{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D5G66QTFD3D6HFVKFFJ5AE4CKV","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":"3b3fc9b7193f0ca4a82ae2d85c08abbd72db5375babc2524d81be5e7b9e3b4b3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-09T12:15:08Z","title_canon_sha256":"d18848547bce77a3fc73493bce7c2af36019c41782b861e3de6ca1aa3abcf008"},"schema_version":"1.0","source":{"id":"2508.06960","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06960","created_at":"2026-07-05T11:51:38Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06960v1","created_at":"2026-07-05T11:51:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06960","created_at":"2026-07-05T11:51:38Z"},{"alias_kind":"pith_short_12","alias_value":"D5G66QTFD3D6","created_at":"2026-07-05T11:51:38Z"},{"alias_kind":"pith_short_16","alias_value":"D5G66QTFD3D6HFVK","created_at":"2026-07-05T11:51:38Z"},{"alias_kind":"pith_short_8","alias_value":"D5G66QTF","created_at":"2026-07-05T11:51:38Z"}],"graph_snapshots":[{"event_id":"sha256:89d59ca63a00e132c0de09a9a975e64afe5da53abef7ab50a72a466106705883","target":"graph","created_at":"2026-07-05T11:51:38Z","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/2508.06960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancement of large language models has fundamentally shifted the bottleneck in AI development from computational power to data availability-with countless valuable datasets remaining hidden across specialized repositories, research appendices, and domain platforms. As reasoning capabilities and deep research methodologies continue to evolve, a critical question emerges: can AI agents transcend conventional search to systematically discover any dataset that meets specific user requirements, enabling truly autonomous demand-driven data curation? We introduce DatasetResearch, the firs","authors_text":"Dayuan Fu, Dequan Wang, Keyu Li, Mohan Jiang, Pengfei Liu, Xiangkun Hu, Yunze Wu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-09T12:15:08Z","title":"DatasetResearch: Benchmarking Agent Systems for Demand-Driven Dataset Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06960","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:be9df7918c4776ca04caae4ac44d6b13d2bf3386a8f960f86e1f10d0e180595c","target":"record","created_at":"2026-07-05T11:51:38Z","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":"3b3fc9b7193f0ca4a82ae2d85c08abbd72db5375babc2524d81be5e7b9e3b4b3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-09T12:15:08Z","title_canon_sha256":"d18848547bce77a3fc73493bce7c2af36019c41782b861e3de6ca1aa3abcf008"},"schema_version":"1.0","source":{"id":"2508.06960","kind":"arxiv","version":1}},"canonical_sha256":"1f4def42651ec7e396aa2953d01382555ca07152cb2bdd21200a178456625430","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f4def42651ec7e396aa2953d01382555ca07152cb2bdd21200a178456625430","first_computed_at":"2026-07-05T11:51:38.358983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:38.358983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dEODHfgrEYRwGvhdv+akZstiDUa4+PcY8pFNzusVdEVf8QPDshgMpjqcKd8Rk6vTjU+v5INJd7QhOnLfqFrtDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:38.359525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.06960","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be9df7918c4776ca04caae4ac44d6b13d2bf3386a8f960f86e1f10d0e180595c","sha256:89d59ca63a00e132c0de09a9a975e64afe5da53abef7ab50a72a466106705883"],"state_sha256":"0d6cfe5ff678495c96a54c8a25b27aa95618137b32140191f10a3b3b4993ad82"}