{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CB2M5SRILYTMWMRIM6XAU7HWXE","short_pith_number":"pith:CB2M5SRI","schema_version":"1.0","canonical_sha256":"1074ceca285e26cb322867ae0a7cf6b90bb035b547434f95b6f04f3f28ef5b14","source":{"kind":"arxiv","id":"2602.08629","version":2},"attestation_state":"computed","paper":{"title":"CauScale: Neural Causal Discovery at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Peng, Chaochao Lu, Jiaguo Tian, Sirui Chen, Yu Qiao","submitted_at":"2026-02-09T13:21:32Z","abstract_excerpt":"Causal discovery is essential for advancing data-driven fields such as scientific AI and data analysis, yet existing approaches face significant time- and space-efficiency bottlenecks when scaling to large graphs. To address this challenge, we present CauScale, a neural architecture designed for efficient causal discovery that scales inference to graphs with up to 1000 nodes. CauScale improves time efficiency via a reduction unit that compresses data embeddings and improves space efficiency by adopting tied attention weights to avoid maintaining axis-specific attention maps. To keep high causa"},"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":"2602.08629","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T13:21:32Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7a4d70efb478086acdc515b9ff54e3c65739e6d0c27e2dddd49c3abbbb401b4e","abstract_canon_sha256":"38599f78faf4ca31a7ec4aff1fd66846052a67d682752481dfef71ad8225c5f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:17:50.272387Z","signature_b64":"AK4jrjmfv7GZe8koTj0M03wgO+jGP8x7KmLRzOGFSj0KrkNO/aZcHhIh8eLl3zjcozf4ZCSrQO/5oXyl005tCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1074ceca285e26cb322867ae0a7cf6b90bb035b547434f95b6f04f3f28ef5b14","last_reissued_at":"2026-06-25T01:17:50.271980Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:17:50.271980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CauScale: Neural Causal Discovery at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Peng, Chaochao Lu, Jiaguo Tian, Sirui Chen, Yu Qiao","submitted_at":"2026-02-09T13:21:32Z","abstract_excerpt":"Causal discovery is essential for advancing data-driven fields such as scientific AI and data analysis, yet existing approaches face significant time- and space-efficiency bottlenecks when scaling to large graphs. To address this challenge, we present CauScale, a neural architecture designed for efficient causal discovery that scales inference to graphs with up to 1000 nodes. CauScale improves time efficiency via a reduction unit that compresses data embeddings and improves space efficiency by adopting tied attention weights to avoid maintaining axis-specific attention maps. To keep high causa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.08629","kind":"arxiv","version":2},"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/2602.08629/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":"2602.08629","created_at":"2026-06-25T01:17:50.272031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.08629v2","created_at":"2026-06-25T01:17:50.272031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.08629","created_at":"2026-06-25T01:17:50.272031+00:00"},{"alias_kind":"pith_short_12","alias_value":"CB2M5SRILYTM","created_at":"2026-06-25T01:17:50.272031+00:00"},{"alias_kind":"pith_short_16","alias_value":"CB2M5SRILYTMWMRI","created_at":"2026-06-25T01:17:50.272031+00:00"},{"alias_kind":"pith_short_8","alias_value":"CB2M5SRI","created_at":"2026-06-25T01:17:50.272031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.31156","citing_title":"TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CB2M5SRILYTMWMRIM6XAU7HWXE","json":"https://pith.science/pith/CB2M5SRILYTMWMRIM6XAU7HWXE.json","graph_json":"https://pith.science/api/pith-number/CB2M5SRILYTMWMRIM6XAU7HWXE/graph.json","events_json":"https://pith.science/api/pith-number/CB2M5SRILYTMWMRIM6XAU7HWXE/events.json","paper":"https://pith.science/paper/CB2M5SRI"},"agent_actions":{"view_html":"https://pith.science/pith/CB2M5SRILYTMWMRIM6XAU7HWXE","download_json":"https://pith.science/pith/CB2M5SRILYTMWMRIM6XAU7HWXE.json","view_paper":"https://pith.science/paper/CB2M5SRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.08629&json=true","fetch_graph":"https://pith.science/api/pith-number/CB2M5SRILYTMWMRIM6XAU7HWXE/graph.json","fetch_events":"https://pith.science/api/pith-number/CB2M5SRILYTMWMRIM6XAU7HWXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CB2M5SRILYTMWMRIM6XAU7HWXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CB2M5SRILYTMWMRIM6XAU7HWXE/action/storage_attestation","attest_author":"https://pith.science/pith/CB2M5SRILYTMWMRIM6XAU7HWXE/action/author_attestation","sign_citation":"https://pith.science/pith/CB2M5SRILYTMWMRIM6XAU7HWXE/action/citation_signature","submit_replication":"https://pith.science/pith/CB2M5SRILYTMWMRIM6XAU7HWXE/action/replication_record"}},"created_at":"2026-06-25T01:17:50.272031+00:00","updated_at":"2026-06-25T01:17:50.272031+00:00"}