{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Z4TQB6YC3TXLLAHA7QBZ3ZNN3X","short_pith_number":"pith:Z4TQB6YC","canonical_record":{"source":{"id":"2508.12108","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-16T17:08:43Z","cross_cats_sorted":[],"title_canon_sha256":"540a196dd306beb64f19dad3518175a591f1b0992155fd108ebabb92b5da0ec2","abstract_canon_sha256":"8a7fbe3b7bc7ebc1fbef3d032ce2eeaf75132e2b3542cb4204b765d2e8f6f0c9"},"schema_version":"1.0"},"canonical_sha256":"cf2700fb02dceeb580e0fc039de5addde7f2b8700fe6f47664292a0710b86e19","source":{"kind":"arxiv","id":"2508.12108","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12108","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12108v1","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12108","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_12","alias_value":"Z4TQB6YC3TXL","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_16","alias_value":"Z4TQB6YC3TXLLAHA","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_8","alias_value":"Z4TQB6YC","created_at":"2026-07-05T11:55:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Z4TQB6YC3TXLLAHA7QBZ3ZNN3X","target":"record","payload":{"canonical_record":{"source":{"id":"2508.12108","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-16T17:08:43Z","cross_cats_sorted":[],"title_canon_sha256":"540a196dd306beb64f19dad3518175a591f1b0992155fd108ebabb92b5da0ec2","abstract_canon_sha256":"8a7fbe3b7bc7ebc1fbef3d032ce2eeaf75132e2b3542cb4204b765d2e8f6f0c9"},"schema_version":"1.0"},"canonical_sha256":"cf2700fb02dceeb580e0fc039de5addde7f2b8700fe6f47664292a0710b86e19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:00.202220Z","signature_b64":"Fk6I+Mc5UNQnLJT7dE4d9RdnIGLjkVn7yhxbP/jVhSmOAOkcyVzHOk3eseE0vWe7RovpBZ8WXG2YAyehqRPRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf2700fb02dceeb580e0fc039de5addde7f2b8700fe6f47664292a0710b86e19","last_reissued_at":"2026-07-05T11:55:00.201712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:00.201712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.12108","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":"2026-07-05T11:55:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"liq2R+8NICrTiMlk7F/lOVWTruHLEaHO9pedFmbu4v/Ec22IdQAr7UCmHxP4upK7Ff0RR7ixCpSgW9G01I4dAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T08:43:03.078499Z"},"content_sha256":"96c2c2a08a9feb7bb85915095af1093c8d9b1571a005ca60d3046fc202af94be","schema_version":"1.0","event_id":"sha256:96c2c2a08a9feb7bb85915095af1093c8d9b1571a005ca60d3046fc202af94be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Z4TQB6YC3TXLLAHA7QBZ3ZNN3X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VELVET-Med: Vision and Efficient Language Pre-training for Volumetric Imaging Tasks in Medicine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Si Yong Yeo, Xulei Yang, Yang Yu, Ziyang Zhang","submitted_at":"2025-08-16T17:08:43Z","abstract_excerpt":"Vision-and-language models (VLMs) have been increasingly explored in the medical domain, particularly following the success of CLIP in general domain. However, unlike the relatively straightforward pairing of 2D images and text, curating large-scale paired data in the medical field for volumetric modalities such as CT scans remains a challenging and time-intensive process. This difficulty often limits the performance on downstream tasks. To address these challenges, we propose a novel vision-language pre-training (VLP) framework, termed as \\textbf{VELVET-Med}, specifically designed for limited"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12108","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/2508.12108/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":"2026-07-05T11:55:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i7QsQAcuh/sAx6ORzA1w7t6nXVQJ7YP7rRY/DDNMoteuqw5GEtyqjUDVRaRzlL/e2361KOAXnsjAWWKMY1peCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T08:43:03.078991Z"},"content_sha256":"db57ea81a96b835d10726f8b975cf3ad430390acfdf392daf24bf694c01a98b5","schema_version":"1.0","event_id":"sha256:db57ea81a96b835d10726f8b975cf3ad430390acfdf392daf24bf694c01a98b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z4TQB6YC3TXLLAHA7QBZ3ZNN3X/bundle.json","state_url":"https://pith.science/pith/Z4TQB6YC3TXLLAHA7QBZ3ZNN3X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z4TQB6YC3TXLLAHA7QBZ3ZNN3X/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":"2026-08-16T08:43:03Z","links":{"resolver":"https://pith.science/pith/Z4TQB6YC3TXLLAHA7QBZ3ZNN3X","bundle":"https://pith.science/pith/Z4TQB6YC3TXLLAHA7QBZ3ZNN3X/bundle.json","state":"https://pith.science/pith/Z4TQB6YC3TXLLAHA7QBZ3ZNN3X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z4TQB6YC3TXLLAHA7QBZ3ZNN3X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z4TQB6YC3TXLLAHA7QBZ3ZNN3X","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":"8a7fbe3b7bc7ebc1fbef3d032ce2eeaf75132e2b3542cb4204b765d2e8f6f0c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-16T17:08:43Z","title_canon_sha256":"540a196dd306beb64f19dad3518175a591f1b0992155fd108ebabb92b5da0ec2"},"schema_version":"1.0","source":{"id":"2508.12108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12108","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12108v1","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12108","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_12","alias_value":"Z4TQB6YC3TXL","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_16","alias_value":"Z4TQB6YC3TXLLAHA","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_8","alias_value":"Z4TQB6YC","created_at":"2026-07-05T11:55:00Z"}],"graph_snapshots":[{"event_id":"sha256:db57ea81a96b835d10726f8b975cf3ad430390acfdf392daf24bf694c01a98b5","target":"graph","created_at":"2026-07-05T11:55:00Z","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/2508.12108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-language models (VLMs) have been increasingly explored in the medical domain, particularly following the success of CLIP in general domain. However, unlike the relatively straightforward pairing of 2D images and text, curating large-scale paired data in the medical field for volumetric modalities such as CT scans remains a challenging and time-intensive process. This difficulty often limits the performance on downstream tasks. To address these challenges, we propose a novel vision-language pre-training (VLP) framework, termed as \\textbf{VELVET-Med}, specifically designed for limited","authors_text":"Si Yong Yeo, Xulei Yang, Yang Yu, Ziyang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-16T17:08:43Z","title":"VELVET-Med: Vision and Efficient Language Pre-training for Volumetric Imaging Tasks in Medicine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12108","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":"sha256:96c2c2a08a9feb7bb85915095af1093c8d9b1571a005ca60d3046fc202af94be","target":"record","created_at":"2026-07-05T11:55:00Z","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":"8a7fbe3b7bc7ebc1fbef3d032ce2eeaf75132e2b3542cb4204b765d2e8f6f0c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-16T17:08:43Z","title_canon_sha256":"540a196dd306beb64f19dad3518175a591f1b0992155fd108ebabb92b5da0ec2"},"schema_version":"1.0","source":{"id":"2508.12108","kind":"arxiv","version":1}},"canonical_sha256":"cf2700fb02dceeb580e0fc039de5addde7f2b8700fe6f47664292a0710b86e19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf2700fb02dceeb580e0fc039de5addde7f2b8700fe6f47664292a0710b86e19","first_computed_at":"2026-07-05T11:55:00.201712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:00.201712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fk6I+Mc5UNQnLJT7dE4d9RdnIGLjkVn7yhxbP/jVhSmOAOkcyVzHOk3eseE0vWe7RovpBZ8WXG2YAyehqRPRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:00.202220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96c2c2a08a9feb7bb85915095af1093c8d9b1571a005ca60d3046fc202af94be","sha256:db57ea81a96b835d10726f8b975cf3ad430390acfdf392daf24bf694c01a98b5"],"state_sha256":"176a9a1401be96250888b57696b1875d7f3986290ba4a0e6bee8d5fb7e5c8db6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hBM/0M60hod7wXRtUfvoRBz4j8L+GOgMIFeobV5RDGTTzYJFDIyTq+hu3G5wr0uMyqNCSZ4jPRLqNRagewJvDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T08:43:03.083330Z","bundle_sha256":"a18f656fa9239493dacae6c6ec0b243ffbfe7a5771338214b3fb8f8cdef18197"}}