{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VDTQK5XSASNILLSSFYXYJDB7R6","short_pith_number":"pith:VDTQK5XS","canonical_record":{"source":{"id":"2402.17168","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-27T03:03:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fc8419328e14e12ca590ada9c3593db26e4cb8e3d1b3f2b4a2ea0edff3b635a9","abstract_canon_sha256":"63819eac09b1060a4754e8ba013c0c8a26c1f45f0125ba8a599f0778ac24973f"},"schema_version":"1.0"},"canonical_sha256":"a8e70576f2049a85ae522e2f848c3f8f84c94674b2fbbba4cdb43ad8b29ae20b","source":{"kind":"arxiv","id":"2402.17168","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17168","created_at":"2026-07-05T07:49:43Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17168v1","created_at":"2026-07-05T07:49:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17168","created_at":"2026-07-05T07:49:43Z"},{"alias_kind":"pith_short_12","alias_value":"VDTQK5XSASNI","created_at":"2026-07-05T07:49:43Z"},{"alias_kind":"pith_short_16","alias_value":"VDTQK5XSASNILLSS","created_at":"2026-07-05T07:49:43Z"},{"alias_kind":"pith_short_8","alias_value":"VDTQK5XS","created_at":"2026-07-05T07:49:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VDTQK5XSASNILLSSFYXYJDB7R6","target":"record","payload":{"canonical_record":{"source":{"id":"2402.17168","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-27T03:03:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fc8419328e14e12ca590ada9c3593db26e4cb8e3d1b3f2b4a2ea0edff3b635a9","abstract_canon_sha256":"63819eac09b1060a4754e8ba013c0c8a26c1f45f0125ba8a599f0778ac24973f"},"schema_version":"1.0"},"canonical_sha256":"a8e70576f2049a85ae522e2f848c3f8f84c94674b2fbbba4cdb43ad8b29ae20b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:43.503465Z","signature_b64":"DB46jZ7pj6e+nZ+FuW/udyKJnVyAAHmTMP/EpqhIl6YJogO0RLKUSUFhkbm6zWEylEYG0Q+htksK8H8gmOXQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8e70576f2049a85ae522e2f848c3f8f84c94674b2fbbba4cdb43ad8b29ae20b","last_reissued_at":"2026-07-05T07:49:43.502995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:43.502995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.17168","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":"2026-07-05T07:49:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQa2m6i3E40zgh6tL8uLjZcUj30MWboE7cSxAgDX7smdReE+RZwmK7goSuIts5dqwBHhntoT0W8lvpQAl9D0CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:15:32.609004Z"},"content_sha256":"c3d434613f4608895cc7edbf1b68e1b54fd134ffb1ed8fe2100bd326827503bc","schema_version":"1.0","event_id":"sha256:c3d434613f4608895cc7edbf1b68e1b54fd134ffb1ed8fe2100bd326827503bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VDTQK5XSASNILLSSFYXYJDB7R6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Data Science Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Kan Ren, Nan Chen, Qiyang Jiang, Xingyu Han, Yuge Zhang, Yuqing Yang","submitted_at":"2024-02-27T03:03:06Z","abstract_excerpt":"In the era of data-driven decision-making, the complexity of data analysis necessitates advanced expertise and tools of data science, presenting significant challenges even for specialists. Large Language Models (LLMs) have emerged as promising aids as data science agents, assisting humans in data analysis and processing. Yet their practical efficacy remains constrained by the varied demands of real-world applications and complicated analytical process. In this paper, we introduce DSEval -- a novel evaluation paradigm, as well as a series of innovative benchmarks tailored for assessing the per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17168","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/2402.17168/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":"2026-07-05T07:49:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZkFhkIvllwCz2CxFYvjuaWK+GmiBUsAQCVxlUQb+cQ/yYSzm77QpFz98E33pv90azCO7FSuk8tx2P5YF9OZPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:15:32.609515Z"},"content_sha256":"a0cd60cdceaa49648d6ee909d5f39b2bf8f564f468b34fdb4592eafe9f44e213","schema_version":"1.0","event_id":"sha256:a0cd60cdceaa49648d6ee909d5f39b2bf8f564f468b34fdb4592eafe9f44e213"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VDTQK5XSASNILLSSFYXYJDB7R6/bundle.json","state_url":"https://pith.science/pith/VDTQK5XSASNILLSSFYXYJDB7R6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VDTQK5XSASNILLSSFYXYJDB7R6/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":"2026-08-04T15:15:32Z","links":{"resolver":"https://pith.science/pith/VDTQK5XSASNILLSSFYXYJDB7R6","bundle":"https://pith.science/pith/VDTQK5XSASNILLSSFYXYJDB7R6/bundle.json","state":"https://pith.science/pith/VDTQK5XSASNILLSSFYXYJDB7R6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VDTQK5XSASNILLSSFYXYJDB7R6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VDTQK5XSASNILLSSFYXYJDB7R6","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":"63819eac09b1060a4754e8ba013c0c8a26c1f45f0125ba8a599f0778ac24973f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-27T03:03:06Z","title_canon_sha256":"fc8419328e14e12ca590ada9c3593db26e4cb8e3d1b3f2b4a2ea0edff3b635a9"},"schema_version":"1.0","source":{"id":"2402.17168","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17168","created_at":"2026-07-05T07:49:43Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17168v1","created_at":"2026-07-05T07:49:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17168","created_at":"2026-07-05T07:49:43Z"},{"alias_kind":"pith_short_12","alias_value":"VDTQK5XSASNI","created_at":"2026-07-05T07:49:43Z"},{"alias_kind":"pith_short_16","alias_value":"VDTQK5XSASNILLSS","created_at":"2026-07-05T07:49:43Z"},{"alias_kind":"pith_short_8","alias_value":"VDTQK5XS","created_at":"2026-07-05T07:49:43Z"}],"graph_snapshots":[{"event_id":"sha256:a0cd60cdceaa49648d6ee909d5f39b2bf8f564f468b34fdb4592eafe9f44e213","target":"graph","created_at":"2026-07-05T07:49:43Z","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/2402.17168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the era of data-driven decision-making, the complexity of data analysis necessitates advanced expertise and tools of data science, presenting significant challenges even for specialists. Large Language Models (LLMs) have emerged as promising aids as data science agents, assisting humans in data analysis and processing. Yet their practical efficacy remains constrained by the varied demands of real-world applications and complicated analytical process. In this paper, we introduce DSEval -- a novel evaluation paradigm, as well as a series of innovative benchmarks tailored for assessing the per","authors_text":"Kan Ren, Nan Chen, Qiyang Jiang, Xingyu Han, Yuge Zhang, Yuqing Yang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-27T03:03:06Z","title":"Benchmarking Data Science Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17168","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:c3d434613f4608895cc7edbf1b68e1b54fd134ffb1ed8fe2100bd326827503bc","target":"record","created_at":"2026-07-05T07:49:43Z","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":"63819eac09b1060a4754e8ba013c0c8a26c1f45f0125ba8a599f0778ac24973f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-27T03:03:06Z","title_canon_sha256":"fc8419328e14e12ca590ada9c3593db26e4cb8e3d1b3f2b4a2ea0edff3b635a9"},"schema_version":"1.0","source":{"id":"2402.17168","kind":"arxiv","version":1}},"canonical_sha256":"a8e70576f2049a85ae522e2f848c3f8f84c94674b2fbbba4cdb43ad8b29ae20b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8e70576f2049a85ae522e2f848c3f8f84c94674b2fbbba4cdb43ad8b29ae20b","first_computed_at":"2026-07-05T07:49:43.502995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:43.502995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DB46jZ7pj6e+nZ+FuW/udyKJnVyAAHmTMP/EpqhIl6YJogO0RLKUSUFhkbm6zWEylEYG0Q+htksK8H8gmOXQDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:43.503465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17168","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3d434613f4608895cc7edbf1b68e1b54fd134ffb1ed8fe2100bd326827503bc","sha256:a0cd60cdceaa49648d6ee909d5f39b2bf8f564f468b34fdb4592eafe9f44e213"],"state_sha256":"1e99359f8c89eb65171a92e4fb5a277f7f68883a94f5e2a44ca146f106066051"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ioBczRzzB1x3DrB9vmGyO5O6VBLAXeLfELBW5T5bxyjwgOaMjWQH3fbLU6a2RtaKL/gNCd3UuLgze+CY4DtRDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:15:32.613845Z","bundle_sha256":"d537fc5c1d7b8de2403a15c2df1d1bb40d3a174c746233c2eb79235ee19b0ea9"}}