{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LVX3R2LCEKV7X5VHPJTFYJJSYK","short_pith_number":"pith:LVX3R2LC","schema_version":"1.0","canonical_sha256":"5d6fb8e96222abfbf6a77a665c2532c2ba7c69be6321f000a1e7014521570025","source":{"kind":"arxiv","id":"2506.19742","version":1},"attestation_state":"computed","paper":{"title":"NeRF-based CBCT Reconstruction needs Normalization and Initialization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Dai Sun, Han Li, Nassir Navab, Qingpeng Kong, S. Kevin Zhou, Yujia Li, Zhicheng Li, Zhiwei Cheng, Zhuowei Xu","submitted_at":"2025-06-24T16:01:45Z","abstract_excerpt":"Cone Beam Computed Tomography (CBCT) is widely used in medical imaging. However, the limited number and intensity of X-ray projections make reconstruction an ill-posed problem with severe artifacts. NeRF-based methods have achieved great success in this task. However, they suffer from a local-global training mismatch between their two key components: the hash encoder and the neural network. Specifically, in each training step, only a subset of the hash encoder's parameters is used (local sparse), whereas all parameters in the neural network participate (global dense). Consequently, hash featur"},"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":"2506.19742","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2025-06-24T16:01:45Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"5c860292b6b6df3126378a4ff3f2c87cab0a979c8b255a47f53e64a3ad0a5672","abstract_canon_sha256":"93fa146e87671dd52e55a17800e2d877615348148c4ab33175816ce7d9a7a931"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:37.961815Z","signature_b64":"TBT4csemWJNHkwfF6l0R1T5W8ZzCOgyh2ECGgaNFEMeUh1NIzvHw7YF9LLjhnzK9tp17HLIIdVWgHXYbXlxiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d6fb8e96222abfbf6a77a665c2532c2ba7c69be6321f000a1e7014521570025","last_reissued_at":"2026-07-05T11:26:37.961341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:37.961341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeRF-based CBCT Reconstruction needs Normalization and Initialization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Dai Sun, Han Li, Nassir Navab, Qingpeng Kong, S. Kevin Zhou, Yujia Li, Zhicheng Li, Zhiwei Cheng, Zhuowei Xu","submitted_at":"2025-06-24T16:01:45Z","abstract_excerpt":"Cone Beam Computed Tomography (CBCT) is widely used in medical imaging. However, the limited number and intensity of X-ray projections make reconstruction an ill-posed problem with severe artifacts. NeRF-based methods have achieved great success in this task. However, they suffer from a local-global training mismatch between their two key components: the hash encoder and the neural network. Specifically, in each training step, only a subset of the hash encoder's parameters is used (local sparse), whereas all parameters in the neural network participate (global dense). Consequently, hash featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19742","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/2506.19742/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":"2506.19742","created_at":"2026-07-05T11:26:37.961394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19742v1","created_at":"2026-07-05T11:26:37.961394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19742","created_at":"2026-07-05T11:26:37.961394+00:00"},{"alias_kind":"pith_short_12","alias_value":"LVX3R2LCEKV7","created_at":"2026-07-05T11:26:37.961394+00:00"},{"alias_kind":"pith_short_16","alias_value":"LVX3R2LCEKV7X5VH","created_at":"2026-07-05T11:26:37.961394+00:00"},{"alias_kind":"pith_short_8","alias_value":"LVX3R2LC","created_at":"2026-07-05T11:26:37.961394+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23673","citing_title":"HASD: Hierarchical Adaption for pathology Slide-level Domain-shift","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LVX3R2LCEKV7X5VHPJTFYJJSYK","json":"https://pith.science/pith/LVX3R2LCEKV7X5VHPJTFYJJSYK.json","graph_json":"https://pith.science/api/pith-number/LVX3R2LCEKV7X5VHPJTFYJJSYK/graph.json","events_json":"https://pith.science/api/pith-number/LVX3R2LCEKV7X5VHPJTFYJJSYK/events.json","paper":"https://pith.science/paper/LVX3R2LC"},"agent_actions":{"view_html":"https://pith.science/pith/LVX3R2LCEKV7X5VHPJTFYJJSYK","download_json":"https://pith.science/pith/LVX3R2LCEKV7X5VHPJTFYJJSYK.json","view_paper":"https://pith.science/paper/LVX3R2LC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19742&json=true","fetch_graph":"https://pith.science/api/pith-number/LVX3R2LCEKV7X5VHPJTFYJJSYK/graph.json","fetch_events":"https://pith.science/api/pith-number/LVX3R2LCEKV7X5VHPJTFYJJSYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LVX3R2LCEKV7X5VHPJTFYJJSYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LVX3R2LCEKV7X5VHPJTFYJJSYK/action/storage_attestation","attest_author":"https://pith.science/pith/LVX3R2LCEKV7X5VHPJTFYJJSYK/action/author_attestation","sign_citation":"https://pith.science/pith/LVX3R2LCEKV7X5VHPJTFYJJSYK/action/citation_signature","submit_replication":"https://pith.science/pith/LVX3R2LCEKV7X5VHPJTFYJJSYK/action/replication_record"}},"created_at":"2026-07-05T11:26:37.961394+00:00","updated_at":"2026-07-05T11:26:37.961394+00:00"}