{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2QVL6DSNSCLKWUJ6AZUKNKPVFX","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":"26362eca6e827d08e8779fa84d816d142c73fee1de4de43703d3e7bfede9647d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T06:38:30Z","title_canon_sha256":"e07bc74aa593208bd24af0ef68d152e39454252f209c94a13ff22ac8e72f3bea"},"schema_version":"1.0","source":{"id":"2606.01049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01049","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01049v1","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01049","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"2QVL6DSNSCLK","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"pith_short_16","alias_value":"2QVL6DSNSCLKWUJ6","created_at":"2026-06-02T01:04:19Z"},{"alias_kind":"pith_short_8","alias_value":"2QVL6DSN","created_at":"2026-06-02T01:04:19Z"}],"graph_snapshots":[{"event_id":"sha256:c9fa21da8b24deb47a555c15f2ae49de9fc62b4fda3272086d475de1e95f2a5e","target":"graph","created_at":"2026-06-02T01:04:19Z","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/2606.01049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale biomedical image-text datasets extracted from scientific literature provide valuable resources for medical multimodal model training. These datasets are commonly organized as image-caption pairs; however, figure captions are often short, context-dependent, and only partially informative without the surrounding article text. At the same time, large-scale automatic extraction introduces structural noise such as missing captions, residual markup, duplicated context, and incoherent multi-paragraph figure descriptions. We revisit data construction for medical multimodal continued pretra","authors_text":"Congkai Xie, Guanghao Zhu, Hongxia Yang, Jianmin Wu, Minheng Ni, Pengkai Wang, Shuo Cai, Wenjun Wang, Yanggan Gu, Zeyu Liu, Zhijie Sang, Zhitian Hou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T06:38:30Z","title":"PMC-InterCPT: Rethinking Biomedical Interleaved Data for Multimodal Continued Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01049","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:c6c625989bc4521245b17aca6f8dcbbecef0b32dd9967f88c31b03be3b17ac89","target":"record","created_at":"2026-06-02T01:04:19Z","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":"26362eca6e827d08e8779fa84d816d142c73fee1de4de43703d3e7bfede9647d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T06:38:30Z","title_canon_sha256":"e07bc74aa593208bd24af0ef68d152e39454252f209c94a13ff22ac8e72f3bea"},"schema_version":"1.0","source":{"id":"2606.01049","kind":"arxiv","version":1}},"canonical_sha256":"d42abf0e4d9096ab513e0668a6a9f52de38bedabc66d1e61c2e12c409290791c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d42abf0e4d9096ab513e0668a6a9f52de38bedabc66d1e61c2e12c409290791c","first_computed_at":"2026-06-02T01:04:19.691657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:19.691657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2emOBLBrlF+mggp6vOt7NySYOri3HtP60m+7SpSPTdnCj94JP33CHP4kGK9uLEOVgdRXgE7VFPSxw9zVT+J0Aw==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:19.692202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6c625989bc4521245b17aca6f8dcbbecef0b32dd9967f88c31b03be3b17ac89","sha256:c9fa21da8b24deb47a555c15f2ae49de9fc62b4fda3272086d475de1e95f2a5e"],"state_sha256":"596a9928050aa085dae74adf43c680f12fdb861901e395baeb04d99c525ad26e"}