{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ATEWO5Z25GRSPKK7P24TINQWML","short_pith_number":"pith:ATEWO5Z2","schema_version":"1.0","canonical_sha256":"04c967773ae9a327a95f7eb934361662ce0697037283ee3fbe59effc238d8950","source":{"kind":"arxiv","id":"2605.17528","version":1},"attestation_state":"computed","paper":{"title":"CasualSynth: Generating Structurally Sound Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiahao Sun, Thomas Lukasiewicz, Wei Dai, Zehua Cheng","submitted_at":"2026-05-17T16:21:01Z","abstract_excerpt":"Large Language Models (LLMs) generate realistic synthetic data but offer no guarantee that their outputs respect the causal mechanisms governing the target domain. We introduce CausalSynth, a framework that decouples causal structure generation from semantic realization, yielding synthetic data that is both causally valid and linguistically rich. The framework operates in three phases. First, a Structural Causal Model (SCM) - a tuple of structural equations defined over a directed acyclic graph (DAG) generates causal skeletons, i.e., variable assignments that satisfy the Global Markov Property"},"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":"2605.17528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T16:21:01Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"376d76fcfe9e1a292e460bc54603cf41243199de48bb8905d9fdbe4b56789a42","abstract_canon_sha256":"544ba68cd65b93991b16729637481329ded0ae810e01e29c16cc284f92e6162e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:44.180687Z","signature_b64":"YmBas6ywVBm0o0ukkp4WQ3oHDvjm/Hhh5HyNFyTrrXGFLuYpDYgULb9l7d59DrNryx65g9z/heD8pyiLQOmQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04c967773ae9a327a95f7eb934361662ce0697037283ee3fbe59effc238d8950","last_reissued_at":"2026-05-20T00:04:44.179861Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:44.179861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CasualSynth: Generating Structurally Sound Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiahao Sun, Thomas Lukasiewicz, Wei Dai, Zehua Cheng","submitted_at":"2026-05-17T16:21:01Z","abstract_excerpt":"Large Language Models (LLMs) generate realistic synthetic data but offer no guarantee that their outputs respect the causal mechanisms governing the target domain. We introduce CausalSynth, a framework that decouples causal structure generation from semantic realization, yielding synthetic data that is both causally valid and linguistically rich. The framework operates in three phases. First, a Structural Causal Model (SCM) - a tuple of structural equations defined over a directed acyclic graph (DAG) generates causal skeletons, i.e., variable assignments that satisfy the Global Markov Property"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17528","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/2605.17528/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.620670Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.559969Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"c1a7944899c5e2f529980b10085a101374dc144c0276548ee5a5bd8123047f92"},"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":"2605.17528","created_at":"2026-05-20T00:04:44.180001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17528v1","created_at":"2026-05-20T00:04:44.180001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17528","created_at":"2026-05-20T00:04:44.180001+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATEWO5Z25GRS","created_at":"2026-05-20T00:04:44.180001+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATEWO5Z25GRSPKK7","created_at":"2026-05-20T00:04:44.180001+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATEWO5Z2","created_at":"2026-05-20T00:04:44.180001+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/ATEWO5Z25GRSPKK7P24TINQWML","json":"https://pith.science/pith/ATEWO5Z25GRSPKK7P24TINQWML.json","graph_json":"https://pith.science/api/pith-number/ATEWO5Z25GRSPKK7P24TINQWML/graph.json","events_json":"https://pith.science/api/pith-number/ATEWO5Z25GRSPKK7P24TINQWML/events.json","paper":"https://pith.science/paper/ATEWO5Z2"},"agent_actions":{"view_html":"https://pith.science/pith/ATEWO5Z25GRSPKK7P24TINQWML","download_json":"https://pith.science/pith/ATEWO5Z25GRSPKK7P24TINQWML.json","view_paper":"https://pith.science/paper/ATEWO5Z2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17528&json=true","fetch_graph":"https://pith.science/api/pith-number/ATEWO5Z25GRSPKK7P24TINQWML/graph.json","fetch_events":"https://pith.science/api/pith-number/ATEWO5Z25GRSPKK7P24TINQWML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATEWO5Z25GRSPKK7P24TINQWML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATEWO5Z25GRSPKK7P24TINQWML/action/storage_attestation","attest_author":"https://pith.science/pith/ATEWO5Z25GRSPKK7P24TINQWML/action/author_attestation","sign_citation":"https://pith.science/pith/ATEWO5Z25GRSPKK7P24TINQWML/action/citation_signature","submit_replication":"https://pith.science/pith/ATEWO5Z25GRSPKK7P24TINQWML/action/replication_record"}},"created_at":"2026-05-20T00:04:44.180001+00:00","updated_at":"2026-05-20T00:04:44.180001+00:00"}