{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SSGZXGFOL24KGSMRFHLZLBONWV","short_pith_number":"pith:SSGZXGFO","schema_version":"1.0","canonical_sha256":"948d9b98ae5eb8a3499129d79585cdb548e4eef6187efe078de160862466ba59","source":{"kind":"arxiv","id":"2606.07865","version":1},"attestation_state":"computed","paper":{"title":"Instrumented data for causal scientific machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel N. Wilke","submitted_at":"2026-06-05T21:53:39Z","abstract_excerpt":"Scientific machine learning is limited less by model size than by the data it is trained on. Observational data records what happened but not why; template synthetic data has a known generating process but only for the simulator's template, not the case a user faces. We argue a third option is now operationally feasible: instrumented data, in which every datum carries the mechanistic model that produced it, an explicit uncertainty over that model, and an executable family of counterfactuals. Verification-and-validation (V&V) instrumented image-to-simulation pipelines are one realisation: a sen"},"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":"2606.07865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T21:53:39Z","cross_cats_sorted":["cs.AI","physics.comp-ph","stat.ML"],"title_canon_sha256":"6c99302888f4807764bfb8ebbf789cffd91f50ad05db7f14f9aee0639f5170b9","abstract_canon_sha256":"d68b751c4898f90cfafaca2c877528a306501c139ecd8d1400df7ebc0a019718"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:54.102253Z","signature_b64":"f0yw9svSr2oTqZKv8c3l9o4H+xhEhzIGMHm5JtNtV4+0nM54bI0u8CUoXTXwxzJWeJr+V1wE7Dtpx0KQ00AuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"948d9b98ae5eb8a3499129d79585cdb548e4eef6187efe078de160862466ba59","last_reissued_at":"2026-06-09T01:04:54.101837Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:54.101837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instrumented data for causal scientific machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel N. Wilke","submitted_at":"2026-06-05T21:53:39Z","abstract_excerpt":"Scientific machine learning is limited less by model size than by the data it is trained on. Observational data records what happened but not why; template synthetic data has a known generating process but only for the simulator's template, not the case a user faces. We argue a third option is now operationally feasible: instrumented data, in which every datum carries the mechanistic model that produced it, an explicit uncertainty over that model, and an executable family of counterfactuals. Verification-and-validation (V&V) instrumented image-to-simulation pipelines are one realisation: a sen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07865","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/2606.07865/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":"2606.07865","created_at":"2026-06-09T01:04:54.101907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07865v1","created_at":"2026-06-09T01:04:54.101907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07865","created_at":"2026-06-09T01:04:54.101907+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSGZXGFOL24K","created_at":"2026-06-09T01:04:54.101907+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSGZXGFOL24KGSMR","created_at":"2026-06-09T01:04:54.101907+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSGZXGFO","created_at":"2026-06-09T01:04:54.101907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSGZXGFOL24KGSMRFHLZLBONWV","json":"https://pith.science/pith/SSGZXGFOL24KGSMRFHLZLBONWV.json","graph_json":"https://pith.science/api/pith-number/SSGZXGFOL24KGSMRFHLZLBONWV/graph.json","events_json":"https://pith.science/api/pith-number/SSGZXGFOL24KGSMRFHLZLBONWV/events.json","paper":"https://pith.science/paper/SSGZXGFO"},"agent_actions":{"view_html":"https://pith.science/pith/SSGZXGFOL24KGSMRFHLZLBONWV","download_json":"https://pith.science/pith/SSGZXGFOL24KGSMRFHLZLBONWV.json","view_paper":"https://pith.science/paper/SSGZXGFO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07865&json=true","fetch_graph":"https://pith.science/api/pith-number/SSGZXGFOL24KGSMRFHLZLBONWV/graph.json","fetch_events":"https://pith.science/api/pith-number/SSGZXGFOL24KGSMRFHLZLBONWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSGZXGFOL24KGSMRFHLZLBONWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSGZXGFOL24KGSMRFHLZLBONWV/action/storage_attestation","attest_author":"https://pith.science/pith/SSGZXGFOL24KGSMRFHLZLBONWV/action/author_attestation","sign_citation":"https://pith.science/pith/SSGZXGFOL24KGSMRFHLZLBONWV/action/citation_signature","submit_replication":"https://pith.science/pith/SSGZXGFOL24KGSMRFHLZLBONWV/action/replication_record"}},"created_at":"2026-06-09T01:04:54.101907+00:00","updated_at":"2026-06-09T01:04:54.101907+00:00"}