{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2V75BJSZBWNSM4HWZRKCTYIKYK","short_pith_number":"pith:2V75BJSZ","schema_version":"1.0","canonical_sha256":"d57fd0a6590d9b2670f6cc5429e10ac2ac1f18d53594f531c12e9daf728d5fea","source":{"kind":"arxiv","id":"2608.04393","version":1},"attestation_state":"computed","paper":{"title":"When Proxy Prediction Becomes Equation Reconstruction: Diagnostics and Residual Learning for Factor-Derived Proxy Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Shafee, Chayan Lahiri, Cody Fehringer","submitted_at":"2026-08-05T02:54:34Z","abstract_excerpt":"Scientific machine learning often relies on proxy targets computed from known domain factors when direct observations are limited. When those same factors are used as model inputs, however, high predictive accuracy may reflect reconstruction of the proxy-generating equation rather than robustness to degraded factor information. We study this problem in RUSLE-derived soil-loss proxy prediction under controlled degradation of the soil-erodibility factor $K$. We introduce a diagnostic framework that combines degraded-formula references, classical tree-based baselines, matched direct and formula-f"},"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":"2608.04393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T02:54:34Z","cross_cats_sorted":[],"title_canon_sha256":"3fe98ec44d07772dbbd3c1dc16b4e2c9f91a4140abe96ac4ac2ae8cc8b5d3f91","abstract_canon_sha256":"5f01496a9f62b874784357cecc5d50111a66febb1c598ec0200af5718f861339"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:34:47.378624Z","signature_b64":"n1Og1vbSuZYAdJs3c09VeVO+HC08z1ZzSzBL3jRWBeGujGPukpEK/9hMez3A5d9YPOk+BGZHS43M1u0Iw5tpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d57fd0a6590d9b2670f6cc5429e10ac2ac1f18d53594f531c12e9daf728d5fea","last_reissued_at":"2026-08-06T01:34:47.377104Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:34:47.377104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Proxy Prediction Becomes Equation Reconstruction: Diagnostics and Residual Learning for Factor-Derived Proxy Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Shafee, Chayan Lahiri, Cody Fehringer","submitted_at":"2026-08-05T02:54:34Z","abstract_excerpt":"Scientific machine learning often relies on proxy targets computed from known domain factors when direct observations are limited. When those same factors are used as model inputs, however, high predictive accuracy may reflect reconstruction of the proxy-generating equation rather than robustness to degraded factor information. We study this problem in RUSLE-derived soil-loss proxy prediction under controlled degradation of the soil-erodibility factor $K$. We introduce a diagnostic framework that combines degraded-formula references, classical tree-based baselines, matched direct and formula-f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04393","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/2608.04393/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":"2608.04393","created_at":"2026-08-06T01:34:47.378928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04393v1","created_at":"2026-08-06T01:34:47.378928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04393","created_at":"2026-08-06T01:34:47.378928+00:00"},{"alias_kind":"pith_short_12","alias_value":"2V75BJSZBWNS","created_at":"2026-08-06T01:34:47.378928+00:00"},{"alias_kind":"pith_short_16","alias_value":"2V75BJSZBWNSM4HW","created_at":"2026-08-06T01:34:47.378928+00:00"},{"alias_kind":"pith_short_8","alias_value":"2V75BJSZ","created_at":"2026-08-06T01:34:47.378928+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/2V75BJSZBWNSM4HWZRKCTYIKYK","json":"https://pith.science/pith/2V75BJSZBWNSM4HWZRKCTYIKYK.json","graph_json":"https://pith.science/api/pith-number/2V75BJSZBWNSM4HWZRKCTYIKYK/graph.json","events_json":"https://pith.science/api/pith-number/2V75BJSZBWNSM4HWZRKCTYIKYK/events.json","paper":"https://pith.science/paper/2V75BJSZ"},"agent_actions":{"view_html":"https://pith.science/pith/2V75BJSZBWNSM4HWZRKCTYIKYK","download_json":"https://pith.science/pith/2V75BJSZBWNSM4HWZRKCTYIKYK.json","view_paper":"https://pith.science/paper/2V75BJSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04393&json=true","fetch_graph":"https://pith.science/api/pith-number/2V75BJSZBWNSM4HWZRKCTYIKYK/graph.json","fetch_events":"https://pith.science/api/pith-number/2V75BJSZBWNSM4HWZRKCTYIKYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2V75BJSZBWNSM4HWZRKCTYIKYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2V75BJSZBWNSM4HWZRKCTYIKYK/action/storage_attestation","attest_author":"https://pith.science/pith/2V75BJSZBWNSM4HWZRKCTYIKYK/action/author_attestation","sign_citation":"https://pith.science/pith/2V75BJSZBWNSM4HWZRKCTYIKYK/action/citation_signature","submit_replication":"https://pith.science/pith/2V75BJSZBWNSM4HWZRKCTYIKYK/action/replication_record"}},"created_at":"2026-08-06T01:34:47.378928+00:00","updated_at":"2026-08-06T01:34:47.378928+00:00"}