{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:65SERJAJ6LAVVIJTP7GQVEOEDQ","short_pith_number":"pith:65SERJAJ","canonical_record":{"source":{"id":"2608.10522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T05:57:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3fd5dc7ecc7bac0edb0ba972c374fafb455caf3f01d782e682e01c43b12c9481","abstract_canon_sha256":"928546ef362f5ed37daf00d9b50c72b36b7897249bad1a5dc976562f2cbbcd94"},"schema_version":"1.0"},"canonical_sha256":"f76448a409f2c15aa1337fcd0a91c41c191e2fdd93662bcf47f7a33104701b00","source":{"kind":"arxiv","id":"2608.10522","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10522","created_at":"2026-08-12T01:22:40Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10522v1","created_at":"2026-08-12T01:22:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10522","created_at":"2026-08-12T01:22:40Z"},{"alias_kind":"pith_short_12","alias_value":"65SERJAJ6LAV","created_at":"2026-08-12T01:22:40Z"},{"alias_kind":"pith_short_16","alias_value":"65SERJAJ6LAVVIJT","created_at":"2026-08-12T01:22:40Z"},{"alias_kind":"pith_short_8","alias_value":"65SERJAJ","created_at":"2026-08-12T01:22:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:65SERJAJ6LAVVIJTP7GQVEOEDQ","target":"record","payload":{"canonical_record":{"source":{"id":"2608.10522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T05:57:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3fd5dc7ecc7bac0edb0ba972c374fafb455caf3f01d782e682e01c43b12c9481","abstract_canon_sha256":"928546ef362f5ed37daf00d9b50c72b36b7897249bad1a5dc976562f2cbbcd94"},"schema_version":"1.0"},"canonical_sha256":"f76448a409f2c15aa1337fcd0a91c41c191e2fdd93662bcf47f7a33104701b00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:22:40.208613Z","signature_b64":"5AXnt0jniNy/+FHJbD3TQgry2zBHbLt9GS+UxuOkLZApoDIjljbuT4HJh1tWuWPCi1wlRHaMRb/zX57f9MfBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f76448a409f2c15aa1337fcd0a91c41c191e2fdd93662bcf47f7a33104701b00","last_reissued_at":"2026-08-12T01:22:40.206897Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:22:40.206897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.10522","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":"2026-08-12T01:22:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yH+w95szGNdiAAlkpwqlytGLEerQzJmHn7cCcSSs0dtgaF03QmbAwPd900IoxSsURZWRkB+OBJ+RmByvzxkVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:54:10.018755Z"},"content_sha256":"7922e424523fb83384af8f4834cffb9d448b4684270cf425f2e76ae35658881c","schema_version":"1.0","event_id":"sha256:7922e424523fb83384af8f4834cffb9d448b4684270cf425f2e76ae35658881c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:65SERJAJ6LAVVIJTP7GQVEOEDQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unlocking the Power of Medical Tabular Data via Semantic-Aware Multimodal Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haiming Li, H. Peter Soyer, Jiajun Sun, Jingmin Zhu, Monika Janda, Victoria Mar, Yingsheng Liu, Zhen Yu, Zongyuan Ge","submitted_at":"2026-08-11T05:57:09Z","abstract_excerpt":"While vision-language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent in structured clinical tables. However, existing multimodal pre-training methods underutilize this potential due to semantic-agnostic designs that treat tabular inputs as flat vectors and employ unstable continuous regression objectives. To overcome this, we propose a novel semantic-aware framework explicitly modeling the intrinsic two-dimensional structure of tabular data. First, addressing the inter-feature hierarchy of varying diagnostic impor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10522","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/2608.10522/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":"2026-08-12T01:22:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0EcT9Qy8z7gSCvhpqguoBXBvdx9dX+CkutZf6hwS6eNOECRvje4DKcipzKVmRemMrlwgDNnfKpUDbnU9q7GeCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:54:10.019335Z"},"content_sha256":"e479ada42a876629777d95f9da84ed523966495dc371ec8b0b4b7d31dc82fc31","schema_version":"1.0","event_id":"sha256:e479ada42a876629777d95f9da84ed523966495dc371ec8b0b4b7d31dc82fc31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ/bundle.json","state_url":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ/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":"2026-08-19T08:54:10Z","links":{"resolver":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ","bundle":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ/bundle.json","state":"https://pith.science/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/65SERJAJ6LAVVIJTP7GQVEOEDQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:65SERJAJ6LAVVIJTP7GQVEOEDQ","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":"928546ef362f5ed37daf00d9b50c72b36b7897249bad1a5dc976562f2cbbcd94","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T05:57:09Z","title_canon_sha256":"3fd5dc7ecc7bac0edb0ba972c374fafb455caf3f01d782e682e01c43b12c9481"},"schema_version":"1.0","source":{"id":"2608.10522","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10522","created_at":"2026-08-12T01:22:40Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10522v1","created_at":"2026-08-12T01:22:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10522","created_at":"2026-08-12T01:22:40Z"},{"alias_kind":"pith_short_12","alias_value":"65SERJAJ6LAV","created_at":"2026-08-12T01:22:40Z"},{"alias_kind":"pith_short_16","alias_value":"65SERJAJ6LAVVIJT","created_at":"2026-08-12T01:22:40Z"},{"alias_kind":"pith_short_8","alias_value":"65SERJAJ","created_at":"2026-08-12T01:22:40Z"}],"graph_snapshots":[{"event_id":"sha256:e479ada42a876629777d95f9da84ed523966495dc371ec8b0b4b7d31dc82fc31","target":"graph","created_at":"2026-08-12T01:22:40Z","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/2608.10522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While vision-language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent in structured clinical tables. However, existing multimodal pre-training methods underutilize this potential due to semantic-agnostic designs that treat tabular inputs as flat vectors and employ unstable continuous regression objectives. To overcome this, we propose a novel semantic-aware framework explicitly modeling the intrinsic two-dimensional structure of tabular data. First, addressing the inter-feature hierarchy of varying diagnostic impor","authors_text":"Haiming Li, H. Peter Soyer, Jiajun Sun, Jingmin Zhu, Monika Janda, Victoria Mar, Yingsheng Liu, Zhen Yu, Zongyuan Ge","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T05:57:09Z","title":"Unlocking the Power of Medical Tabular Data via Semantic-Aware Multimodal Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10522","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":"sha256:7922e424523fb83384af8f4834cffb9d448b4684270cf425f2e76ae35658881c","target":"record","created_at":"2026-08-12T01:22:40Z","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":"928546ef362f5ed37daf00d9b50c72b36b7897249bad1a5dc976562f2cbbcd94","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T05:57:09Z","title_canon_sha256":"3fd5dc7ecc7bac0edb0ba972c374fafb455caf3f01d782e682e01c43b12c9481"},"schema_version":"1.0","source":{"id":"2608.10522","kind":"arxiv","version":1}},"canonical_sha256":"f76448a409f2c15aa1337fcd0a91c41c191e2fdd93662bcf47f7a33104701b00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f76448a409f2c15aa1337fcd0a91c41c191e2fdd93662bcf47f7a33104701b00","first_computed_at":"2026-08-12T01:22:40.206897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:22:40.206897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5AXnt0jniNy/+FHJbD3TQgry2zBHbLt9GS+UxuOkLZApoDIjljbuT4HJh1tWuWPCi1wlRHaMRb/zX57f9MfBDg==","signature_status":"signed_v1","signed_at":"2026-08-12T01:22:40.208613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10522","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7922e424523fb83384af8f4834cffb9d448b4684270cf425f2e76ae35658881c","sha256:e479ada42a876629777d95f9da84ed523966495dc371ec8b0b4b7d31dc82fc31"],"state_sha256":"90465f95eeecb0fdced97f556be6383f8584d848f621a01434546a127c3af071"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2BGHhX4VgYGBL+kzyeNIlJ2n71rPlsjukzbe4v/snB38SEoKLH59S1GuYxUd5hfimNSBel0kLHPQIvUrj0bwAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T08:54:10.025434Z","bundle_sha256":"da33379511d7bdc9f9f21fb2a4bda50865ef0c9b8c2de7932c938d496c4a0f99"}}