{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6FEWOBSBS3BDRKUU5URVNL4UET","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":"4e8a3da66193987d96671a8a815d2f3150586488446e2446b44a81e4fefb53d5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2025-06-04T11:21:17Z","title_canon_sha256":"1eae3a34febf1a37233cde1aad626949828b00118a8682da53957f03f2f13eee"},"schema_version":"1.0","source":{"id":"2506.03844","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03844","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03844v3","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03844","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"6FEWOBSBS3BD","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"6FEWOBSBS3BDRKUU","created_at":"2026-05-20T00:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"6FEWOBSB","created_at":"2026-05-20T00:04:10Z"}],"graph_snapshots":[{"event_id":"sha256:f1131beaaea57e393ce0ced8922ed172611d2509bc72d93bfc3a7345721da180","target":"graph","created_at":"2026-05-20T00:04:10Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By contrasting feature attributions across seven diverse classifiers in a heterogeneous Rashomon set, the framework extracts consensus design rules (filled valence s-, d-, and f-shells, low chemical heterogeneity, enrichment in C, S, Si, O) that enable identification of 122 high-confidence candidates from ~45,000 compounds, with DFT validation showing dielectric screening as a coherence proxy (R² = 0.89 against experimental T₂) and favorable mid-gap states in TiO₂."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That consensus feature attributions from composition-only classifiers trained on existing data capture the essential physical requirements for quantum defect hosting and that the dielectric-T₂ correlation observed in 12 materials will generalize to the full set of 122 screened candidates without structural or defect-specific details in the initial filter."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A composition-only ML framework with Rashomon ensembles extracts consensus design rules and screens ~45,000 compounds to identify 122 high-confidence quantum defect hosts, recovering known materials and predicting new ones validated by limited DFT."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Machine learning on compositions alone extracts consensus design rules to identify 122 high-confidence quantum defect host candidates."}],"snapshot_sha256":"dfce17fa0b73531ee8c083adc957df9c6288cae165123e4549906a368e81eed4"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.03844/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Solid-state spin defects in wide-bandgap semiconductors are leading candidates for quantum information processing, but systematic identification of suitable host materials remains limited by the cost of first-principles screening across vast chemical spaces. We address this with a composition-only machine learning framework built on heterogeneous Rashomon set ensembles: by contrasting the feature attributions of seven diverse classifiers, we extract consensus design rules that no single model identifies alone-filled valence s-, d-, and f-shells, low chemical heterogeneity, and enrichment in C,","authors_text":"Mohammed Mahshook, Rudra Banerjee","cross_cats":[],"headline":"Machine learning on compositions alone extracts consensus design rules to identify 122 high-confidence quantum defect host candidates.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2025-06-04T11:21:17Z","title":"Beyond Diamond: Interpretable Machine Learning Reveals Design Principles for Quantum Defect Host Materials"},"references":{"count":61,"internal_anchors":0,"resolved_work":61,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Building a quantum- ready ecosystem","work_id":"18fa45f7-a5a6-4fe8-ac25-d7227b903dfb","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Review of distributed quantum computing: from sin- gle qpu to high performance quantum computing","work_id":"d7101fbb-4ed0-4b30-89a7-385124cd2c3a","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Scalable entanglement certi- fication via quantum communication","work_id":"2a60c6b4-7f00-416d-a3b3-be2df3179cbb","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Quantum sensing and metrology for fundamental physics with molecules","work_id":"8a179d38-18f8-4e05-ad35-b7ea3a0fab32","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"An elementary review on basic principles and developments of qubits for quantum computing","work_id":"8d6bcba5-f41b-46f9-a79a-b81b6b9650e8","year":2024}],"snapshot_sha256":"2e1dc9385e11bbd355343136c7471b1bbd2d3be6471dcc59184899cfb9fcb607"},"source":{"id":"2506.03844","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-19T11:32:16.143277Z","id":"2e2b3166-fd0e-4cf8-96bc-3ac6d0c5f5a0","model_set":{"reader":"grok-4.3"},"one_line_summary":"A composition-only ML framework with Rashomon ensembles extracts consensus design rules and screens ~45,000 compounds to identify 122 high-confidence quantum defect hosts, recovering known materials and predicting new ones validated by limited DFT.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Machine learning on compositions alone extracts consensus design rules to identify 122 high-confidence quantum defect host candidates.","strongest_claim":"By contrasting feature attributions across seven diverse classifiers in a heterogeneous Rashomon set, the framework extracts consensus design rules (filled valence s-, d-, and f-shells, low chemical heterogeneity, enrichment in C, S, Si, O) that enable identification of 122 high-confidence candidates from ~45,000 compounds, with DFT validation showing dielectric screening as a coherence proxy (R² = 0.89 against experimental T₂) and favorable mid-gap states in TiO₂.","weakest_assumption":"That consensus feature attributions from composition-only classifiers trained on existing data capture the essential physical requirements for quantum defect hosting and that the dielectric-T₂ correlation observed in 12 materials will generalize to the full set of 122 screened candidates without structural or defect-specific details in the initial filter."}},"verdict_id":"2e2b3166-fd0e-4cf8-96bc-3ac6d0c5f5a0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e6232239682763c86eaa95d604679e6bdd0ac8d3ba98fca220e9d69919d12de4","target":"record","created_at":"2026-05-20T00:04:10Z","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":"4e8a3da66193987d96671a8a815d2f3150586488446e2446b44a81e4fefb53d5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2025-06-04T11:21:17Z","title_canon_sha256":"1eae3a34febf1a37233cde1aad626949828b00118a8682da53957f03f2f13eee"},"schema_version":"1.0","source":{"id":"2506.03844","kind":"arxiv","version":3}},"canonical_sha256":"f14967064196c238aa94ed2356af9424ed950e03b55c70864f482d9ecee560d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f14967064196c238aa94ed2356af9424ed950e03b55c70864f482d9ecee560d7","first_computed_at":"2026-05-20T00:04:10.316279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:10.316279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VChyeAN/jTQFmazrMD0XEJzGZs6TWdbPywSNexz0mCIEROZpXiHUz3C1EsArm5VdPTGHprxuP2SXwbiVjE8zBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:10.317173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03844","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6232239682763c86eaa95d604679e6bdd0ac8d3ba98fca220e9d69919d12de4","sha256:f1131beaaea57e393ce0ced8922ed172611d2509bc72d93bfc3a7345721da180"],"state_sha256":"988bb30f3520f7016449cb9f79f3b9e7e007a79bf1d15c8a99422112adf8358a"}