{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R2B27J343ADNLOHRNKWMRJOZBH","short_pith_number":"pith:R2B27J34","schema_version":"1.0","canonical_sha256":"8e83afa77cd806d5b8f16aacc8a5d909efdd667187d1de3fc68e0110ff6d0b68","source":{"kind":"arxiv","id":"2507.18971","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Dataset Discovery with DataScout","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Aditya G. Parameswaran, Bhavya Chopra, Madelon Hulsebos, Rachel Lin, Shreya Shankar, Wenjing Lin","submitted_at":"2025-07-25T05:45:05Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.18971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-25T05:45:05Z","cross_cats_sorted":[],"title_canon_sha256":"9b3f8c4e2c701b34478638b0af4120b23315d749a246404972ccfb2a5c511526","abstract_canon_sha256":"642040e0ba7c71ac967c1c4edeb27e9ed9431e20a0748746c6a94b5dd72b55b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:17.194458Z","signature_b64":"AnK3qGKx/xZdoELAkzd2oR2c+HWkbwH88ghYCF3/VwMTRmohHtslnyzifw8YP6X+LqeWIH6zo7eidKEpkFxUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e83afa77cd806d5b8f16aacc8a5d909efdd667187d1de3fc68e0110ff6d0b68","last_reissued_at":"2026-07-05T11:43:17.193977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:17.193977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Dataset Discovery with DataScout","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Aditya G. Parameswaran, Bhavya Chopra, Madelon Hulsebos, Rachel Lin, Shreya Shankar, Wenjing Lin","submitted_at":"2025-07-25T05:45:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18971","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/2507.18971/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.18971","created_at":"2026-07-05T11:43:17.194033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18971v1","created_at":"2026-07-05T11:43:17.194033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18971","created_at":"2026-07-05T11:43:17.194033+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2B27J343ADN","created_at":"2026-07-05T11:43:17.194033+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2B27J343ADNLOHR","created_at":"2026-07-05T11:43:17.194033+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2B27J34","created_at":"2026-07-05T11:43:17.194033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2B27J343ADNLOHRNKWMRJOZBH","json":"https://pith.science/pith/R2B27J343ADNLOHRNKWMRJOZBH.json","graph_json":"https://pith.science/api/pith-number/R2B27J343ADNLOHRNKWMRJOZBH/graph.json","events_json":"https://pith.science/api/pith-number/R2B27J343ADNLOHRNKWMRJOZBH/events.json","paper":"https://pith.science/paper/R2B27J34"},"agent_actions":{"view_html":"https://pith.science/pith/R2B27J343ADNLOHRNKWMRJOZBH","download_json":"https://pith.science/pith/R2B27J343ADNLOHRNKWMRJOZBH.json","view_paper":"https://pith.science/paper/R2B27J34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18971&json=true","fetch_graph":"https://pith.science/api/pith-number/R2B27J343ADNLOHRNKWMRJOZBH/graph.json","fetch_events":"https://pith.science/api/pith-number/R2B27J343ADNLOHRNKWMRJOZBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2B27J343ADNLOHRNKWMRJOZBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2B27J343ADNLOHRNKWMRJOZBH/action/storage_attestation","attest_author":"https://pith.science/pith/R2B27J343ADNLOHRNKWMRJOZBH/action/author_attestation","sign_citation":"https://pith.science/pith/R2B27J343ADNLOHRNKWMRJOZBH/action/citation_signature","submit_replication":"https://pith.science/pith/R2B27J343ADNLOHRNKWMRJOZBH/action/replication_record"}},"created_at":"2026-07-05T11:43:17.194033+00:00","updated_at":"2026-07-05T11:43:17.194033+00:00"}