{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LXS3VP5WGNEFKYHKBNXC2GX2IM","short_pith_number":"pith:LXS3VP5W","canonical_record":{"source":{"id":"2502.05091","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T17:10:22Z","cross_cats_sorted":[],"title_canon_sha256":"1ed073b957cce208765c99abaaaf128bbebb6e7700198f0fe6e5c1f6feed7c6a","abstract_canon_sha256":"9d0b11e5a2d417a5a872dd243a177e3fddaaa62b0ff1057ee61c67dcbceeb732"},"schema_version":"1.0"},"canonical_sha256":"5de5babfb633485560ea0b6e2d1afa433dff9639a0fb310832e3fbc07c4ceaca","source":{"kind":"arxiv","id":"2502.05091","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05091","created_at":"2026-07-05T10:53:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05091v2","created_at":"2026-07-05T10:53:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05091","created_at":"2026-07-05T10:53:52Z"},{"alias_kind":"pith_short_12","alias_value":"LXS3VP5WGNEF","created_at":"2026-07-05T10:53:52Z"},{"alias_kind":"pith_short_16","alias_value":"LXS3VP5WGNEFKYHK","created_at":"2026-07-05T10:53:52Z"},{"alias_kind":"pith_short_8","alias_value":"LXS3VP5W","created_at":"2026-07-05T10:53:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LXS3VP5WGNEFKYHKBNXC2GX2IM","target":"record","payload":{"canonical_record":{"source":{"id":"2502.05091","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T17:10:22Z","cross_cats_sorted":[],"title_canon_sha256":"1ed073b957cce208765c99abaaaf128bbebb6e7700198f0fe6e5c1f6feed7c6a","abstract_canon_sha256":"9d0b11e5a2d417a5a872dd243a177e3fddaaa62b0ff1057ee61c67dcbceeb732"},"schema_version":"1.0"},"canonical_sha256":"5de5babfb633485560ea0b6e2d1afa433dff9639a0fb310832e3fbc07c4ceaca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:52.242900Z","signature_b64":"0F2d1pD72YERkn22R7i35h75pgGq1rOu/PBbAOZwOCMnVBxepU0vp6xze8tTtLSyrjT26WXXe0oVLWULfReRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5de5babfb633485560ea0b6e2d1afa433dff9639a0fb310832e3fbc07c4ceaca","last_reissued_at":"2026-07-05T10:53:52.242307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:52.242307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.05091","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:53:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hRWxNN8YUtACUiX/zVGI1NUD/id792BdanUuTn2w49TUaZEo1u/kIbmro6xNR4vBJL8herKcznQKEw2khYHNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:36:39.098118Z"},"content_sha256":"46f05ec633a8406b1dccd4cda8404df281893975bda7943316d26fb2b401e3eb","schema_version":"1.0","event_id":"sha256:46f05ec633a8406b1dccd4cda8404df281893975bda7943316d26fb2b401e3eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LXS3VP5WGNEFKYHKBNXC2GX2IM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DCFormer: Efficient 3D Vision-Language Modeling with Decomposed Convolutions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gorkem Can Ates, Kuang Gong, Wei Shao, Yu Xin","submitted_at":"2025-02-07T17:10:22Z","abstract_excerpt":"Vision-language models (VLMs) have been widely applied to 2D medical image analysis due to their ability to align visual and textual representations. However, extending VLMs to 3D imaging remains computationally challenging. Existing 3D VLMs often rely on Vision Transformers (ViTs), which are computationally expensive due to the quadratic complexity of self-attention, or on 3D convolutions, which require large numbers of parameters and FLOPs as kernel size increases. We introduce DCFormer, an efficient 3D image encoder that factorizes 3D convolutions into three parallel 1D convolutions along t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05091","kind":"arxiv","version":2},"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/2502.05091/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":"2026-07-05T10:53:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"loqpO/Yr5/+Jop3AE+QjbKgUxD5NVfMH3BvNW1MEIjoD+jJwypBY33xnHVNVbUQz2gg2f6rCaRjOxDHGU0kECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:36:39.098702Z"},"content_sha256":"3b4050ba21049b313dd7bc6f114a7143640f6bcf10b0a4bd8183698ee7a66e37","schema_version":"1.0","event_id":"sha256:3b4050ba21049b313dd7bc6f114a7143640f6bcf10b0a4bd8183698ee7a66e37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LXS3VP5WGNEFKYHKBNXC2GX2IM/bundle.json","state_url":"https://pith.science/pith/LXS3VP5WGNEFKYHKBNXC2GX2IM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LXS3VP5WGNEFKYHKBNXC2GX2IM/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":"2026-08-04T03:36:39Z","links":{"resolver":"https://pith.science/pith/LXS3VP5WGNEFKYHKBNXC2GX2IM","bundle":"https://pith.science/pith/LXS3VP5WGNEFKYHKBNXC2GX2IM/bundle.json","state":"https://pith.science/pith/LXS3VP5WGNEFKYHKBNXC2GX2IM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LXS3VP5WGNEFKYHKBNXC2GX2IM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LXS3VP5WGNEFKYHKBNXC2GX2IM","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":"9d0b11e5a2d417a5a872dd243a177e3fddaaa62b0ff1057ee61c67dcbceeb732","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T17:10:22Z","title_canon_sha256":"1ed073b957cce208765c99abaaaf128bbebb6e7700198f0fe6e5c1f6feed7c6a"},"schema_version":"1.0","source":{"id":"2502.05091","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05091","created_at":"2026-07-05T10:53:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05091v2","created_at":"2026-07-05T10:53:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05091","created_at":"2026-07-05T10:53:52Z"},{"alias_kind":"pith_short_12","alias_value":"LXS3VP5WGNEF","created_at":"2026-07-05T10:53:52Z"},{"alias_kind":"pith_short_16","alias_value":"LXS3VP5WGNEFKYHK","created_at":"2026-07-05T10:53:52Z"},{"alias_kind":"pith_short_8","alias_value":"LXS3VP5W","created_at":"2026-07-05T10:53:52Z"}],"graph_snapshots":[{"event_id":"sha256:3b4050ba21049b313dd7bc6f114a7143640f6bcf10b0a4bd8183698ee7a66e37","target":"graph","created_at":"2026-07-05T10:53:52Z","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/2502.05091/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have been widely applied to 2D medical image analysis due to their ability to align visual and textual representations. However, extending VLMs to 3D imaging remains computationally challenging. Existing 3D VLMs often rely on Vision Transformers (ViTs), which are computationally expensive due to the quadratic complexity of self-attention, or on 3D convolutions, which require large numbers of parameters and FLOPs as kernel size increases. We introduce DCFormer, an efficient 3D image encoder that factorizes 3D convolutions into three parallel 1D convolutions along t","authors_text":"Gorkem Can Ates, Kuang Gong, Wei Shao, Yu Xin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T17:10:22Z","title":"DCFormer: Efficient 3D Vision-Language Modeling with Decomposed Convolutions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05091","kind":"arxiv","version":2},"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":"sha256:46f05ec633a8406b1dccd4cda8404df281893975bda7943316d26fb2b401e3eb","target":"record","created_at":"2026-07-05T10:53:52Z","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":"9d0b11e5a2d417a5a872dd243a177e3fddaaa62b0ff1057ee61c67dcbceeb732","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T17:10:22Z","title_canon_sha256":"1ed073b957cce208765c99abaaaf128bbebb6e7700198f0fe6e5c1f6feed7c6a"},"schema_version":"1.0","source":{"id":"2502.05091","kind":"arxiv","version":2}},"canonical_sha256":"5de5babfb633485560ea0b6e2d1afa433dff9639a0fb310832e3fbc07c4ceaca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5de5babfb633485560ea0b6e2d1afa433dff9639a0fb310832e3fbc07c4ceaca","first_computed_at":"2026-07-05T10:53:52.242307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:52.242307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0F2d1pD72YERkn22R7i35h75pgGq1rOu/PBbAOZwOCMnVBxepU0vp6xze8tTtLSyrjT26WXXe0oVLWULfReRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:52.242900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05091","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46f05ec633a8406b1dccd4cda8404df281893975bda7943316d26fb2b401e3eb","sha256:3b4050ba21049b313dd7bc6f114a7143640f6bcf10b0a4bd8183698ee7a66e37"],"state_sha256":"2a4edc4d395e80146ae6f105f85d05151a7f84c4ac573e09759b688646ab6054"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"721ac23lSlvEr1el7thIm6C4uaHWxaLqk0FbRJ1IN9kyHWxvXTP3aD+f0Bc5h81VljFGv55uv3R5JPS/aKsPAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:36:39.103892Z","bundle_sha256":"59c4fa33908d4b2a3d99907b9aeffc0a088123566dd46de3828d1bf1a94f6ff4"}}