{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6RB3NNVMWX5MUYDWLOGHQKQQOR","short_pith_number":"pith:6RB3NNVM","schema_version":"1.0","canonical_sha256":"f443b6b6acb5faca60765b8c782a10747e89ed6cf6f2a822d24dbe5b10c3df53","source":{"kind":"arxiv","id":"2607.26829","version":1},"attestation_state":"computed","paper":{"title":"BATS: Resource-Efficient Volumetric Segmentation with Boundary-Aware Mixed-Resolution Tokens","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Hagerman, Fredrik Kahl, Roman Naeem","submitted_at":"2026-07-29T12:21:40Z","abstract_excerpt":"Many high-performing volumetric segmentation models maintain dense multi-scale feature maps, leading to high activation memory and inference cost. We present BATS (Boundary-Aware Token Selection), a 3D medical image segmentation architecture that concentrates fine-resolution processing near predicted class boundaries. A dense boundary predictor identifies where additional resolution is needed, while a fine-first context cascade constructs an input-dependent mixed-resolution hierarchy. Homogeneous regions are represented coarsely, with finer tokens retained around boundaries, thin structures, a"},"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":"2607.26829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T12:21:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a14a56e7e252d93f76663ea26ae53b9b44539cb40d7a696780a3659ec16a405f","abstract_canon_sha256":"9d3990a6d5526d65626287469f67220a2586c239b991e3d6459a92fb5a591c61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f443b6b6acb5faca60765b8c782a10747e89ed6cf6f2a822d24dbe5b10c3df53","last_reissued_at":"2026-07-30T01:22:27.888720Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:22:27.888720Z"},"graph_snapshot":{"paper":{"title":"BATS: Resource-Efficient Volumetric Segmentation with Boundary-Aware Mixed-Resolution Tokens","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Hagerman, Fredrik Kahl, Roman Naeem","submitted_at":"2026-07-29T12:21:40Z","abstract_excerpt":"Many high-performing volumetric segmentation models maintain dense multi-scale feature maps, leading to high activation memory and inference cost. We present BATS (Boundary-Aware Token Selection), a 3D medical image segmentation architecture that concentrates fine-resolution processing near predicted class boundaries. A dense boundary predictor identifies where additional resolution is needed, while a fine-first context cascade constructs an input-dependent mixed-resolution hierarchy. Homogeneous regions are represented coarsely, with finer tokens retained around boundaries, thin structures, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26829","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/2607.26829/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":"2607.26829","created_at":"2026-07-30T01:22:27.893791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26829v1","created_at":"2026-07-30T01:22:27.893791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26829","created_at":"2026-07-30T01:22:27.893791+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RB3NNVMWX5M","created_at":"2026-07-30T01:22:27.893791+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RB3NNVMWX5MUYDW","created_at":"2026-07-30T01:22:27.893791+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RB3NNVM","created_at":"2026-07-30T01:22:27.893791+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/6RB3NNVMWX5MUYDWLOGHQKQQOR","json":"https://pith.science/pith/6RB3NNVMWX5MUYDWLOGHQKQQOR.json","graph_json":"https://pith.science/api/pith-number/6RB3NNVMWX5MUYDWLOGHQKQQOR/graph.json","events_json":"https://pith.science/api/pith-number/6RB3NNVMWX5MUYDWLOGHQKQQOR/events.json","paper":"https://pith.science/paper/6RB3NNVM"},"agent_actions":{"view_html":"https://pith.science/pith/6RB3NNVMWX5MUYDWLOGHQKQQOR","download_json":"https://pith.science/pith/6RB3NNVMWX5MUYDWLOGHQKQQOR.json","view_paper":"https://pith.science/paper/6RB3NNVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26829&json=true","fetch_graph":"https://pith.science/api/pith-number/6RB3NNVMWX5MUYDWLOGHQKQQOR/graph.json","fetch_events":"https://pith.science/api/pith-number/6RB3NNVMWX5MUYDWLOGHQKQQOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RB3NNVMWX5MUYDWLOGHQKQQOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RB3NNVMWX5MUYDWLOGHQKQQOR/action/storage_attestation","attest_author":"https://pith.science/pith/6RB3NNVMWX5MUYDWLOGHQKQQOR/action/author_attestation","sign_citation":"https://pith.science/pith/6RB3NNVMWX5MUYDWLOGHQKQQOR/action/citation_signature","submit_replication":"https://pith.science/pith/6RB3NNVMWX5MUYDWLOGHQKQQOR/action/replication_record"}},"created_at":"2026-07-30T01:22:27.893791+00:00","updated_at":"2026-07-30T01:22:27.893791+00:00"}