkx2m1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d877c379e4dac22935efcf73729e852c2f63d7cea7435e65e529a88c44e3f3b","last_reissued_at":"2026-07-05T03:57:27.504533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:27.504533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A FAIR and AI-ready Higgs boson decay dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","hep-ph"],"primary_cat":"hep-ex","authors_text":"Daniel Diaz, Daniel S. Katz, E. A. Huerta, Farouk Mokhtar, Javier Duarte, Mark S. Neubauer, Philip Harris, Raghav Kansal, Roger Rusack, Sang Eon Park, Volodymyr V. Kindratenko, Yifan Chen, Zhizhen Zhao","submitted_at":"2021-08-04T18:00:03Z","abstract_excerpt":"To enable the reusability of massive scientific datasets by humans and machines, researchers aim to adhere to the principles of findability, accessibility, interoperability, and reusability (FAIR) for data and artificial intelligence (AI) models. This article provides a domain-agnostic, step-by-step assessment guide to evaluate whether or not a given dataset meets these principles. We demonstrate how to use this guide to evaluate the FAIRness of an open simulated dataset produced by the CMS Collaboration at the CERN Large Hadron Collider. This dataset consists of Higgs boson decays and quark a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02214","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/2108.02214/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":"2108.02214","created_at":"2026-07-05T03:57:27.504601+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.02214v2","created_at":"2026-07-05T03:57:27.504601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02214","created_at":"2026-07-05T03:57:27.504601+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWDXYN46JWWC","created_at":"2026-07-05T03:57:27.504601+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWDXYN46JWWCFE26","created_at":"2026-07-05T03:57:27.504601+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWDXYN46","created_at":"2026-07-05T03:57:27.504601+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01354","citing_title":"Local Conformal Predictions for Calibrated Surrogates","ref_index":190,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07667","citing_title":"Design Principles for AI-Ready QCD Data with a Barrel Imaging Calorimeter Application","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BWDXYN46JWWCFE267T3TOKPIKL","json":"https://pith.science/pith/BWDXYN46JWWCFE267T3TOKPIKL.json","graph_json":"https://pith.science/api/pith-number/BWDXYN46JWWCFE267T3TOKPIKL/graph.json","events_json":"https://pith.science/api/pith-number/BWDXYN46JWWCFE267T3TOKPIKL/events.json","paper":"https://pith.science/paper/BWDXYN46"},"agent_actions":{"view_html":"https://pith.science/pith/BWDXYN46JWWCFE267T3TOKPIKL","download_json":"https://pith.science/pith/BWDXYN46JWWCFE267T3TOKPIKL.json","view_paper":"https://pith.science/paper/BWDXYN46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.02214&json=true","fetch_graph":"https://pith.science/api/pith-number/BWDXYN46JWWCFE267T3TOKPIKL/graph.json","fetch_events":"https://pith.science/api/pith-number/BWDXYN46JWWCFE267T3TOKPIKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWDXYN46JWWCFE267T3TOKPIKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWDXYN46JWWCFE267T3TOKPIKL/action/storage_attestation","attest_author":"https://pith.science/pith/BWDXYN46JWWCFE267T3TOKPIKL/action/author_attestation","sign_citation":"https://pith.science/pith/BWDXYN46JWWCFE267T3TOKPIKL/action/citation_signature","submit_replication":"https://pith.science/pith/BWDXYN46JWWCFE267T3TOKPIKL/action/replication_record"}},"created_at":"2026-07-05T03:57:27.504601+00:00","updated_at":"2026-07-05T03:57:27.504601+00:00"}