{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HIJJSQULKWAPWTOIYUDS3J4GUA","short_pith_number":"pith:HIJJSQUL","canonical_record":{"source":{"id":"2102.05638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-10T18:53:11Z","cross_cats_sorted":[],"title_canon_sha256":"00d1f02912392758a8aac07a8b64764f841f9c68ef7267b41c664de7950242ee","abstract_canon_sha256":"29bc57766b7d51e63e3a3c48517013d85046210eef90efc7ead6b69e700382ca"},"schema_version":"1.0"},"canonical_sha256":"3a1299428b5580fb4dc8c5072da786a01b0bf898fba915ec6f0918561398d21a","source":{"kind":"arxiv","id":"2102.05638","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.05638","created_at":"2026-07-05T02:14:20Z"},{"alias_kind":"arxiv_version","alias_value":"2102.05638v1","created_at":"2026-07-05T02:14:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05638","created_at":"2026-07-05T02:14:20Z"},{"alias_kind":"pith_short_12","alias_value":"HIJJSQULKWAP","created_at":"2026-07-05T02:14:20Z"},{"alias_kind":"pith_short_16","alias_value":"HIJJSQULKWAPWTOI","created_at":"2026-07-05T02:14:20Z"},{"alias_kind":"pith_short_8","alias_value":"HIJJSQUL","created_at":"2026-07-05T02:14:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HIJJSQULKWAPWTOIYUDS3J4GUA","target":"record","payload":{"canonical_record":{"source":{"id":"2102.05638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-10T18:53:11Z","cross_cats_sorted":[],"title_canon_sha256":"00d1f02912392758a8aac07a8b64764f841f9c68ef7267b41c664de7950242ee","abstract_canon_sha256":"29bc57766b7d51e63e3a3c48517013d85046210eef90efc7ead6b69e700382ca"},"schema_version":"1.0"},"canonical_sha256":"3a1299428b5580fb4dc8c5072da786a01b0bf898fba915ec6f0918561398d21a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:20.529766Z","signature_b64":"380ynew9Ep72JDAaKbwgzkT1axM4yU0kg7Zp8hTLS6gakuQFjzoUi/3DuXChKGKNp9nB+8rQofnE2kfrkgjXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a1299428b5580fb4dc8c5072da786a01b0bf898fba915ec6f0918561398d21a","last_reissued_at":"2026-07-05T02:14:20.529149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:20.529149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.05638","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:14:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l3qGHwBMNd42cd3f9mW2uIhM22OmVH3p5gGuSdQU0oRJVQj13YcHP8iGtc17I5HXbXweGYFEMS56Vg+i3JrvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:41:05.546064Z"},"content_sha256":"8e5c3b8c97e1692c63a49be340b2f291c7c8b7fc406cca42cf88f0ca0913c249","schema_version":"1.0","event_id":"sha256:8e5c3b8c97e1692c63a49be340b2f291c7c8b7fc406cca42cf88f0ca0913c249"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HIJJSQULKWAPWTOIYUDS3J4GUA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generating Synthetic Text Data to Evaluate Causal Inference Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilya Shpitser, Mark Dredze, Zach Wood-Doughty","submitted_at":"2021-02-10T18:53:11Z","abstract_excerpt":"Drawing causal conclusions from observational data requires making assumptions about the true data-generating process. Causal inference research typically considers low-dimensional data, such as categorical or numerical fields in structured medical records. High-dimensional and unstructured data such as natural language complicates the evaluation of causal inference methods; such evaluations rely on synthetic datasets with known causal effects. Models for natural language generation have been widely studied and perform well empirically. However, existing methods not immediately applicable to p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05638","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/2102.05638/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:14:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2WtMELg8E6rqU/wlScoyN25q+7v5nQJOr1jzW4dR/ceUXTg1ZL8HmqvrVk9A433r1ne/U4TdoSFRblWMGp5ADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:41:05.546712Z"},"content_sha256":"e377414c5e06f33f63a68f3fa26ebadd69fa2588edfbbb4c2695d3aab96d6286","schema_version":"1.0","event_id":"sha256:e377414c5e06f33f63a68f3fa26ebadd69fa2588edfbbb4c2695d3aab96d6286"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HIJJSQULKWAPWTOIYUDS3J4GUA/bundle.json","state_url":"https://pith.science/pith/HIJJSQULKWAPWTOIYUDS3J4GUA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HIJJSQULKWAPWTOIYUDS3J4GUA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T06:41:05Z","links":{"resolver":"https://pith.science/pith/HIJJSQULKWAPWTOIYUDS3J4GUA","bundle":"https://pith.science/pith/HIJJSQULKWAPWTOIYUDS3J4GUA/bundle.json","state":"https://pith.science/pith/HIJJSQULKWAPWTOIYUDS3J4GUA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HIJJSQULKWAPWTOIYUDS3J4GUA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HIJJSQULKWAPWTOIYUDS3J4GUA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"29bc57766b7d51e63e3a3c48517013d85046210eef90efc7ead6b69e700382ca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-10T18:53:11Z","title_canon_sha256":"00d1f02912392758a8aac07a8b64764f841f9c68ef7267b41c664de7950242ee"},"schema_version":"1.0","source":{"id":"2102.05638","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.05638","created_at":"2026-07-05T02:14:20Z"},{"alias_kind":"arxiv_version","alias_value":"2102.05638v1","created_at":"2026-07-05T02:14:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05638","created_at":"2026-07-05T02:14:20Z"},{"alias_kind":"pith_short_12","alias_value":"HIJJSQULKWAP","created_at":"2026-07-05T02:14:20Z"},{"alias_kind":"pith_short_16","alias_value":"HIJJSQULKWAPWTOI","created_at":"2026-07-05T02:14:20Z"},{"alias_kind":"pith_short_8","alias_value":"HIJJSQUL","created_at":"2026-07-05T02:14:20Z"}],"graph_snapshots":[{"event_id":"sha256:e377414c5e06f33f63a68f3fa26ebadd69fa2588edfbbb4c2695d3aab96d6286","target":"graph","created_at":"2026-07-05T02:14:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2102.05638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Drawing causal conclusions from observational data requires making assumptions about the true data-generating process. Causal inference research typically considers low-dimensional data, such as categorical or numerical fields in structured medical records. High-dimensional and unstructured data such as natural language complicates the evaluation of causal inference methods; such evaluations rely on synthetic datasets with known causal effects. Models for natural language generation have been widely studied and perform well empirically. However, existing methods not immediately applicable to p","authors_text":"Ilya Shpitser, Mark Dredze, Zach Wood-Doughty","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-10T18:53:11Z","title":"Generating Synthetic Text Data to Evaluate Causal Inference Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05638","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e5c3b8c97e1692c63a49be340b2f291c7c8b7fc406cca42cf88f0ca0913c249","target":"record","created_at":"2026-07-05T02:14:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"29bc57766b7d51e63e3a3c48517013d85046210eef90efc7ead6b69e700382ca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-10T18:53:11Z","title_canon_sha256":"00d1f02912392758a8aac07a8b64764f841f9c68ef7267b41c664de7950242ee"},"schema_version":"1.0","source":{"id":"2102.05638","kind":"arxiv","version":1}},"canonical_sha256":"3a1299428b5580fb4dc8c5072da786a01b0bf898fba915ec6f0918561398d21a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a1299428b5580fb4dc8c5072da786a01b0bf898fba915ec6f0918561398d21a","first_computed_at":"2026-07-05T02:14:20.529149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:20.529149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"380ynew9Ep72JDAaKbwgzkT1axM4yU0kg7Zp8hTLS6gakuQFjzoUi/3DuXChKGKNp9nB+8rQofnE2kfrkgjXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:20.529766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.05638","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e5c3b8c97e1692c63a49be340b2f291c7c8b7fc406cca42cf88f0ca0913c249","sha256:e377414c5e06f33f63a68f3fa26ebadd69fa2588edfbbb4c2695d3aab96d6286"],"state_sha256":"825fc80b3560b61dd1e0d524da17a017e78ef87ee9960c4dfa9764c2110cf388"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zP6myJi5Oj8VBe9l7ucnBFSaGDKB3wfx/N63vVuS3r+rru1S4b+UyLDGObDZaN4HKtYlkl3XEhpmTvFma1XiAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T06:41:05.550959Z","bundle_sha256":"a5d5b82cd4d60a8f9b9f243b7c2ecedd166b4b6723b3d6eb1b400fca2bad1e87"}}