{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6XQF2S3QRV33AM6R7TLSQFAKEZ","short_pith_number":"pith:6XQF2S3Q","canonical_record":{"source":{"id":"2501.04185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ME","submitted_at":"2025-01-07T23:34:20Z","cross_cats_sorted":[],"title_canon_sha256":"977eed44e272c075b3d436275b083fc71237d937a711fdac5fc481441a1ccaba","abstract_canon_sha256":"e0b6f669cc025792c7ef1bbeee2a00e115f9f816c3334172a0679ac7e79e7d48"},"schema_version":"1.0"},"canonical_sha256":"f5e05d4b708d77b033d1fcd728140a26659e82e2c202a7bb615a9f78dec98064","source":{"kind":"arxiv","id":"2501.04185","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04185","created_at":"2026-07-05T09:58:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04185v1","created_at":"2026-07-05T09:58:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04185","created_at":"2026-07-05T09:58:31Z"},{"alias_kind":"pith_short_12","alias_value":"6XQF2S3QRV33","created_at":"2026-07-05T09:58:31Z"},{"alias_kind":"pith_short_16","alias_value":"6XQF2S3QRV33AM6R","created_at":"2026-07-05T09:58:31Z"},{"alias_kind":"pith_short_8","alias_value":"6XQF2S3Q","created_at":"2026-07-05T09:58:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6XQF2S3QRV33AM6R7TLSQFAKEZ","target":"record","payload":{"canonical_record":{"source":{"id":"2501.04185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ME","submitted_at":"2025-01-07T23:34:20Z","cross_cats_sorted":[],"title_canon_sha256":"977eed44e272c075b3d436275b083fc71237d937a711fdac5fc481441a1ccaba","abstract_canon_sha256":"e0b6f669cc025792c7ef1bbeee2a00e115f9f816c3334172a0679ac7e79e7d48"},"schema_version":"1.0"},"canonical_sha256":"f5e05d4b708d77b033d1fcd728140a26659e82e2c202a7bb615a9f78dec98064","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:31.406036Z","signature_b64":"dNsjBKNP2M+LDhKbt2dMZeC/Q1shb7hyqu19OUm2f+YAevReEcrWjQof9PeRlRC3LUBsFAsGxtQ8Hvfl4MXaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5e05d4b708d77b033d1fcd728140a26659e82e2c202a7bb615a9f78dec98064","last_reissued_at":"2026-07-05T09:58:31.405550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:31.405550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.04185","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":"2026-07-05T09:58:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y9j4ZaXiBnsHkA9SiwieE/8QRTmJKRTbxqTPief5Ukk917xHp3tzlUmDQDqXfPpPntbD3JYUcUbACamawXEkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-29T07:03:36.453117Z"},"content_sha256":"4328df8c5de3989a41cbb1e4e460ddc837e2174b823bdc8885d7b033dfd1bd06","schema_version":"1.0","event_id":"sha256:4328df8c5de3989a41cbb1e4e460ddc837e2174b823bdc8885d7b033dfd1bd06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6XQF2S3QRV33AM6R7TLSQFAKEZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Estimating Propensities of Selection for Big Datasets via Data Integration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Anders Holmberg, Bronwyn Loong, Lyndon Ang, Robert Clark","submitted_at":"2025-01-07T23:34:20Z","abstract_excerpt":"Big data presents potential but unresolved value as a source for analysis and inference. However,selection bias, present in many of these datasets, needs to be accounted for so that appropriate inferences can be made on the target population. One way of approaching the selection bias issue is to first estimate the propensity of inclusion in the big dataset for each member of the big dataset, and then to apply these propensities in an inverse probability weighting approach to produce population estimates. In this paper, we provide details of a new variant of existing propensity score estimation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04185","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/2501.04185/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":"2026-07-05T09:58:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kAkyFL6SCEbW8NB3f5ZZdJoOxPypLy0ZFEup6zh6jsTieFdMUHbhkBlH4mN7jN2B5Tsvu1Jf8BfjteAm30xZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-29T07:03:36.453516Z"},"content_sha256":"e4b35d3fed75fe23f4eb8a9c9f5e7181281caa493950444d56d2bed9617fb939","schema_version":"1.0","event_id":"sha256:e4b35d3fed75fe23f4eb8a9c9f5e7181281caa493950444d56d2bed9617fb939"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XQF2S3QRV33AM6R7TLSQFAKEZ/bundle.json","state_url":"https://pith.science/pith/6XQF2S3QRV33AM6R7TLSQFAKEZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XQF2S3QRV33AM6R7TLSQFAKEZ/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":"2026-07-29T07:03:36Z","links":{"resolver":"https://pith.science/pith/6XQF2S3QRV33AM6R7TLSQFAKEZ","bundle":"https://pith.science/pith/6XQF2S3QRV33AM6R7TLSQFAKEZ/bundle.json","state":"https://pith.science/pith/6XQF2S3QRV33AM6R7TLSQFAKEZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XQF2S3QRV33AM6R7TLSQFAKEZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6XQF2S3QRV33AM6R7TLSQFAKEZ","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":"e0b6f669cc025792c7ef1bbeee2a00e115f9f816c3334172a0679ac7e79e7d48","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ME","submitted_at":"2025-01-07T23:34:20Z","title_canon_sha256":"977eed44e272c075b3d436275b083fc71237d937a711fdac5fc481441a1ccaba"},"schema_version":"1.0","source":{"id":"2501.04185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04185","created_at":"2026-07-05T09:58:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04185v1","created_at":"2026-07-05T09:58:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04185","created_at":"2026-07-05T09:58:31Z"},{"alias_kind":"pith_short_12","alias_value":"6XQF2S3QRV33","created_at":"2026-07-05T09:58:31Z"},{"alias_kind":"pith_short_16","alias_value":"6XQF2S3QRV33AM6R","created_at":"2026-07-05T09:58:31Z"},{"alias_kind":"pith_short_8","alias_value":"6XQF2S3Q","created_at":"2026-07-05T09:58:31Z"}],"graph_snapshots":[{"event_id":"sha256:e4b35d3fed75fe23f4eb8a9c9f5e7181281caa493950444d56d2bed9617fb939","target":"graph","created_at":"2026-07-05T09:58:31Z","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/2501.04185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Big data presents potential but unresolved value as a source for analysis and inference. However,selection bias, present in many of these datasets, needs to be accounted for so that appropriate inferences can be made on the target population. One way of approaching the selection bias issue is to first estimate the propensity of inclusion in the big dataset for each member of the big dataset, and then to apply these propensities in an inverse probability weighting approach to produce population estimates. In this paper, we provide details of a new variant of existing propensity score estimation","authors_text":"Anders Holmberg, Bronwyn Loong, Lyndon Ang, Robert Clark","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ME","submitted_at":"2025-01-07T23:34:20Z","title":"Estimating Propensities of Selection for Big Datasets via Data Integration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04185","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":"sha256:4328df8c5de3989a41cbb1e4e460ddc837e2174b823bdc8885d7b033dfd1bd06","target":"record","created_at":"2026-07-05T09:58:31Z","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":"e0b6f669cc025792c7ef1bbeee2a00e115f9f816c3334172a0679ac7e79e7d48","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ME","submitted_at":"2025-01-07T23:34:20Z","title_canon_sha256":"977eed44e272c075b3d436275b083fc71237d937a711fdac5fc481441a1ccaba"},"schema_version":"1.0","source":{"id":"2501.04185","kind":"arxiv","version":1}},"canonical_sha256":"f5e05d4b708d77b033d1fcd728140a26659e82e2c202a7bb615a9f78dec98064","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5e05d4b708d77b033d1fcd728140a26659e82e2c202a7bb615a9f78dec98064","first_computed_at":"2026-07-05T09:58:31.405550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:31.405550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dNsjBKNP2M+LDhKbt2dMZeC/Q1shb7hyqu19OUm2f+YAevReEcrWjQof9PeRlRC3LUBsFAsGxtQ8Hvfl4MXaBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:31.406036Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4328df8c5de3989a41cbb1e4e460ddc837e2174b823bdc8885d7b033dfd1bd06","sha256:e4b35d3fed75fe23f4eb8a9c9f5e7181281caa493950444d56d2bed9617fb939"],"state_sha256":"c28f7eed4fb9168dbced268bd5a5c9cb95ac0c59ec47b5faedf2557775f44b10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SbAc0/o50L553vLrFmWYJvvGKzvoVJBPAgxHoNqcVdd199f1PETErot4LgR5zfLuxr+wXNF5FHpmeg+vza4mBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-29T07:03:36.456416Z","bundle_sha256":"1625fcc073f7747151d87bf5fbca02161b7c28f9ee882c792fe8e7007ccef0ff"}}