{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CSGYX3ODVMHI5JGLOTP4PVAOJG","short_pith_number":"pith:CSGYX3OD","schema_version":"1.0","canonical_sha256":"148d8bedc3ab0e8ea4cb74dfc7d40e49aadbcf407a70cc8ead8708e570d6b689","source":{"kind":"arxiv","id":"2608.04515","version":1},"attestation_state":"computed","paper":{"title":"CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiaxuan Zhao, Lichi Zhang, Qiang Hu, Yusong Sun, Zhenhao Li, Zhenyu Yi","submitted_at":"2026-08-05T06:49:49Z","abstract_excerpt":"Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices. However, this slice-wise formulation produces thousands of visual tokens that burden the LLM backbone, many of which capture overlapping visual evidence across adjacent slices. To understand how effectively a growing visual token budget improves performance, we perform scaling analyses on two 3D medical VQA benchmarks and find diminishing returns: cost keeps rising while accuracy saturates, and improving in-plane resolution is more effective than adding slices at comparable budgets. The budget s"},"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":"2608.04515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T06:49:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"706ac83675aa765793b5585f0b7b47d551f6cf8c7972b162b397bbb2a4e11de6","abstract_canon_sha256":"9e6bbf3685213c2a304c20eeceefa9b0dd52576a6fb418cffafbf86e564bce7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:35:45.925044Z","signature_b64":"ujljw0+CZaAV9UxKsgip8HUODuwGNZVRd+UFVGwhyKvAtgpNFSEZTiYg3oqaPj8x3f+ynrzEsuG/dE/pUBO+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"148d8bedc3ab0e8ea4cb74dfc7d40e49aadbcf407a70cc8ead8708e570d6b689","last_reissued_at":"2026-08-06T01:35:45.923580Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:35:45.923580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiaxuan Zhao, Lichi Zhang, Qiang Hu, Yusong Sun, Zhenhao Li, Zhenyu Yi","submitted_at":"2026-08-05T06:49:49Z","abstract_excerpt":"Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices. However, this slice-wise formulation produces thousands of visual tokens that burden the LLM backbone, many of which capture overlapping visual evidence across adjacent slices. To understand how effectively a growing visual token budget improves performance, we perform scaling analyses on two 3D medical VQA benchmarks and find diminishing returns: cost keeps rising while accuracy saturates, and improving in-plane resolution is more effective than adding slices at comparable budgets. The budget s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04515","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/2608.04515/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":"2608.04515","created_at":"2026-08-06T01:35:45.925432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04515v1","created_at":"2026-08-06T01:35:45.925432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04515","created_at":"2026-08-06T01:35:45.925432+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSGYX3ODVMHI","created_at":"2026-08-06T01:35:45.925432+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSGYX3ODVMHI5JGL","created_at":"2026-08-06T01:35:45.925432+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSGYX3OD","created_at":"2026-08-06T01:35:45.925432+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/CSGYX3ODVMHI5JGLOTP4PVAOJG","json":"https://pith.science/pith/CSGYX3ODVMHI5JGLOTP4PVAOJG.json","graph_json":"https://pith.science/api/pith-number/CSGYX3ODVMHI5JGLOTP4PVAOJG/graph.json","events_json":"https://pith.science/api/pith-number/CSGYX3ODVMHI5JGLOTP4PVAOJG/events.json","paper":"https://pith.science/paper/CSGYX3OD"},"agent_actions":{"view_html":"https://pith.science/pith/CSGYX3ODVMHI5JGLOTP4PVAOJG","download_json":"https://pith.science/pith/CSGYX3ODVMHI5JGLOTP4PVAOJG.json","view_paper":"https://pith.science/paper/CSGYX3OD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04515&json=true","fetch_graph":"https://pith.science/api/pith-number/CSGYX3ODVMHI5JGLOTP4PVAOJG/graph.json","fetch_events":"https://pith.science/api/pith-number/CSGYX3ODVMHI5JGLOTP4PVAOJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSGYX3ODVMHI5JGLOTP4PVAOJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSGYX3ODVMHI5JGLOTP4PVAOJG/action/storage_attestation","attest_author":"https://pith.science/pith/CSGYX3ODVMHI5JGLOTP4PVAOJG/action/author_attestation","sign_citation":"https://pith.science/pith/CSGYX3ODVMHI5JGLOTP4PVAOJG/action/citation_signature","submit_replication":"https://pith.science/pith/CSGYX3ODVMHI5JGLOTP4PVAOJG/action/replication_record"}},"created_at":"2026-08-06T01:35:45.925432+00:00","updated_at":"2026-08-06T01:35:45.925432+00:00"}