{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YBIEJNV45OF3UDO64QD3TTWHUO","short_pith_number":"pith:YBIEJNV4","canonical_record":{"source":{"id":"2507.23336","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T08:32:37Z","cross_cats_sorted":["cs.CL","cs.MA"],"title_canon_sha256":"374b55f4b3349d0a0198191aa678d1503067e678169d38a3ef4a6881a0342715","abstract_canon_sha256":"806510c52274cab0669292e86053a7926ccc39ade7e8aacc29ab3a9347b8f0db"},"schema_version":"1.0"},"canonical_sha256":"c05044b6bceb8bba0ddee407b9cec7a3b8b31a0d594cd27520c421c1fb20d6f5","source":{"kind":"arxiv","id":"2507.23336","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23336","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23336v2","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23336","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"YBIEJNV45OF3","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"YBIEJNV45OF3UDO6","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"YBIEJNV4","created_at":"2026-07-05T11:49:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YBIEJNV45OF3UDO64QD3TTWHUO","target":"record","payload":{"canonical_record":{"source":{"id":"2507.23336","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T08:32:37Z","cross_cats_sorted":["cs.CL","cs.MA"],"title_canon_sha256":"374b55f4b3349d0a0198191aa678d1503067e678169d38a3ef4a6881a0342715","abstract_canon_sha256":"806510c52274cab0669292e86053a7926ccc39ade7e8aacc29ab3a9347b8f0db"},"schema_version":"1.0"},"canonical_sha256":"c05044b6bceb8bba0ddee407b9cec7a3b8b31a0d594cd27520c421c1fb20d6f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:58.634415Z","signature_b64":"xW47cYG1zzbh/VumHIzX5yGA+kUy2mNFSF/o689p/e13+fTfO5KR+sV5sdIcNq2emi3NmB+tMvgDv1+SWxl5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c05044b6bceb8bba0ddee407b9cec7a3b8b31a0d594cd27520c421c1fb20d6f5","last_reissued_at":"2026-07-05T11:49:58.633831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:58.633831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.23336","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":"2026-07-05T11:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"senYrDeANQu94N9CMJcixeCjHfShsb0C/wZzVJZHUCcGYN3O5YKlXfO5QexQBiTM8x+oezV4QXbuPGg+e8mvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:17:00.415878Z"},"content_sha256":"13a76a8a572970a2a437733805efe4ee1eb050ec6345d736578039977db44212","schema_version":"1.0","event_id":"sha256:13a76a8a572970a2a437733805efe4ee1eb050ec6345d736578039977db44212"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YBIEJNV45OF3UDO64QD3TTWHUO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DSBC : Data Science task Benchmarking with Context engineering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.MA"],"primary_cat":"cs.AI","authors_text":"Ali Shafique, Giulio Martini, Hamza Farooq, Jebish Purbey, Ram Mohan Rao Kadiyala, Siddhant Gupta, Suman Debnath","submitted_at":"2025-07-31T08:32:37Z","abstract_excerpt":"Recent advances in large language models (LLMs) have significantly impacted data science workflows, giving rise to specialized data science agents designed to automate analytical tasks. Despite rapid adoption, systematic benchmarks evaluating the efficacy and limitations of these agents remain scarce. In this paper, we introduce a comprehensive benchmark specifically crafted to reflect real-world user interactions with data science agents by observing usage of our commercial applications. We evaluate three LLMs: Claude-4.0-Sonnet, Gemini-2.5-Flash, and OpenAI-o4-Mini across three approaches: z"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23336","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/2507.23336/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":"2026-07-05T11:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"agGNz2Ou573OTXMVwxRwu+2B4OkqTdez9csSHIry2/55aFHTmY41TQacRNPCCNl9LPptqrNBbKftDZ8waHduAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:17:00.416398Z"},"content_sha256":"c7c367085631b6bc77fee4831ad60e86ced1d2ae284bcf06d837f8b2487b0335","schema_version":"1.0","event_id":"sha256:c7c367085631b6bc77fee4831ad60e86ced1d2ae284bcf06d837f8b2487b0335"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBIEJNV45OF3UDO64QD3TTWHUO/bundle.json","state_url":"https://pith.science/pith/YBIEJNV45OF3UDO64QD3TTWHUO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBIEJNV45OF3UDO64QD3TTWHUO/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":"2026-08-23T19:17:00Z","links":{"resolver":"https://pith.science/pith/YBIEJNV45OF3UDO64QD3TTWHUO","bundle":"https://pith.science/pith/YBIEJNV45OF3UDO64QD3TTWHUO/bundle.json","state":"https://pith.science/pith/YBIEJNV45OF3UDO64QD3TTWHUO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBIEJNV45OF3UDO64QD3TTWHUO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YBIEJNV45OF3UDO64QD3TTWHUO","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":"806510c52274cab0669292e86053a7926ccc39ade7e8aacc29ab3a9347b8f0db","cross_cats_sorted":["cs.CL","cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T08:32:37Z","title_canon_sha256":"374b55f4b3349d0a0198191aa678d1503067e678169d38a3ef4a6881a0342715"},"schema_version":"1.0","source":{"id":"2507.23336","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23336","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23336v2","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23336","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"YBIEJNV45OF3","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"YBIEJNV45OF3UDO6","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"YBIEJNV4","created_at":"2026-07-05T11:49:58Z"}],"graph_snapshots":[{"event_id":"sha256:c7c367085631b6bc77fee4831ad60e86ced1d2ae284bcf06d837f8b2487b0335","target":"graph","created_at":"2026-07-05T11:49:58Z","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/2507.23336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have significantly impacted data science workflows, giving rise to specialized data science agents designed to automate analytical tasks. Despite rapid adoption, systematic benchmarks evaluating the efficacy and limitations of these agents remain scarce. In this paper, we introduce a comprehensive benchmark specifically crafted to reflect real-world user interactions with data science agents by observing usage of our commercial applications. We evaluate three LLMs: Claude-4.0-Sonnet, Gemini-2.5-Flash, and OpenAI-o4-Mini across three approaches: z","authors_text":"Ali Shafique, Giulio Martini, Hamza Farooq, Jebish Purbey, Ram Mohan Rao Kadiyala, Siddhant Gupta, Suman Debnath","cross_cats":["cs.CL","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T08:32:37Z","title":"DSBC : Data Science task Benchmarking with Context engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23336","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":"sha256:13a76a8a572970a2a437733805efe4ee1eb050ec6345d736578039977db44212","target":"record","created_at":"2026-07-05T11:49:58Z","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":"806510c52274cab0669292e86053a7926ccc39ade7e8aacc29ab3a9347b8f0db","cross_cats_sorted":["cs.CL","cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T08:32:37Z","title_canon_sha256":"374b55f4b3349d0a0198191aa678d1503067e678169d38a3ef4a6881a0342715"},"schema_version":"1.0","source":{"id":"2507.23336","kind":"arxiv","version":2}},"canonical_sha256":"c05044b6bceb8bba0ddee407b9cec7a3b8b31a0d594cd27520c421c1fb20d6f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c05044b6bceb8bba0ddee407b9cec7a3b8b31a0d594cd27520c421c1fb20d6f5","first_computed_at":"2026-07-05T11:49:58.633831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:58.633831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xW47cYG1zzbh/VumHIzX5yGA+kUy2mNFSF/o689p/e13+fTfO5KR+sV5sdIcNq2emi3NmB+tMvgDv1+SWxl5Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:58.634415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.23336","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13a76a8a572970a2a437733805efe4ee1eb050ec6345d736578039977db44212","sha256:c7c367085631b6bc77fee4831ad60e86ced1d2ae284bcf06d837f8b2487b0335"],"state_sha256":"b814572780d4f33085b24f03ab08e84083487359702f6092b09538ef3023f169"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zwfj3DwbKXITenjDZEhqQHI8JXZvh6kQZfIZDJm7mVEJOncrze98jQ9zjynVZTlwA9Z6ip2UWsnadnkaarmqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T19:17:00.421189Z","bundle_sha256":"cab127ff71c1425578a29f38858617c96e1d1f9cef3ad4fb82d3ff208686e735"}}