{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FECJ2OC7FXNWG32QGNDT4M7SBA","short_pith_number":"pith:FECJ2OC7","canonical_record":{"source":{"id":"2505.18223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:37:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c7db140963df01fadf8a35a4539d075f324e4d3a1729077b2903ade4d3f5a83","abstract_canon_sha256":"03f2a8c70f4f50c8ae7d91052a2f684dd78427f09ed53b76b5d8e4f892c112c1"},"schema_version":"1.0"},"canonical_sha256":"29049d385f2ddb636f5033473e33f20830f4da0d7027b1c516fa1d1c1d8062d4","source":{"kind":"arxiv","id":"2505.18223","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18223","created_at":"2026-07-05T11:16:58Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18223v2","created_at":"2026-07-05T11:16:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18223","created_at":"2026-07-05T11:16:58Z"},{"alias_kind":"pith_short_12","alias_value":"FECJ2OC7FXNW","created_at":"2026-07-05T11:16:58Z"},{"alias_kind":"pith_short_16","alias_value":"FECJ2OC7FXNWG32Q","created_at":"2026-07-05T11:16:58Z"},{"alias_kind":"pith_short_8","alias_value":"FECJ2OC7","created_at":"2026-07-05T11:16:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FECJ2OC7FXNWG32QGNDT4M7SBA","target":"record","payload":{"canonical_record":{"source":{"id":"2505.18223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:37:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c7db140963df01fadf8a35a4539d075f324e4d3a1729077b2903ade4d3f5a83","abstract_canon_sha256":"03f2a8c70f4f50c8ae7d91052a2f684dd78427f09ed53b76b5d8e4f892c112c1"},"schema_version":"1.0"},"canonical_sha256":"29049d385f2ddb636f5033473e33f20830f4da0d7027b1c516fa1d1c1d8062d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:58.448161Z","signature_b64":"yawGWob4Y6v1f+ATOE4Qy3vnyavUtqTBqA+D//XD5sGJlWNIFgeXiad5wZSffrg8SUFu6/bXrumBl+ei8XHLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29049d385f2ddb636f5033473e33f20830f4da0d7027b1c516fa1d1c1d8062d4","last_reissued_at":"2026-07-05T11:16:58.447596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:58.447596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.18223","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yc1Nfw5mWGdXxA56pjKNKzpSbbz9FGxh9/lsgV8UvLMX5Mm9ml6ZMQ61F7nHLCQFxc1xJT+kLyMmdOb/TL7TBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:08:46.295144Z"},"content_sha256":"680e775963b6e18289ed1478106adcd2efda161d9ae779c82deb435bb5105ea4","schema_version":"1.0","event_id":"sha256:680e775963b6e18289ed1478106adcd2efda161d9ae779c82deb435bb5105ea4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FECJ2OC7FXNWG32QGNDT4M7SBA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hanyu Li, Haoyu Liu, Michael I. Jordan, Tianyu Guo, Tingyu Zhu, Xiaotie Deng, Zeyu Zheng","submitted_at":"2025-05-23T09:37:52Z","abstract_excerpt":"Large Language Models (LLMs) show promise as data analysis agents, but existing benchmarks overlook the iterative nature of the field, where experts' decisions evolve with deeper insights of the dataset. To address this, we introduce IDA-Bench, a novel benchmark evaluating LLM agents in multi-round interactive scenarios. Derived from complex Kaggle notebooks, tasks are presented as sequential natural language instructions by an LLM-simulated user. Agent performance is judged by comparing its final numerical output to the human-derived baseline. Initial results show that even state-of-the-art c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18223","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/2505.18223/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":"2026-07-05T11:16:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2fQSBwArULPVtKU9rvic9eAKXu1RtkKUd6Fw3lddzIHqOw2bkaTOM4gqgzxZy9q2gYVuR9NuZUTwxy2Ysy7/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:08:46.295638Z"},"content_sha256":"3268d502b91ef1cb7905099c63224c37cc63b4417843184a0a3a53c4a836f1f6","schema_version":"1.0","event_id":"sha256:3268d502b91ef1cb7905099c63224c37cc63b4417843184a0a3a53c4a836f1f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FECJ2OC7FXNWG32QGNDT4M7SBA/bundle.json","state_url":"https://pith.science/pith/FECJ2OC7FXNWG32QGNDT4M7SBA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FECJ2OC7FXNWG32QGNDT4M7SBA/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":"2026-08-09T01:08:46Z","links":{"resolver":"https://pith.science/pith/FECJ2OC7FXNWG32QGNDT4M7SBA","bundle":"https://pith.science/pith/FECJ2OC7FXNWG32QGNDT4M7SBA/bundle.json","state":"https://pith.science/pith/FECJ2OC7FXNWG32QGNDT4M7SBA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FECJ2OC7FXNWG32QGNDT4M7SBA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FECJ2OC7FXNWG32QGNDT4M7SBA","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":"03f2a8c70f4f50c8ae7d91052a2f684dd78427f09ed53b76b5d8e4f892c112c1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:37:52Z","title_canon_sha256":"2c7db140963df01fadf8a35a4539d075f324e4d3a1729077b2903ade4d3f5a83"},"schema_version":"1.0","source":{"id":"2505.18223","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18223","created_at":"2026-07-05T11:16:58Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18223v2","created_at":"2026-07-05T11:16:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18223","created_at":"2026-07-05T11:16:58Z"},{"alias_kind":"pith_short_12","alias_value":"FECJ2OC7FXNW","created_at":"2026-07-05T11:16:58Z"},{"alias_kind":"pith_short_16","alias_value":"FECJ2OC7FXNWG32Q","created_at":"2026-07-05T11:16:58Z"},{"alias_kind":"pith_short_8","alias_value":"FECJ2OC7","created_at":"2026-07-05T11:16:58Z"}],"graph_snapshots":[{"event_id":"sha256:3268d502b91ef1cb7905099c63224c37cc63b4417843184a0a3a53c4a836f1f6","target":"graph","created_at":"2026-07-05T11:16:58Z","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/2505.18223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) show promise as data analysis agents, but existing benchmarks overlook the iterative nature of the field, where experts' decisions evolve with deeper insights of the dataset. To address this, we introduce IDA-Bench, a novel benchmark evaluating LLM agents in multi-round interactive scenarios. Derived from complex Kaggle notebooks, tasks are presented as sequential natural language instructions by an LLM-simulated user. Agent performance is judged by comparing its final numerical output to the human-derived baseline. Initial results show that even state-of-the-art c","authors_text":"Hanyu Li, Haoyu Liu, Michael I. Jordan, Tianyu Guo, Tingyu Zhu, Xiaotie Deng, Zeyu Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:37:52Z","title":"IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18223","kind":"arxiv","version":2},"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":"sha256:680e775963b6e18289ed1478106adcd2efda161d9ae779c82deb435bb5105ea4","target":"record","created_at":"2026-07-05T11:16:58Z","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":"03f2a8c70f4f50c8ae7d91052a2f684dd78427f09ed53b76b5d8e4f892c112c1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:37:52Z","title_canon_sha256":"2c7db140963df01fadf8a35a4539d075f324e4d3a1729077b2903ade4d3f5a83"},"schema_version":"1.0","source":{"id":"2505.18223","kind":"arxiv","version":2}},"canonical_sha256":"29049d385f2ddb636f5033473e33f20830f4da0d7027b1c516fa1d1c1d8062d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29049d385f2ddb636f5033473e33f20830f4da0d7027b1c516fa1d1c1d8062d4","first_computed_at":"2026-07-05T11:16:58.447596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:58.447596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yawGWob4Y6v1f+ATOE4Qy3vnyavUtqTBqA+D//XD5sGJlWNIFgeXiad5wZSffrg8SUFu6/bXrumBl+ei8XHLBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:58.448161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18223","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:680e775963b6e18289ed1478106adcd2efda161d9ae779c82deb435bb5105ea4","sha256:3268d502b91ef1cb7905099c63224c37cc63b4417843184a0a3a53c4a836f1f6"],"state_sha256":"52dc6ed78af06c15965c8da8eee3ca8f4df081bff39fbef86488f847ae829a12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1z35f3ZXIJzYB9ef5njwbYszgIrLyULzwhw1VdlXyjaab/PWfPl4mKFloqpgHd/PTx+HVHmLSFK9I9zZQbmvAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:08:46.299403Z","bundle_sha256":"92591c33d73de9baa5334cbfaf7149db1207ee6c122054652a9f783d67a5a1ef"}}