{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R2B27J343ADNLOHRNKWMRJOZBH","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":"642040e0ba7c71ac967c1c4edeb27e9ed9431e20a0748746c6a94b5dd72b55b5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-25T05:45:05Z","title_canon_sha256":"9b3f8c4e2c701b34478638b0af4120b23315d749a246404972ccfb2a5c511526"},"schema_version":"1.0","source":{"id":"2507.18971","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18971","created_at":"2026-07-05T11:43:17Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18971v1","created_at":"2026-07-05T11:43:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18971","created_at":"2026-07-05T11:43:17Z"},{"alias_kind":"pith_short_12","alias_value":"R2B27J343ADN","created_at":"2026-07-05T11:43:17Z"},{"alias_kind":"pith_short_16","alias_value":"R2B27J343ADNLOHR","created_at":"2026-07-05T11:43:17Z"},{"alias_kind":"pith_short_8","alias_value":"R2B27J34","created_at":"2026-07-05T11:43:17Z"}],"graph_snapshots":[{"event_id":"sha256:836f5e17753930f5eb5a4aa6878b182201ff050bbf9162800bd17f9efc3701a2","target":"graph","created_at":"2026-07-05T11:43:17Z","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/2507.18971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dataset Search -- the process of finding appropriate datasets for a given task -- remains a critical yet under-explored challenge in data science workflows. Assessing dataset suitability for a task (e.g., training a classification model) is a multi-pronged affair that involves understanding: data characteristics (e.g. granularity, attributes, size), semantics (e.g., data semantics, creation goals), and relevance to the task at hand. Present-day dataset search interfaces are restrictive -- users struggle to convey implicit preferences and lack visibility into the search space and result inclusi","authors_text":"Aditya G. Parameswaran, Bhavya Chopra, Madelon Hulsebos, Rachel Lin, Shreya Shankar, Wenjing Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-25T05:45:05Z","title":"Rethinking Dataset Discovery with DataScout"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18971","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":"sha256:84ca5988bad153740b042343de2545568e0680bb5041813d3968bd8daf401e43","target":"record","created_at":"2026-07-05T11:43:17Z","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":"642040e0ba7c71ac967c1c4edeb27e9ed9431e20a0748746c6a94b5dd72b55b5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-25T05:45:05Z","title_canon_sha256":"9b3f8c4e2c701b34478638b0af4120b23315d749a246404972ccfb2a5c511526"},"schema_version":"1.0","source":{"id":"2507.18971","kind":"arxiv","version":1}},"canonical_sha256":"8e83afa77cd806d5b8f16aacc8a5d909efdd667187d1de3fc68e0110ff6d0b68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e83afa77cd806d5b8f16aacc8a5d909efdd667187d1de3fc68e0110ff6d0b68","first_computed_at":"2026-07-05T11:43:17.193977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:17.193977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AnK3qGKx/xZdoELAkzd2oR2c+HWkbwH88ghYCF3/VwMTRmohHtslnyzifw8YP6X+LqeWIH6zo7eidKEpkFxUBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:17.194458Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18971","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84ca5988bad153740b042343de2545568e0680bb5041813d3968bd8daf401e43","sha256:836f5e17753930f5eb5a4aa6878b182201ff050bbf9162800bd17f9efc3701a2"],"state_sha256":"3dd7fc433e5ddc10df8f9687444537d903c2ca2e07e2546058b4ee3236266bdc"}