{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7KJ3PMQ6BNPQ7VLYGVM4VK5ME2","short_pith_number":"pith:7KJ3PMQ6","canonical_record":{"source":{"id":"2508.12048","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-16T13:49:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d9eeee10b271868839762fce6b99feaafde1b191871085b4a2c5fc79a91027ec","abstract_canon_sha256":"3263b521b7753746ea314f7fbf1d69a648c564e257bbd866b20f32992e41b8e5"},"schema_version":"1.0"},"canonical_sha256":"fa93b7b21e0b5f0fd5783559caabac26a94f31e311297d8dd98fb06c3dae3045","source":{"kind":"arxiv","id":"2508.12048","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12048","created_at":"2026-07-05T11:54:59Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12048v1","created_at":"2026-07-05T11:54:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12048","created_at":"2026-07-05T11:54:59Z"},{"alias_kind":"pith_short_12","alias_value":"7KJ3PMQ6BNPQ","created_at":"2026-07-05T11:54:59Z"},{"alias_kind":"pith_short_16","alias_value":"7KJ3PMQ6BNPQ7VLY","created_at":"2026-07-05T11:54:59Z"},{"alias_kind":"pith_short_8","alias_value":"7KJ3PMQ6","created_at":"2026-07-05T11:54:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7KJ3PMQ6BNPQ7VLYGVM4VK5ME2","target":"record","payload":{"canonical_record":{"source":{"id":"2508.12048","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-16T13:49:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d9eeee10b271868839762fce6b99feaafde1b191871085b4a2c5fc79a91027ec","abstract_canon_sha256":"3263b521b7753746ea314f7fbf1d69a648c564e257bbd866b20f32992e41b8e5"},"schema_version":"1.0"},"canonical_sha256":"fa93b7b21e0b5f0fd5783559caabac26a94f31e311297d8dd98fb06c3dae3045","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:59.329861Z","signature_b64":"QHF7RO+WSlNx/TMIk8MgmJvu2ds1hzGQzJYiPqFvJG0NdWU9623DTDd70Mts9U9PogrJ0lUxhDOBQfZYNMruBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa93b7b21e0b5f0fd5783559caabac26a94f31e311297d8dd98fb06c3dae3045","last_reissued_at":"2026-07-05T11:54:59.329395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:59.329395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.12048","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":"2026-07-05T11:54:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wG3eZkrKhQBGDli/gCYm5h93B9RQ3NikD5z1EnWTSVQJApLrH7rNsGDydqoBMuSCNq5B1PGHtdLVPNyLQ/5KCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:01:36.621366Z"},"content_sha256":"ec0205e23a8b51b698f42d10c10442f0dfe01d96ee9b2814b8b75d7de779aa13","schema_version":"1.0","event_id":"sha256:ec0205e23a8b51b698f42d10c10442f0dfe01d96ee9b2814b8b75d7de779aa13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7KJ3PMQ6BNPQ7VLYGVM4VK5ME2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Data Fusion via Subsampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Haiying Wang, Jing Wang, Kun Chen","submitted_at":"2025-08-16T13:49:26Z","abstract_excerpt":"Data fusion and transfer learning are rapidly growing fields that enhance model performance for a target population by leveraging other related data sources or tasks. The challenges lie in the various potential heterogeneities between the target and external data, as well as various practical concerns that prevent a na\\\"ive data integration. We consider a realistic scenario where the target data is limited in size while the external data is large but contaminated with outliers; such data contamination, along with other computational and operational constraints, necessitates proper selection or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12048","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/2508.12048/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":"2026-07-05T11:54:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2DUcPsmELREudwvj2oD/qdQPiRiizDpYYmaOETsNdW9J//OkJW+kdH0cENgSwuS0eRBrOEBm0nByKezLbm9oBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:01:36.621860Z"},"content_sha256":"d8801c72135f0f54635f63320b83b8125170401c7dccb815cef51b10a1ad7880","schema_version":"1.0","event_id":"sha256:d8801c72135f0f54635f63320b83b8125170401c7dccb815cef51b10a1ad7880"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/bundle.json","state_url":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/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":"2026-08-15T16:01:36Z","links":{"resolver":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2","bundle":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/bundle.json","state":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7KJ3PMQ6BNPQ7VLYGVM4VK5ME2","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":"3263b521b7753746ea314f7fbf1d69a648c564e257bbd866b20f32992e41b8e5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-16T13:49:26Z","title_canon_sha256":"d9eeee10b271868839762fce6b99feaafde1b191871085b4a2c5fc79a91027ec"},"schema_version":"1.0","source":{"id":"2508.12048","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12048","created_at":"2026-07-05T11:54:59Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12048v1","created_at":"2026-07-05T11:54:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12048","created_at":"2026-07-05T11:54:59Z"},{"alias_kind":"pith_short_12","alias_value":"7KJ3PMQ6BNPQ","created_at":"2026-07-05T11:54:59Z"},{"alias_kind":"pith_short_16","alias_value":"7KJ3PMQ6BNPQ7VLY","created_at":"2026-07-05T11:54:59Z"},{"alias_kind":"pith_short_8","alias_value":"7KJ3PMQ6","created_at":"2026-07-05T11:54:59Z"}],"graph_snapshots":[{"event_id":"sha256:d8801c72135f0f54635f63320b83b8125170401c7dccb815cef51b10a1ad7880","target":"graph","created_at":"2026-07-05T11:54:59Z","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/2508.12048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data fusion and transfer learning are rapidly growing fields that enhance model performance for a target population by leveraging other related data sources or tasks. The challenges lie in the various potential heterogeneities between the target and external data, as well as various practical concerns that prevent a na\\\"ive data integration. We consider a realistic scenario where the target data is limited in size while the external data is large but contaminated with outliers; such data contamination, along with other computational and operational constraints, necessitates proper selection or","authors_text":"Haiying Wang, Jing Wang, Kun Chen","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-16T13:49:26Z","title":"Robust Data Fusion via Subsampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12048","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:ec0205e23a8b51b698f42d10c10442f0dfe01d96ee9b2814b8b75d7de779aa13","target":"record","created_at":"2026-07-05T11:54:59Z","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":"3263b521b7753746ea314f7fbf1d69a648c564e257bbd866b20f32992e41b8e5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-16T13:49:26Z","title_canon_sha256":"d9eeee10b271868839762fce6b99feaafde1b191871085b4a2c5fc79a91027ec"},"schema_version":"1.0","source":{"id":"2508.12048","kind":"arxiv","version":1}},"canonical_sha256":"fa93b7b21e0b5f0fd5783559caabac26a94f31e311297d8dd98fb06c3dae3045","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa93b7b21e0b5f0fd5783559caabac26a94f31e311297d8dd98fb06c3dae3045","first_computed_at":"2026-07-05T11:54:59.329395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:59.329395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QHF7RO+WSlNx/TMIk8MgmJvu2ds1hzGQzJYiPqFvJG0NdWU9623DTDd70Mts9U9PogrJ0lUxhDOBQfZYNMruBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:59.329861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12048","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec0205e23a8b51b698f42d10c10442f0dfe01d96ee9b2814b8b75d7de779aa13","sha256:d8801c72135f0f54635f63320b83b8125170401c7dccb815cef51b10a1ad7880"],"state_sha256":"d95e8e8473a85a94f0891bd38fff1cfb3056cbf9f877be9a74b62ba3a54c36f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8sJ9kTiSsD7KJeZp53vFMcz5DHm3HYH4QXWMC31EQ4Hlq7fvVO95n4gG0h392f8qj6WNjne2JJZtDfSRZUC7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T16:01:36.626268Z","bundle_sha256":"02f0f55c11ce72c560dbccfbe2bc9e5417ed327319f79962ae72495d5d4c14de"}}