{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FZ6GZLVQVNFF3ICMOXM3XVPDTZ","short_pith_number":"pith:FZ6GZLVQ","canonical_record":{"source":{"id":"2407.10956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-15T17:54:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6cb43df52e695afa63f3158d93d0bf0d7a8404a55d93e4d268c00ec107b34760","abstract_canon_sha256":"7420724f0af8cdc88b274e77b9620648dbeaa0e0cee5c13e8d934fdcb2ad5c58"},"schema_version":"1.0"},"canonical_sha256":"2e7c6caeb0ab4a5da04c75d9bbd5e39e5c2ac6719ca84c603e308e23dc738790","source":{"kind":"arxiv","id":"2407.10956","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10956","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10956v1","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10956","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"pith_short_12","alias_value":"FZ6GZLVQVNFF","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"pith_short_16","alias_value":"FZ6GZLVQVNFF3ICM","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"pith_short_8","alias_value":"FZ6GZLVQ","created_at":"2026-07-05T08:44:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FZ6GZLVQVNFF3ICMOXM3XVPDTZ","target":"record","payload":{"canonical_record":{"source":{"id":"2407.10956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-15T17:54:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6cb43df52e695afa63f3158d93d0bf0d7a8404a55d93e4d268c00ec107b34760","abstract_canon_sha256":"7420724f0af8cdc88b274e77b9620648dbeaa0e0cee5c13e8d934fdcb2ad5c58"},"schema_version":"1.0"},"canonical_sha256":"2e7c6caeb0ab4a5da04c75d9bbd5e39e5c2ac6719ca84c603e308e23dc738790","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:06.928351Z","signature_b64":"hEUvHNYvoODWzF9i94CHaOFfFC5K9Jmiyu8OTQYHgfHa3mQudlvj2ANXNRCRdeewXjsHnLZ7OwWwmCE15ZNeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e7c6caeb0ab4a5da04c75d9bbd5e39e5c2ac6719ca84c603e308e23dc738790","last_reissued_at":"2026-07-05T08:44:06.927915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:06.927915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.10956","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":"2026-07-05T08:44:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1DV+rv5niAnstqqqi3sn478DSMY7fv1U0dABbN8Jjczl6rVDlnVYUGTpFFw73JIoaZMex7UHCjKCBFaIXzNcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:03:07.503972Z"},"content_sha256":"aa52516abadd3cf549cbb416940381a4886ac8181591560a1bd78ef00e03daec","schema_version":"1.0","event_id":"sha256:aa52516abadd3cf549cbb416940381a4886ac8181591560a1bd78ef00e03daec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FZ6GZLVQVNFF3ICMOXM3XVPDTZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ansong Ni, Caiming Xiong, Danyang Zhang, Fangyu Lei, Hanchong Zhang, Haoyuan Wu, Hongcheng Gao, Hongshen Xu, Jixuan Chen, Kai Yu, Lu Chen, Pengcheng Yin, Qian Liu, Ruisheng Cao, Ruoxi Sun, Sida Wang, Tao Yu, Tianbao Xie, Victor Zhong, Wenjing Hu, Xinzhuang Xiong, Yeqiao Fu, Yuchen Mao","submitted_at":"2024-07-15T17:54:37Z","abstract_excerpt":"Data science and engineering workflows often span multiple stages, from warehousing to orchestration, using tools like BigQuery, dbt, and Airbyte. As vision language models (VLMs) advance in multimodal understanding and code generation, VLM-based agents could potentially automate these workflows by generating SQL queries, Python code, and GUI operations. This automation can improve the productivity of experts while democratizing access to large-scale data analysis. In this paper, we introduce Spider2-V, the first multimodal agent benchmark focusing on professional data science and engineering "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10956","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/2407.10956/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":"2026-07-05T08:44:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CHt3e3K4hwc4buZyooAsW3CmnQ9qMKpcQFkoOwP28YuZnk1CLFi1XdfL0sAigaUgpzZCfMcmCYNDAHHx3LsODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:03:07.504997Z"},"content_sha256":"a66ffc0183ddf574ef77cc97d5182e37faced2a869c16348d139b7677fce1af8","schema_version":"1.0","event_id":"sha256:a66ffc0183ddf574ef77cc97d5182e37faced2a869c16348d139b7677fce1af8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/bundle.json","state_url":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/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":"2026-08-05T03:03:07Z","links":{"resolver":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ","bundle":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/bundle.json","state":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FZ6GZLVQVNFF3ICMOXM3XVPDTZ","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":"7420724f0af8cdc88b274e77b9620648dbeaa0e0cee5c13e8d934fdcb2ad5c58","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-15T17:54:37Z","title_canon_sha256":"6cb43df52e695afa63f3158d93d0bf0d7a8404a55d93e4d268c00ec107b34760"},"schema_version":"1.0","source":{"id":"2407.10956","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10956","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10956v1","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10956","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"pith_short_12","alias_value":"FZ6GZLVQVNFF","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"pith_short_16","alias_value":"FZ6GZLVQVNFF3ICM","created_at":"2026-07-05T08:44:06Z"},{"alias_kind":"pith_short_8","alias_value":"FZ6GZLVQ","created_at":"2026-07-05T08:44:06Z"}],"graph_snapshots":[{"event_id":"sha256:a66ffc0183ddf574ef77cc97d5182e37faced2a869c16348d139b7677fce1af8","target":"graph","created_at":"2026-07-05T08:44:06Z","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/2407.10956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data science and engineering workflows often span multiple stages, from warehousing to orchestration, using tools like BigQuery, dbt, and Airbyte. As vision language models (VLMs) advance in multimodal understanding and code generation, VLM-based agents could potentially automate these workflows by generating SQL queries, Python code, and GUI operations. This automation can improve the productivity of experts while democratizing access to large-scale data analysis. In this paper, we introduce Spider2-V, the first multimodal agent benchmark focusing on professional data science and engineering ","authors_text":"Ansong Ni, Caiming Xiong, Danyang Zhang, Fangyu Lei, Hanchong Zhang, Haoyuan Wu, Hongcheng Gao, Hongshen Xu, Jixuan Chen, Kai Yu, Lu Chen, Pengcheng Yin, Qian Liu, Ruisheng Cao, Ruoxi Sun, Sida Wang, Tao Yu, Tianbao Xie, Victor Zhong, Wenjing Hu, Xinzhuang Xiong, Yeqiao Fu, Yuchen Mao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-15T17:54:37Z","title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10956","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:aa52516abadd3cf549cbb416940381a4886ac8181591560a1bd78ef00e03daec","target":"record","created_at":"2026-07-05T08:44:06Z","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":"7420724f0af8cdc88b274e77b9620648dbeaa0e0cee5c13e8d934fdcb2ad5c58","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-15T17:54:37Z","title_canon_sha256":"6cb43df52e695afa63f3158d93d0bf0d7a8404a55d93e4d268c00ec107b34760"},"schema_version":"1.0","source":{"id":"2407.10956","kind":"arxiv","version":1}},"canonical_sha256":"2e7c6caeb0ab4a5da04c75d9bbd5e39e5c2ac6719ca84c603e308e23dc738790","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e7c6caeb0ab4a5da04c75d9bbd5e39e5c2ac6719ca84c603e308e23dc738790","first_computed_at":"2026-07-05T08:44:06.927915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:06.927915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hEUvHNYvoODWzF9i94CHaOFfFC5K9Jmiyu8OTQYHgfHa3mQudlvj2ANXNRCRdeewXjsHnLZ7OwWwmCE15ZNeCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:06.928351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10956","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa52516abadd3cf549cbb416940381a4886ac8181591560a1bd78ef00e03daec","sha256:a66ffc0183ddf574ef77cc97d5182e37faced2a869c16348d139b7677fce1af8"],"state_sha256":"af415aba6536b20dded3a0f1a7abdd1d69ec25a1c7ebada1b659a392e1ce3f15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jdpIUxudGj30ER5vEAIBI91wgEuQVfVguXpAEQsTmG8gR8z0S94Gvz1rzbke1W+CirfCMzCdyK2QYiNG2uaaDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:03:07.510960Z","bundle_sha256":"1b41f01c68e3dc226b9b458949d888a42ff48a0adb40bdf7a2adc54f2ad1c203"}}