{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KWSUHZ36RCOZNYXHOWIIXGQUXW","short_pith_number":"pith:KWSUHZ36","canonical_record":{"source":{"id":"2506.08844","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T14:30:44Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"0615abc0db27e60094eb25af101be1c7092c4a7b3b792c516ae8e2141fec005f","abstract_canon_sha256":"35e89f0363daf35927b9d34534f0ef57b659ab341dbf9f52562d74db88c25b3a"},"schema_version":"1.0"},"canonical_sha256":"55a543e77e889d96e2e775908b9a14bd859f5e5bb6ecf4a355e4e8c47fd7f651","source":{"kind":"arxiv","id":"2506.08844","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08844","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08844v1","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08844","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"pith_short_12","alias_value":"KWSUHZ36RCOZ","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"pith_short_16","alias_value":"KWSUHZ36RCOZNYXH","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"pith_short_8","alias_value":"KWSUHZ36","created_at":"2026-07-05T11:19:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KWSUHZ36RCOZNYXHOWIIXGQUXW","target":"record","payload":{"canonical_record":{"source":{"id":"2506.08844","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T14:30:44Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"0615abc0db27e60094eb25af101be1c7092c4a7b3b792c516ae8e2141fec005f","abstract_canon_sha256":"35e89f0363daf35927b9d34534f0ef57b659ab341dbf9f52562d74db88c25b3a"},"schema_version":"1.0"},"canonical_sha256":"55a543e77e889d96e2e775908b9a14bd859f5e5bb6ecf4a355e4e8c47fd7f651","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:14.089823Z","signature_b64":"ZJtoiMhPTCdOiBAcwwwkp1p45GhdzqWFXKkd0n6NcKBntIMuwXGo1XghaJo8SRVM2SbVuEFGvLydYxBzksYgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55a543e77e889d96e2e775908b9a14bd859f5e5bb6ecf4a355e4e8c47fd7f651","last_reissued_at":"2026-07-05T11:19:14.089423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:14.089423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.08844","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":"2026-07-05T11:19:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VRTD3R0uoffrUfQWOL4e8D2K29isETjyzRUT3KQenW1VXxes/+lpJxK6X7SchoB+KGKVUF9pEJNNX6Xussf6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:29:42.287551Z"},"content_sha256":"f5ab593a007ef794ba71093965e555e8fed2379be546e8ccdf845331f2919eb2","schema_version":"1.0","event_id":"sha256:f5ab593a007ef794ba71093965e555e8fed2379be546e8ccdf845331f2919eb2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KWSUHZ36RCOZNYXHOWIIXGQUXW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IMAGIC-500: IMputation benchmark on A Generative Imaginary Country (500k samples)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE"],"primary_cat":"cs.LG","authors_text":"Anisoara Calinescu, David Antony Selby, Sebastian Vollmer, Seth Flaxman, Siyi Sun, Yunchuan Huang","submitted_at":"2025-06-10T14:30:44Z","abstract_excerpt":"Missing data imputation in tabular datasets remains a pivotal challenge in data science and machine learning, particularly within socioeconomic research. However, real-world socioeconomic datasets are typically subject to strict data protection protocols, which often prohibit public sharing, even for synthetic derivatives. This severely limits the reproducibility and accessibility of benchmark studies in such settings. Further, there are very few publicly available synthetic datasets. Thus, there is limited availability of benchmarks for systematic evaluation of imputation methods on socioecon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08844","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/2506.08844/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":"2026-07-05T11:19:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9e/6uQ6VoYOTc9lq1aMnpkOAyz8Y8b8Bsy1qsGSSwoB6Nh6/aKR8P9O2z4XplJvteUCqtHf9wC1tYmafuYKCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:29:42.288080Z"},"content_sha256":"cf915cd36e00be4e772708877d1dc21e9d7ff9010d24fef98acf2cfbc698a964","schema_version":"1.0","event_id":"sha256:cf915cd36e00be4e772708877d1dc21e9d7ff9010d24fef98acf2cfbc698a964"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KWSUHZ36RCOZNYXHOWIIXGQUXW/bundle.json","state_url":"https://pith.science/pith/KWSUHZ36RCOZNYXHOWIIXGQUXW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KWSUHZ36RCOZNYXHOWIIXGQUXW/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":"2026-08-04T19:29:42Z","links":{"resolver":"https://pith.science/pith/KWSUHZ36RCOZNYXHOWIIXGQUXW","bundle":"https://pith.science/pith/KWSUHZ36RCOZNYXHOWIIXGQUXW/bundle.json","state":"https://pith.science/pith/KWSUHZ36RCOZNYXHOWIIXGQUXW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KWSUHZ36RCOZNYXHOWIIXGQUXW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KWSUHZ36RCOZNYXHOWIIXGQUXW","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":"35e89f0363daf35927b9d34534f0ef57b659ab341dbf9f52562d74db88c25b3a","cross_cats_sorted":["cs.CE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T14:30:44Z","title_canon_sha256":"0615abc0db27e60094eb25af101be1c7092c4a7b3b792c516ae8e2141fec005f"},"schema_version":"1.0","source":{"id":"2506.08844","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08844","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08844v1","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08844","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"pith_short_12","alias_value":"KWSUHZ36RCOZ","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"pith_short_16","alias_value":"KWSUHZ36RCOZNYXH","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"pith_short_8","alias_value":"KWSUHZ36","created_at":"2026-07-05T11:19:14Z"}],"graph_snapshots":[{"event_id":"sha256:cf915cd36e00be4e772708877d1dc21e9d7ff9010d24fef98acf2cfbc698a964","target":"graph","created_at":"2026-07-05T11:19:14Z","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/2506.08844/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Missing data imputation in tabular datasets remains a pivotal challenge in data science and machine learning, particularly within socioeconomic research. However, real-world socioeconomic datasets are typically subject to strict data protection protocols, which often prohibit public sharing, even for synthetic derivatives. This severely limits the reproducibility and accessibility of benchmark studies in such settings. Further, there are very few publicly available synthetic datasets. Thus, there is limited availability of benchmarks for systematic evaluation of imputation methods on socioecon","authors_text":"Anisoara Calinescu, David Antony Selby, Sebastian Vollmer, Seth Flaxman, Siyi Sun, Yunchuan Huang","cross_cats":["cs.CE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T14:30:44Z","title":"IMAGIC-500: IMputation benchmark on A Generative Imaginary Country (500k samples)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08844","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:f5ab593a007ef794ba71093965e555e8fed2379be546e8ccdf845331f2919eb2","target":"record","created_at":"2026-07-05T11:19:14Z","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":"35e89f0363daf35927b9d34534f0ef57b659ab341dbf9f52562d74db88c25b3a","cross_cats_sorted":["cs.CE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T14:30:44Z","title_canon_sha256":"0615abc0db27e60094eb25af101be1c7092c4a7b3b792c516ae8e2141fec005f"},"schema_version":"1.0","source":{"id":"2506.08844","kind":"arxiv","version":1}},"canonical_sha256":"55a543e77e889d96e2e775908b9a14bd859f5e5bb6ecf4a355e4e8c47fd7f651","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55a543e77e889d96e2e775908b9a14bd859f5e5bb6ecf4a355e4e8c47fd7f651","first_computed_at":"2026-07-05T11:19:14.089423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:14.089423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZJtoiMhPTCdOiBAcwwwkp1p45GhdzqWFXKkd0n6NcKBntIMuwXGo1XghaJo8SRVM2SbVuEFGvLydYxBzksYgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:14.089823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08844","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5ab593a007ef794ba71093965e555e8fed2379be546e8ccdf845331f2919eb2","sha256:cf915cd36e00be4e772708877d1dc21e9d7ff9010d24fef98acf2cfbc698a964"],"state_sha256":"0d4e272f5412d5d0c67342fd57cec72e477176fcaf9b1a7e02604a1b000b7b27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iWHMaT3UIZQslShk5XMY2zFc7JkXjK8Gu4ibdmqN4rV06s+c0PvlDdC/tnUk55JYeRRg8THPjtlqZcg07tPICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:29:42.292824Z","bundle_sha256":"3ff3c7dcdfd482c4b4d247826aa2438cfa1a2edbf8b70f67e08f79deffb96560"}}