{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B3OVIFKYTZGJABOPPVRAKAY2TN","short_pith_number":"pith:B3OVIFKY","schema_version":"1.0","canonical_sha256":"0edd5415589e4c9005cf7d6205031a9b5667155a504d7d711730bae197a82cfa","source":{"kind":"arxiv","id":"2402.09305","version":1},"attestation_state":"computed","paper":{"title":"Embracing the black box: Heading towards foundation models for causal discovery from time series data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gideon Stein, Joachim Denzler, Maha Shadaydeh","submitted_at":"2024-02-14T16:49:13Z","abstract_excerpt":"Causal discovery from time series data encompasses many existing solutions, including those based on deep learning techniques. However, these methods typically do not endorse one of the most prevalent paradigms in deep learning: End-to-end learning. To address this gap, we explore what we call Causal Pretraining. A methodology that aims to learn a direct mapping from multivariate time series to the underlying causal graphs in a supervised manner. Our empirical findings suggest that causal discovery in a supervised manner is possible, assuming that the training and test time series samples shar"},"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":"2402.09305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-14T16:49:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"60c9a6144736004754072b3cf27f53776d0c827f88da5d5aee839ae5e2f29f88","abstract_canon_sha256":"190268b0ba47289bc1cf33597c82f63e39a32d322abaf13b9c28afce08beb109"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:11.952003Z","signature_b64":"poii819/DsnapJU6c2P5TwBij6lapFwUz4kcqv1RzoCiiLa0pU+L78BMVbnNxR2pBEYrFksUZFqnJc8PKCiJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0edd5415589e4c9005cf7d6205031a9b5667155a504d7d711730bae197a82cfa","last_reissued_at":"2026-07-05T07:45:11.951520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:11.951520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embracing the black box: Heading towards foundation models for causal discovery from time series data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gideon Stein, Joachim Denzler, Maha Shadaydeh","submitted_at":"2024-02-14T16:49:13Z","abstract_excerpt":"Causal discovery from time series data encompasses many existing solutions, including those based on deep learning techniques. However, these methods typically do not endorse one of the most prevalent paradigms in deep learning: End-to-end learning. To address this gap, we explore what we call Causal Pretraining. A methodology that aims to learn a direct mapping from multivariate time series to the underlying causal graphs in a supervised manner. Our empirical findings suggest that causal discovery in a supervised manner is possible, assuming that the training and test time series samples shar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09305","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/2402.09305/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":"2402.09305","created_at":"2026-07-05T07:45:11.951580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09305v1","created_at":"2026-07-05T07:45:11.951580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09305","created_at":"2026-07-05T07:45:11.951580+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3OVIFKYTZGJ","created_at":"2026-07-05T07:45:11.951580+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3OVIFKYTZGJABOP","created_at":"2026-07-05T07:45:11.951580+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3OVIFKY","created_at":"2026-07-05T07:45:11.951580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17516","citing_title":"FoundCause: Causal Discovery with Latent Confounders from Observational Data","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26759","citing_title":"Time Series Causal Discovery via Context-Conditioned and Causality-Augmented Pretraining","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03045","citing_title":"TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations","ref_index":156,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3OVIFKYTZGJABOPPVRAKAY2TN","json":"https://pith.science/pith/B3OVIFKYTZGJABOPPVRAKAY2TN.json","graph_json":"https://pith.science/api/pith-number/B3OVIFKYTZGJABOPPVRAKAY2TN/graph.json","events_json":"https://pith.science/api/pith-number/B3OVIFKYTZGJABOPPVRAKAY2TN/events.json","paper":"https://pith.science/paper/B3OVIFKY"},"agent_actions":{"view_html":"https://pith.science/pith/B3OVIFKYTZGJABOPPVRAKAY2TN","download_json":"https://pith.science/pith/B3OVIFKYTZGJABOPPVRAKAY2TN.json","view_paper":"https://pith.science/paper/B3OVIFKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09305&json=true","fetch_graph":"https://pith.science/api/pith-number/B3OVIFKYTZGJABOPPVRAKAY2TN/graph.json","fetch_events":"https://pith.science/api/pith-number/B3OVIFKYTZGJABOPPVRAKAY2TN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3OVIFKYTZGJABOPPVRAKAY2TN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3OVIFKYTZGJABOPPVRAKAY2TN/action/storage_attestation","attest_author":"https://pith.science/pith/B3OVIFKYTZGJABOPPVRAKAY2TN/action/author_attestation","sign_citation":"https://pith.science/pith/B3OVIFKYTZGJABOPPVRAKAY2TN/action/citation_signature","submit_replication":"https://pith.science/pith/B3OVIFKYTZGJABOPPVRAKAY2TN/action/replication_record"}},"created_at":"2026-07-05T07:45:11.951580+00:00","updated_at":"2026-07-05T07:45:11.951580+00:00"}