{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VMHV47GBJMBBDC4XVLKEAFNNIG","short_pith_number":"pith:VMHV47GB","schema_version":"1.0","canonical_sha256":"ab0f5e7cc14b02118b97aad44015ad418556ae0c88cd6492edc367423e7981c2","source":{"kind":"arxiv","id":"2505.23481","version":2},"attestation_state":"computed","paper":{"title":"PhysicsNeRF: Physics-Guided 3D Reconstruction from Sparse Views","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hasan Kurban, Hussein Alnuweiri, Mohamed Rayan Barhdadi","submitted_at":"2025-05-29T14:30:17Z","abstract_excerpt":"PhysicsNeRF is a physically grounded framework for 3D reconstruction from sparse views, extending Neural Radiance Fields with four complementary constraints: depth ranking, RegNeRF-style consistency, sparsity priors, and cross-view alignment. While standard NeRFs fail under sparse supervision, PhysicsNeRF employs a compact 0.67M-parameter architecture and achieves 21.4 dB average PSNR using only 8 views, outperforming prior methods. A generalization gap of 5.7-6.2 dB is consistently observed and analyzed, revealing fundamental limitations of sparse-view reconstruction. PhysicsNeRF enables phys"},"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":"2505.23481","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T14:30:17Z","cross_cats_sorted":[],"title_canon_sha256":"58fe5062e6aac3ef24087bfe992bdf9b537656822181438fcceac465f6f7e987","abstract_canon_sha256":"0ff291930e83a2732c8cf6a5ded7a824ef52a59cad391b9e6712fc9e4211c71b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:11.433073Z","signature_b64":"jmXuJuxCX7rH4SdI+vYdxDZiFJHYhwK+4uj7oDhCvTjzK5VLkIXy2Ae+nnEYTRqiRmCIkJNOVOm21lABsUCvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab0f5e7cc14b02118b97aad44015ad418556ae0c88cd6492edc367423e7981c2","last_reissued_at":"2026-07-05T11:25:11.432586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:11.432586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhysicsNeRF: Physics-Guided 3D Reconstruction from Sparse Views","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hasan Kurban, Hussein Alnuweiri, Mohamed Rayan Barhdadi","submitted_at":"2025-05-29T14:30:17Z","abstract_excerpt":"PhysicsNeRF is a physically grounded framework for 3D reconstruction from sparse views, extending Neural Radiance Fields with four complementary constraints: depth ranking, RegNeRF-style consistency, sparsity priors, and cross-view alignment. While standard NeRFs fail under sparse supervision, PhysicsNeRF employs a compact 0.67M-parameter architecture and achieves 21.4 dB average PSNR using only 8 views, outperforming prior methods. A generalization gap of 5.7-6.2 dB is consistently observed and analyzed, revealing fundamental limitations of sparse-view reconstruction. PhysicsNeRF enables phys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23481","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/2505.23481/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":"2505.23481","created_at":"2026-07-05T11:25:11.432645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23481v2","created_at":"2026-07-05T11:25:11.432645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23481","created_at":"2026-07-05T11:25:11.432645+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMHV47GBJMBB","created_at":"2026-07-05T11:25:11.432645+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMHV47GBJMBBDC4X","created_at":"2026-07-05T11:25:11.432645+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMHV47GB","created_at":"2026-07-05T11:25:11.432645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18623","citing_title":"Intrinsic 4D Gaussian Segmentation from Scene Cues","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VMHV47GBJMBBDC4XVLKEAFNNIG","json":"https://pith.science/pith/VMHV47GBJMBBDC4XVLKEAFNNIG.json","graph_json":"https://pith.science/api/pith-number/VMHV47GBJMBBDC4XVLKEAFNNIG/graph.json","events_json":"https://pith.science/api/pith-number/VMHV47GBJMBBDC4XVLKEAFNNIG/events.json","paper":"https://pith.science/paper/VMHV47GB"},"agent_actions":{"view_html":"https://pith.science/pith/VMHV47GBJMBBDC4XVLKEAFNNIG","download_json":"https://pith.science/pith/VMHV47GBJMBBDC4XVLKEAFNNIG.json","view_paper":"https://pith.science/paper/VMHV47GB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23481&json=true","fetch_graph":"https://pith.science/api/pith-number/VMHV47GBJMBBDC4XVLKEAFNNIG/graph.json","fetch_events":"https://pith.science/api/pith-number/VMHV47GBJMBBDC4XVLKEAFNNIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMHV47GBJMBBDC4XVLKEAFNNIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMHV47GBJMBBDC4XVLKEAFNNIG/action/storage_attestation","attest_author":"https://pith.science/pith/VMHV47GBJMBBDC4XVLKEAFNNIG/action/author_attestation","sign_citation":"https://pith.science/pith/VMHV47GBJMBBDC4XVLKEAFNNIG/action/citation_signature","submit_replication":"https://pith.science/pith/VMHV47GBJMBBDC4XVLKEAFNNIG/action/replication_record"}},"created_at":"2026-07-05T11:25:11.432645+00:00","updated_at":"2026-07-05T11:25:11.432645+00:00"}