{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VAI3IYGFZHLZUZGVMJNVV7YRLE","short_pith_number":"pith:VAI3IYGF","canonical_record":{"source":{"id":"2505.20731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-05-27T05:20:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cc0f53ddb18d7fe6df4e56ebee0cbf59858178013e2ef43fd03c64adadefabb5","abstract_canon_sha256":"fc8923651d2fe553fac1b385c53deb4412a35c699abba958dd483e6919e04775"},"schema_version":"1.0"},"canonical_sha256":"a811b460c5c9d79a64d5625b5aff11593eecfafd1895475f2dd0918596e66be4","source":{"kind":"arxiv","id":"2505.20731","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20731","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20731v1","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20731","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_12","alias_value":"VAI3IYGFZHLZ","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_16","alias_value":"VAI3IYGFZHLZUZGV","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_8","alias_value":"VAI3IYGF","created_at":"2026-07-05T11:10:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VAI3IYGFZHLZUZGVMJNVV7YRLE","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-05-27T05:20:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cc0f53ddb18d7fe6df4e56ebee0cbf59858178013e2ef43fd03c64adadefabb5","abstract_canon_sha256":"fc8923651d2fe553fac1b385c53deb4412a35c699abba958dd483e6919e04775"},"schema_version":"1.0"},"canonical_sha256":"a811b460c5c9d79a64d5625b5aff11593eecfafd1895475f2dd0918596e66be4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:17.623389Z","signature_b64":"f1ZXWlq1RLIdgo0kR8VFDcNkY+W9/yPvoslDN+5VWYPJkhwoU+rFpWftdpwg6DaHLkKJNqfj24lOoZ3P7o1QDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a811b460c5c9d79a64d5625b5aff11593eecfafd1895475f2dd0918596e66be4","last_reissued_at":"2026-07-05T11:10:17.622898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:17.622898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20731","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":"2026-07-05T11:10:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZiA1pI0KblSXmsCY/WggnwS+iPPhlY9zLS8wouXfRifCSzl1VMcVkdILL1Wnvy108edF4BGGTxHeAdaFePKCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:13:44.399391Z"},"content_sha256":"79ac20cd81312d4c212b5ccbe69e60e74e3028822354f0702ef2185d4c28dc7b","schema_version":"1.0","event_id":"sha256:79ac20cd81312d4c212b5ccbe69e60e74e3028822354f0702ef2185d4c28dc7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VAI3IYGFZHLZUZGVMJNVV7YRLE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised Clustering Through Representation Learning of Large-scale EHR Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Linshanshan Wang, Mengyan Li, Molei Liu, Tianxi Cai, Zongqi Xia","submitted_at":"2025-05-27T05:20:17Z","abstract_excerpt":"Electronic Health Records (EHR) offer rich real-world data for personalized medicine, providing insights into disease progression, treatment responses, and patient outcomes. However, their sparsity, heterogeneity, and high dimensionality make them difficult to model, while the lack of standardized ground truth further complicates predictive modeling. To address these challenges, we propose SCORE, a semi-supervised representation learning framework that captures multi-domain disease profiles through patient embeddings. SCORE employs a Poisson-Adapted Latent factor Mixture (PALM) Model with pre-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20731","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/2505.20731/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":"2026-07-05T11:10:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4rLlvawbct5QZbnTic1ZkJn3Mcq1PiTIE1ySCv1NXLRk/QP4FKWuDjbiDrW6xDE3dLMNho8Hguj8hNaLqbhzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:13:44.399903Z"},"content_sha256":"53e6255a29e71809f6f5e6e3bf1fe95a488a839f7ff42c2adc8eb4a78007de20","schema_version":"1.0","event_id":"sha256:53e6255a29e71809f6f5e6e3bf1fe95a488a839f7ff42c2adc8eb4a78007de20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VAI3IYGFZHLZUZGVMJNVV7YRLE/bundle.json","state_url":"https://pith.science/pith/VAI3IYGFZHLZUZGVMJNVV7YRLE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VAI3IYGFZHLZUZGVMJNVV7YRLE/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":"2026-08-18T05:13:44Z","links":{"resolver":"https://pith.science/pith/VAI3IYGFZHLZUZGVMJNVV7YRLE","bundle":"https://pith.science/pith/VAI3IYGFZHLZUZGVMJNVV7YRLE/bundle.json","state":"https://pith.science/pith/VAI3IYGFZHLZUZGVMJNVV7YRLE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VAI3IYGFZHLZUZGVMJNVV7YRLE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VAI3IYGFZHLZUZGVMJNVV7YRLE","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":"fc8923651d2fe553fac1b385c53deb4412a35c699abba958dd483e6919e04775","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-05-27T05:20:17Z","title_canon_sha256":"cc0f53ddb18d7fe6df4e56ebee0cbf59858178013e2ef43fd03c64adadefabb5"},"schema_version":"1.0","source":{"id":"2505.20731","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20731","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20731v1","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20731","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_12","alias_value":"VAI3IYGFZHLZ","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_16","alias_value":"VAI3IYGFZHLZUZGV","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_8","alias_value":"VAI3IYGF","created_at":"2026-07-05T11:10:17Z"}],"graph_snapshots":[{"event_id":"sha256:53e6255a29e71809f6f5e6e3bf1fe95a488a839f7ff42c2adc8eb4a78007de20","target":"graph","created_at":"2026-07-05T11:10:17Z","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/2505.20731/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Electronic Health Records (EHR) offer rich real-world data for personalized medicine, providing insights into disease progression, treatment responses, and patient outcomes. However, their sparsity, heterogeneity, and high dimensionality make them difficult to model, while the lack of standardized ground truth further complicates predictive modeling. To address these challenges, we propose SCORE, a semi-supervised representation learning framework that captures multi-domain disease profiles through patient embeddings. SCORE employs a Poisson-Adapted Latent factor Mixture (PALM) Model with pre-","authors_text":"Linshanshan Wang, Mengyan Li, Molei Liu, Tianxi Cai, Zongqi Xia","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-05-27T05:20:17Z","title":"Semi-supervised Clustering Through Representation Learning of Large-scale EHR Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20731","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":"sha256:79ac20cd81312d4c212b5ccbe69e60e74e3028822354f0702ef2185d4c28dc7b","target":"record","created_at":"2026-07-05T11:10:17Z","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":"fc8923651d2fe553fac1b385c53deb4412a35c699abba958dd483e6919e04775","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-05-27T05:20:17Z","title_canon_sha256":"cc0f53ddb18d7fe6df4e56ebee0cbf59858178013e2ef43fd03c64adadefabb5"},"schema_version":"1.0","source":{"id":"2505.20731","kind":"arxiv","version":1}},"canonical_sha256":"a811b460c5c9d79a64d5625b5aff11593eecfafd1895475f2dd0918596e66be4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a811b460c5c9d79a64d5625b5aff11593eecfafd1895475f2dd0918596e66be4","first_computed_at":"2026-07-05T11:10:17.622898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:17.622898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f1ZXWlq1RLIdgo0kR8VFDcNkY+W9/yPvoslDN+5VWYPJkhwoU+rFpWftdpwg6DaHLkKJNqfj24lOoZ3P7o1QDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:17.623389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20731","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79ac20cd81312d4c212b5ccbe69e60e74e3028822354f0702ef2185d4c28dc7b","sha256:53e6255a29e71809f6f5e6e3bf1fe95a488a839f7ff42c2adc8eb4a78007de20"],"state_sha256":"14130e3b1505098784f437bf985c4e7e5a3c50bfbe85551900261197bb7dd61a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"awwMimWM/yRzEGU86iU6ExYPD7D++OLDfpH27pPWUTDvtFdyKoebugWU9rdzWKzFurfLLwC06iLCCDxwrgtHCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T05:13:44.404162Z","bundle_sha256":"4396d39ef11702258346bc656e86cafdc65341b4e24645264ba23da26c6f088d"}}