{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2PHNA2DGFXJQPI7ZSOZPRKL6TJ","short_pith_number":"pith:2PHNA2DG","schema_version":"1.0","canonical_sha256":"d3ced068662dd307a3f993b2f8a97e9a67533c48855625768105a5dce3e04a56","source":{"kind":"arxiv","id":"2507.05333","version":1},"attestation_state":"computed","paper":{"title":"Causal Foundation Models: Disentangling Physics from Instrument Properties","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.IM","astro-ph.SR","cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel Muthukrishna, David W. Hogg, Jeroen Audenaert, Paul F. Gregory, V. Ashley Villar","submitted_at":"2025-07-07T18:00:00Z","abstract_excerpt":"Foundation models for structured time series data must contend with a fundamental challenge: observations often conflate the true underlying physical phenomena with systematic distortions introduced by measurement instruments. This entanglement limits model generalization, especially in heterogeneous or multi-instrument settings. We present a causally-motivated foundation model that explicitly disentangles physical and instrumental factors using a dual-encoder architecture trained with structured contrastive learning. Leveraging naturally occurring observational triplets (i.e., where the same "},"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":"2507.05333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T18:00:00Z","cross_cats_sorted":["astro-ph.IM","astro-ph.SR","cs.AI"],"title_canon_sha256":"917747a87fd6be269442c5acb8896e2bdb2d1db17f7daf45df5464a9d9cb25d9","abstract_canon_sha256":"00d11b8089d28fd15943b905f4d825610bd5f7e07d636b5d3212cedba827520d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:28.835012Z","signature_b64":"HU5UPqaJQ5WFbnA2yAiQoUy8VOijRGRKpAt65PWqAbD9GnVboB19aX7R1FRDKI2VCwz6L/QO9M40VLzqzSh2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3ced068662dd307a3f993b2f8a97e9a67533c48855625768105a5dce3e04a56","last_reissued_at":"2026-07-05T11:33:28.834549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:28.834549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Foundation Models: Disentangling Physics from Instrument Properties","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.IM","astro-ph.SR","cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel Muthukrishna, David W. Hogg, Jeroen Audenaert, Paul F. Gregory, V. Ashley Villar","submitted_at":"2025-07-07T18:00:00Z","abstract_excerpt":"Foundation models for structured time series data must contend with a fundamental challenge: observations often conflate the true underlying physical phenomena with systematic distortions introduced by measurement instruments. This entanglement limits model generalization, especially in heterogeneous or multi-instrument settings. We present a causally-motivated foundation model that explicitly disentangles physical and instrumental factors using a dual-encoder architecture trained with structured contrastive learning. Leveraging naturally occurring observational triplets (i.e., where the same "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05333","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/2507.05333/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":"2507.05333","created_at":"2026-07-05T11:33:28.834608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05333v1","created_at":"2026-07-05T11:33:28.834608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05333","created_at":"2026-07-05T11:33:28.834608+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PHNA2DGFXJQ","created_at":"2026-07-05T11:33:28.834608+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PHNA2DGFXJQPI7Z","created_at":"2026-07-05T11:33:28.834608+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PHNA2DG","created_at":"2026-07-05T11:33:28.834608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07437","citing_title":"ASTRAFier: A Novel and Scalable Transformer-based Stellar Variability Classifier","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PHNA2DGFXJQPI7ZSOZPRKL6TJ","json":"https://pith.science/pith/2PHNA2DGFXJQPI7ZSOZPRKL6TJ.json","graph_json":"https://pith.science/api/pith-number/2PHNA2DGFXJQPI7ZSOZPRKL6TJ/graph.json","events_json":"https://pith.science/api/pith-number/2PHNA2DGFXJQPI7ZSOZPRKL6TJ/events.json","paper":"https://pith.science/paper/2PHNA2DG"},"agent_actions":{"view_html":"https://pith.science/pith/2PHNA2DGFXJQPI7ZSOZPRKL6TJ","download_json":"https://pith.science/pith/2PHNA2DGFXJQPI7ZSOZPRKL6TJ.json","view_paper":"https://pith.science/paper/2PHNA2DG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05333&json=true","fetch_graph":"https://pith.science/api/pith-number/2PHNA2DGFXJQPI7ZSOZPRKL6TJ/graph.json","fetch_events":"https://pith.science/api/pith-number/2PHNA2DGFXJQPI7ZSOZPRKL6TJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PHNA2DGFXJQPI7ZSOZPRKL6TJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PHNA2DGFXJQPI7ZSOZPRKL6TJ/action/storage_attestation","attest_author":"https://pith.science/pith/2PHNA2DGFXJQPI7ZSOZPRKL6TJ/action/author_attestation","sign_citation":"https://pith.science/pith/2PHNA2DGFXJQPI7ZSOZPRKL6TJ/action/citation_signature","submit_replication":"https://pith.science/pith/2PHNA2DGFXJQPI7ZSOZPRKL6TJ/action/replication_record"}},"created_at":"2026-07-05T11:33:28.834608+00:00","updated_at":"2026-07-05T11:33:28.834608+00:00"}