{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YR7FQCTDUUCYBNHW7LVFZYOFXC","short_pith_number":"pith:YR7FQCTD","canonical_record":{"source":{"id":"2607.26724","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T10:14:02Z","cross_cats_sorted":[],"title_canon_sha256":"4ab03468343944fc88a39be133850b75ac21b62fb75cf7eb7917cd2a53a32227","abstract_canon_sha256":"155c5f83d7adf4301ac0c3bd57611adccab867061b9f1b1f0be05f00d9ad8dff"},"schema_version":"1.0"},"canonical_sha256":"c47e580a63a50580b4f6faea5ce1c5b88bad1e007e775fb979bc4d7bea714c97","source":{"kind":"arxiv","id":"2607.26724","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26724","created_at":"2026-07-30T01:22:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26724v1","created_at":"2026-07-30T01:22:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26724","created_at":"2026-07-30T01:22:05Z"},{"alias_kind":"pith_short_12","alias_value":"YR7FQCTDUUCY","created_at":"2026-07-30T01:22:05Z"},{"alias_kind":"pith_short_16","alias_value":"YR7FQCTDUUCYBNHW","created_at":"2026-07-30T01:22:05Z"},{"alias_kind":"pith_short_8","alias_value":"YR7FQCTD","created_at":"2026-07-30T01:22:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YR7FQCTDUUCYBNHW7LVFZYOFXC","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26724","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T10:14:02Z","cross_cats_sorted":[],"title_canon_sha256":"4ab03468343944fc88a39be133850b75ac21b62fb75cf7eb7917cd2a53a32227","abstract_canon_sha256":"155c5f83d7adf4301ac0c3bd57611adccab867061b9f1b1f0be05f00d9ad8dff"},"schema_version":"1.0"},"canonical_sha256":"c47e580a63a50580b4f6faea5ce1c5b88bad1e007e775fb979bc4d7bea714c97","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c47e580a63a50580b4f6faea5ce1c5b88bad1e007e775fb979bc4d7bea714c97","last_reissued_at":"2026-07-30T01:22:05.277265Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:22:05.277265Z"},"source_kind":"arxiv","source_id":"2607.26724","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":"2026-07-30T01:22:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KmJBSSWlSwjGLPMGs8UUcs6fNzqG8BxaIjDq1BmFs3iST2hEFGSmHaU+YWw+CrpLfndHzt6/QLKBd8W6CR5VAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:52:10.335143Z"},"content_sha256":"20553752cae9895930889bf04cc7f32f7bff9b017b6e8e2254f7013c0cd2d73b","schema_version":"1.0","event_id":"sha256:20553752cae9895930889bf04cc7f32f7bff9b017b6e8e2254f7013c0cd2d73b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YR7FQCTDUUCYBNHW7LVFZYOFXC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Depeng Jin, Jianghao Yu, Sun Yongquan, Yongjun Yang, Yong Li, Yuming Lin, Zhilun Zhou","submitted_at":"2026-07-29T10:14:02Z","abstract_excerpt":"Large language model (LLM) agents have been widely applied in automating data science tasks. However, existing methods typically rely on a limited set of provided datasets, and they face challenges in data-intensive scenarios that require discovering and leveraging relevant information from large-scale and heterogeneous data repositories. Urban tasks are representative examples of such scenarios, as urban data are not only large-scale and multi-sourced, but also exhibit complex spatial, temporal, and semantic relationships. To address these challenges, we propose UrbanDS, a graph-guided LLM mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26724","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/2607.26724/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":"2026-07-30T01:22:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HV8velrr5V3JyjdbmWnvXi8/bVwfx71VDwH9vapimg32wmvm8E7iLxOWMkYcw8lBsONWCBAt/d9FDRuAZGVNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:52:10.335897Z"},"content_sha256":"81e85779ed1139a6a9d071141654d2a71b46e6d66a67ffa5f3f8a91fc745c7e9","schema_version":"1.0","event_id":"sha256:81e85779ed1139a6a9d071141654d2a71b46e6d66a67ffa5f3f8a91fc745c7e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YR7FQCTDUUCYBNHW7LVFZYOFXC/bundle.json","state_url":"https://pith.science/pith/YR7FQCTDUUCYBNHW7LVFZYOFXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YR7FQCTDUUCYBNHW7LVFZYOFXC/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":"2026-08-06T17:52:10Z","links":{"resolver":"https://pith.science/pith/YR7FQCTDUUCYBNHW7LVFZYOFXC","bundle":"https://pith.science/pith/YR7FQCTDUUCYBNHW7LVFZYOFXC/bundle.json","state":"https://pith.science/pith/YR7FQCTDUUCYBNHW7LVFZYOFXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YR7FQCTDUUCYBNHW7LVFZYOFXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YR7FQCTDUUCYBNHW7LVFZYOFXC","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":"155c5f83d7adf4301ac0c3bd57611adccab867061b9f1b1f0be05f00d9ad8dff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T10:14:02Z","title_canon_sha256":"4ab03468343944fc88a39be133850b75ac21b62fb75cf7eb7917cd2a53a32227"},"schema_version":"1.0","source":{"id":"2607.26724","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26724","created_at":"2026-07-30T01:22:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26724v1","created_at":"2026-07-30T01:22:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26724","created_at":"2026-07-30T01:22:05Z"},{"alias_kind":"pith_short_12","alias_value":"YR7FQCTDUUCY","created_at":"2026-07-30T01:22:05Z"},{"alias_kind":"pith_short_16","alias_value":"YR7FQCTDUUCYBNHW","created_at":"2026-07-30T01:22:05Z"},{"alias_kind":"pith_short_8","alias_value":"YR7FQCTD","created_at":"2026-07-30T01:22:05Z"}],"graph_snapshots":[{"event_id":"sha256:81e85779ed1139a6a9d071141654d2a71b46e6d66a67ffa5f3f8a91fc745c7e9","target":"graph","created_at":"2026-07-30T01:22:05Z","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/2607.26724/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) agents have been widely applied in automating data science tasks. However, existing methods typically rely on a limited set of provided datasets, and they face challenges in data-intensive scenarios that require discovering and leveraging relevant information from large-scale and heterogeneous data repositories. Urban tasks are representative examples of such scenarios, as urban data are not only large-scale and multi-sourced, but also exhibit complex spatial, temporal, and semantic relationships. To address these challenges, we propose UrbanDS, a graph-guided LLM mu","authors_text":"Depeng Jin, Jianghao Yu, Sun Yongquan, Yongjun Yang, Yong Li, Yuming Lin, Zhilun Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T10:14:02Z","title":"UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26724","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":"sha256:20553752cae9895930889bf04cc7f32f7bff9b017b6e8e2254f7013c0cd2d73b","target":"record","created_at":"2026-07-30T01:22:05Z","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":"155c5f83d7adf4301ac0c3bd57611adccab867061b9f1b1f0be05f00d9ad8dff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T10:14:02Z","title_canon_sha256":"4ab03468343944fc88a39be133850b75ac21b62fb75cf7eb7917cd2a53a32227"},"schema_version":"1.0","source":{"id":"2607.26724","kind":"arxiv","version":1}},"canonical_sha256":"c47e580a63a50580b4f6faea5ce1c5b88bad1e007e775fb979bc4d7bea714c97","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c47e580a63a50580b4f6faea5ce1c5b88bad1e007e775fb979bc4d7bea714c97","first_computed_at":"2026-07-30T01:22:05.277265Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:22:05.277265Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26724","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20553752cae9895930889bf04cc7f32f7bff9b017b6e8e2254f7013c0cd2d73b","sha256:81e85779ed1139a6a9d071141654d2a71b46e6d66a67ffa5f3f8a91fc745c7e9"],"state_sha256":"3be5b0eacff4741334e9ba83ee2e8a8a0d3b1860068bc637104561712568856e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AwDOZg0NGwYPkVsEPByDxifyYoFr1lK6iglu18us/Loueg6oGDlnFcFxW2eZIjv09k0SwWH8ss9PlvRzRBJoAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:52:10.343985Z","bundle_sha256":"7cc006ee049824b2e7bd9314a96dbe6fe38911b07f902694173f2babde409071"}}