{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EYPEJR3BQ47MI5YMMD7KUBUJJJ","short_pith_number":"pith:EYPEJR3B","canonical_record":{"source":{"id":"2607.08093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T04:03:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"eec64ba15e9a62a83e1db684ae3610989f669ebb9c9ec9fa63c53c8b42ca165a","abstract_canon_sha256":"9345caee0f56996d0b1e552cc30492ce484c6ece55bb88239ef873c3cc63fbd6"},"schema_version":"1.0"},"canonical_sha256":"261e44c761873ec4770c60feaa06894a419b1b383677ec9ade3f70ad168adb35","source":{"kind":"arxiv","id":"2607.08093","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08093","created_at":"2026-07-10T01:19:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08093v1","created_at":"2026-07-10T01:19:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08093","created_at":"2026-07-10T01:19:25Z"},{"alias_kind":"pith_short_12","alias_value":"EYPEJR3BQ47M","created_at":"2026-07-10T01:19:25Z"},{"alias_kind":"pith_short_16","alias_value":"EYPEJR3BQ47MI5YM","created_at":"2026-07-10T01:19:25Z"},{"alias_kind":"pith_short_8","alias_value":"EYPEJR3B","created_at":"2026-07-10T01:19:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EYPEJR3BQ47MI5YMMD7KUBUJJJ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.08093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T04:03:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"eec64ba15e9a62a83e1db684ae3610989f669ebb9c9ec9fa63c53c8b42ca165a","abstract_canon_sha256":"9345caee0f56996d0b1e552cc30492ce484c6ece55bb88239ef873c3cc63fbd6"},"schema_version":"1.0"},"canonical_sha256":"261e44c761873ec4770c60feaa06894a419b1b383677ec9ade3f70ad168adb35","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:25.844928Z","signature_b64":"5C07ltnGITpmtloggHUgt+3RfIdbrY+Li43SFDFmyeQa0B9bnkAAW2tNw0V7oLtmMHk35WuvfNrVrKwguwNKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"261e44c761873ec4770c60feaa06894a419b1b383677ec9ade3f70ad168adb35","last_reissued_at":"2026-07-10T01:19:25.844424Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:25.844424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.08093","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":"2026-07-10T01:19:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AjMyMA5GpEOYDMKsJMhx7S4K5xop5mnyhjdH6UAICtfJCLNXfsJ2qX4OdkkdKROEV2jmkB8yFn3a/EA/lDdRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:43:40.305349Z"},"content_sha256":"97f46a4fefad4bbe5f60c1f0a0ce1606ee3ec6874106cb0911800cb43bf63c54","schema_version":"1.0","event_id":"sha256:97f46a4fefad4bbe5f60c1f0a0ce1606ee3ec6874106cb0911800cb43bf63c54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EYPEJR3BQ47MI5YMMD7KUBUJJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CausalDS: Benchmarking Causal Reasoning in Data-Science Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Andrej Leban, Yuekai Sun","submitted_at":"2026-07-09T04:03:26Z","abstract_excerpt":"Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use. Yet the relevant benchmark landscape largely divides into symbolic causal reasoning benchmarks without realistic data analysis or data analysis benchmarks without a principled causal data-generating structure. Furthermore, existing causal evaluation datasets are often restricted to curated examples from existing sources, with diversity coming from limited templatized variations rather than from systematic generation of novel synthetic causal structures. We intro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08093","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/2607.08093/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":"2026-07-10T01:19:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gOr9zTXSeYgCNLQTnJ+goOMuM5KHC4/S/gyJSdaLfc+vla8Wlt9Vq8lWKtaC36TgTt01Gk68byHxB4TZ3zAuDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:43:40.305843Z"},"content_sha256":"2dc85a20f3c71a8d2af282fe90f98292f703988fbc8b3cfa7a372475c4dfaed8","schema_version":"1.0","event_id":"sha256:2dc85a20f3c71a8d2af282fe90f98292f703988fbc8b3cfa7a372475c4dfaed8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EYPEJR3BQ47MI5YMMD7KUBUJJJ/bundle.json","state_url":"https://pith.science/pith/EYPEJR3BQ47MI5YMMD7KUBUJJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EYPEJR3BQ47MI5YMMD7KUBUJJJ/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":"2026-08-10T18:43:40Z","links":{"resolver":"https://pith.science/pith/EYPEJR3BQ47MI5YMMD7KUBUJJJ","bundle":"https://pith.science/pith/EYPEJR3BQ47MI5YMMD7KUBUJJJ/bundle.json","state":"https://pith.science/pith/EYPEJR3BQ47MI5YMMD7KUBUJJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EYPEJR3BQ47MI5YMMD7KUBUJJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EYPEJR3BQ47MI5YMMD7KUBUJJJ","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":"9345caee0f56996d0b1e552cc30492ce484c6ece55bb88239ef873c3cc63fbd6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T04:03:26Z","title_canon_sha256":"eec64ba15e9a62a83e1db684ae3610989f669ebb9c9ec9fa63c53c8b42ca165a"},"schema_version":"1.0","source":{"id":"2607.08093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08093","created_at":"2026-07-10T01:19:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08093v1","created_at":"2026-07-10T01:19:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08093","created_at":"2026-07-10T01:19:25Z"},{"alias_kind":"pith_short_12","alias_value":"EYPEJR3BQ47M","created_at":"2026-07-10T01:19:25Z"},{"alias_kind":"pith_short_16","alias_value":"EYPEJR3BQ47MI5YM","created_at":"2026-07-10T01:19:25Z"},{"alias_kind":"pith_short_8","alias_value":"EYPEJR3B","created_at":"2026-07-10T01:19:25Z"}],"graph_snapshots":[{"event_id":"sha256:2dc85a20f3c71a8d2af282fe90f98292f703988fbc8b3cfa7a372475c4dfaed8","target":"graph","created_at":"2026-07-10T01:19:25Z","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/2607.08093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use. Yet the relevant benchmark landscape largely divides into symbolic causal reasoning benchmarks without realistic data analysis or data analysis benchmarks without a principled causal data-generating structure. Furthermore, existing causal evaluation datasets are often restricted to curated examples from existing sources, with diversity coming from limited templatized variations rather than from systematic generation of novel synthetic causal structures. We intro","authors_text":"Andrej Leban, Yuekai Sun","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T04:03:26Z","title":"CausalDS: Benchmarking Causal Reasoning in Data-Science Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08093","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":"sha256:97f46a4fefad4bbe5f60c1f0a0ce1606ee3ec6874106cb0911800cb43bf63c54","target":"record","created_at":"2026-07-10T01:19:25Z","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":"9345caee0f56996d0b1e552cc30492ce484c6ece55bb88239ef873c3cc63fbd6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-09T04:03:26Z","title_canon_sha256":"eec64ba15e9a62a83e1db684ae3610989f669ebb9c9ec9fa63c53c8b42ca165a"},"schema_version":"1.0","source":{"id":"2607.08093","kind":"arxiv","version":1}},"canonical_sha256":"261e44c761873ec4770c60feaa06894a419b1b383677ec9ade3f70ad168adb35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"261e44c761873ec4770c60feaa06894a419b1b383677ec9ade3f70ad168adb35","first_computed_at":"2026-07-10T01:19:25.844424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:25.844424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5C07ltnGITpmtloggHUgt+3RfIdbrY+Li43SFDFmyeQa0B9bnkAAW2tNw0V7oLtmMHk35WuvfNrVrKwguwNKDg==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:25.844928Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97f46a4fefad4bbe5f60c1f0a0ce1606ee3ec6874106cb0911800cb43bf63c54","sha256:2dc85a20f3c71a8d2af282fe90f98292f703988fbc8b3cfa7a372475c4dfaed8"],"state_sha256":"f83eea2b75e2e76a5439017995d6af7986d143c9dee6f0f874211fec21836304"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ofClc+0zqXQxVcwbIB//LBgGcz1JNjrpWVGOB/mPCFOasPdkpPQU+kqVtzzwa3/fnuAanc4FzG/hcgJKVqVZAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:43:40.310451Z","bundle_sha256":"f999fb6a7fc8e3992909b652531fb0536b88f169102aed3e1b6ceeec74c047e1"}}