{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2QVL6DSNSCLKWUJ6AZUKNKPVFX","short_pith_number":"pith:2QVL6DSN","schema_version":"1.0","canonical_sha256":"d42abf0e4d9096ab513e0668a6a9f52de38bedabc66d1e61c2e12c409290791c","source":{"kind":"arxiv","id":"2606.01049","version":1},"attestation_state":"computed","paper":{"title":"PMC-InterCPT: Rethinking Biomedical Interleaved Data for Multimodal Continued Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","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","submitted_at":"2026-05-31T06:38:30Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.01049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T06:38:30Z","cross_cats_sorted":[],"title_canon_sha256":"e07bc74aa593208bd24af0ef68d152e39454252f209c94a13ff22ac8e72f3bea","abstract_canon_sha256":"26362eca6e827d08e8779fa84d816d142c73fee1de4de43703d3e7bfede9647d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:19.692202Z","signature_b64":"2emOBLBrlF+mggp6vOt7NySYOri3HtP60m+7SpSPTdnCj94JP33CHP4kGK9uLEOVgdRXgE7VFPSxw9zVT+J0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d42abf0e4d9096ab513e0668a6a9f52de38bedabc66d1e61c2e12c409290791c","last_reissued_at":"2026-06-02T01:04:19.691657Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:19.691657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PMC-InterCPT: Rethinking Biomedical Interleaved Data for Multimodal Continued Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","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","submitted_at":"2026-05-31T06:38:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01049","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/2606.01049/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.01049","created_at":"2026-06-02T01:04:19.691714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01049v1","created_at":"2026-06-02T01:04:19.691714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01049","created_at":"2026-06-02T01:04:19.691714+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QVL6DSNSCLK","created_at":"2026-06-02T01:04:19.691714+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QVL6DSNSCLKWUJ6","created_at":"2026-06-02T01:04:19.691714+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QVL6DSN","created_at":"2026-06-02T01:04:19.691714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2QVL6DSNSCLKWUJ6AZUKNKPVFX","json":"https://pith.science/pith/2QVL6DSNSCLKWUJ6AZUKNKPVFX.json","graph_json":"https://pith.science/api/pith-number/2QVL6DSNSCLKWUJ6AZUKNKPVFX/graph.json","events_json":"https://pith.science/api/pith-number/2QVL6DSNSCLKWUJ6AZUKNKPVFX/events.json","paper":"https://pith.science/paper/2QVL6DSN"},"agent_actions":{"view_html":"https://pith.science/pith/2QVL6DSNSCLKWUJ6AZUKNKPVFX","download_json":"https://pith.science/pith/2QVL6DSNSCLKWUJ6AZUKNKPVFX.json","view_paper":"https://pith.science/paper/2QVL6DSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01049&json=true","fetch_graph":"https://pith.science/api/pith-number/2QVL6DSNSCLKWUJ6AZUKNKPVFX/graph.json","fetch_events":"https://pith.science/api/pith-number/2QVL6DSNSCLKWUJ6AZUKNKPVFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QVL6DSNSCLKWUJ6AZUKNKPVFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QVL6DSNSCLKWUJ6AZUKNKPVFX/action/storage_attestation","attest_author":"https://pith.science/pith/2QVL6DSNSCLKWUJ6AZUKNKPVFX/action/author_attestation","sign_citation":"https://pith.science/pith/2QVL6DSNSCLKWUJ6AZUKNKPVFX/action/citation_signature","submit_replication":"https://pith.science/pith/2QVL6DSNSCLKWUJ6AZUKNKPVFX/action/replication_record"}},"created_at":"2026-06-02T01:04:19.691714+00:00","updated_at":"2026-06-02T01:04:19.691714+00:00"}