{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UQX73PF37SW24QO2A3VXLLN6YR","short_pith_number":"pith:UQX73PF3","schema_version":"1.0","canonical_sha256":"a42ffdbcbbfcadae41da06eb75adbec4574a1427eb5b2d8cad18c4f0ba3e6148","source":{"kind":"arxiv","id":"2409.07215","version":3},"attestation_state":"computed","paper":{"title":"Is merging worth it? Securely evaluating the information gain for causal dataset acquisition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Chris Holmes, Desi Ivanova, Jake Fawkes, Lucile Ter-Minassian, Uri Shalit","submitted_at":"2024-09-11T12:17:01Z","abstract_excerpt":"Merging datasets across institutions is a lengthy and costly procedure, especially when it involves private information. Data hosts may therefore want to prospectively gauge which datasets are most beneficial to merge with, without revealing sensitive information. For causal estimation this is particularly challenging as the value of a merge depends not only on reduction in epistemic uncertainty but also on improvement in overlap. To address this challenge, we introduce the first cryptographically secure information-theoretic approach for quantifying the value of a merge in the context of hete"},"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":"2409.07215","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2024-09-11T12:17:01Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"05c1aea61b8750ce63f5f874c46787d7d130679502fed48ba0ec66a6358e18c4","abstract_canon_sha256":"262817dd02a81910d8eeea373595f19bed317bde88637e33f3332f8bc5e064a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:37.712589Z","signature_b64":"EDPX3qf/NkAYRXGOfRbxScnwpRPsZFCs0ji0Xp7uUTByfFbMDvwqv+wawrKtHP/62kLkxObewKhF1EPgRWfiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a42ffdbcbbfcadae41da06eb75adbec4574a1427eb5b2d8cad18c4f0ba3e6148","last_reissued_at":"2026-07-05T11:30:37.712109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:37.712109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is merging worth it? Securely evaluating the information gain for causal dataset acquisition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Chris Holmes, Desi Ivanova, Jake Fawkes, Lucile Ter-Minassian, Uri Shalit","submitted_at":"2024-09-11T12:17:01Z","abstract_excerpt":"Merging datasets across institutions is a lengthy and costly procedure, especially when it involves private information. Data hosts may therefore want to prospectively gauge which datasets are most beneficial to merge with, without revealing sensitive information. For causal estimation this is particularly challenging as the value of a merge depends not only on reduction in epistemic uncertainty but also on improvement in overlap. To address this challenge, we introduce the first cryptographically secure information-theoretic approach for quantifying the value of a merge in the context of hete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07215","kind":"arxiv","version":3},"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/2409.07215/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":"2409.07215","created_at":"2026-07-05T11:30:37.712168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07215v3","created_at":"2026-07-05T11:30:37.712168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07215","created_at":"2026-07-05T11:30:37.712168+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQX73PF37SW2","created_at":"2026-07-05T11:30:37.712168+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQX73PF37SW24QO2","created_at":"2026-07-05T11:30:37.712168+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQX73PF3","created_at":"2026-07-05T11:30:37.712168+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/UQX73PF37SW24QO2A3VXLLN6YR","json":"https://pith.science/pith/UQX73PF37SW24QO2A3VXLLN6YR.json","graph_json":"https://pith.science/api/pith-number/UQX73PF37SW24QO2A3VXLLN6YR/graph.json","events_json":"https://pith.science/api/pith-number/UQX73PF37SW24QO2A3VXLLN6YR/events.json","paper":"https://pith.science/paper/UQX73PF3"},"agent_actions":{"view_html":"https://pith.science/pith/UQX73PF37SW24QO2A3VXLLN6YR","download_json":"https://pith.science/pith/UQX73PF37SW24QO2A3VXLLN6YR.json","view_paper":"https://pith.science/paper/UQX73PF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07215&json=true","fetch_graph":"https://pith.science/api/pith-number/UQX73PF37SW24QO2A3VXLLN6YR/graph.json","fetch_events":"https://pith.science/api/pith-number/UQX73PF37SW24QO2A3VXLLN6YR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQX73PF37SW24QO2A3VXLLN6YR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQX73PF37SW24QO2A3VXLLN6YR/action/storage_attestation","attest_author":"https://pith.science/pith/UQX73PF37SW24QO2A3VXLLN6YR/action/author_attestation","sign_citation":"https://pith.science/pith/UQX73PF37SW24QO2A3VXLLN6YR/action/citation_signature","submit_replication":"https://pith.science/pith/UQX73PF37SW24QO2A3VXLLN6YR/action/replication_record"}},"created_at":"2026-07-05T11:30:37.712168+00:00","updated_at":"2026-07-05T11:30:37.712168+00:00"}