{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4363P7J7DBUVD2SEOGZ5JQQM7D","short_pith_number":"pith:4363P7J7","canonical_record":{"source":{"id":"2605.10830","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T16:47:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a2db8cb05ab62dd9343b9ca1dcab5a58278ebb8d0a6a38697666dc5ebf42509","abstract_canon_sha256":"9601dec35214ba7f10838bebf57c91aa5479deb785770e1b051da09524bf7936"},"schema_version":"1.0"},"canonical_sha256":"e6fdb7fd3f186951ea4471b3d4c20cf8f70d17a291bf4fe39153e09b939efad3","source":{"kind":"arxiv","id":"2605.10830","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10830","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10830v2","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10830","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"pith_short_12","alias_value":"4363P7J7DBUV","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"pith_short_16","alias_value":"4363P7J7DBUVD2SE","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"pith_short_8","alias_value":"4363P7J7","created_at":"2026-05-20T00:03:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4363P7J7DBUVD2SEOGZ5JQQM7D","target":"record","payload":{"canonical_record":{"source":{"id":"2605.10830","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T16:47:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a2db8cb05ab62dd9343b9ca1dcab5a58278ebb8d0a6a38697666dc5ebf42509","abstract_canon_sha256":"9601dec35214ba7f10838bebf57c91aa5479deb785770e1b051da09524bf7936"},"schema_version":"1.0"},"canonical_sha256":"e6fdb7fd3f186951ea4471b3d4c20cf8f70d17a291bf4fe39153e09b939efad3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:17.010820Z","signature_b64":"ygEn/NqGlveNaYeaqZWScS+R5C1qrEvrduLhsFBRaniMtRUw+o8QCwg6Z5P/Wm2L4SMdCYB1YrUfwEaAwpJzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6fdb7fd3f186951ea4471b3d4c20cf8f70d17a291bf4fe39153e09b939efad3","last_reissued_at":"2026-05-20T00:03:17.009526Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:17.009526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.10830","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":"2026-05-20T00:03:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fXmLLSiE4UWycF/xglwejUH7HGfDBVPTIr8XJqh0P5evSGdk6T6ANVIb8M9+Dop3ggAigXS1G0zWzLs4uNipDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:12:23.179242Z"},"content_sha256":"e1cd93b1edc453e962d7879e61f162201d11ab61e2fe26b20f56f6f49262fd83","schema_version":"1.0","event_id":"sha256:e1cd93b1edc453e962d7879e61f162201d11ab61e2fe26b20f56f6f49262fd83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4363P7J7DBUVD2SEOGZ5JQQM7D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predicting 3D structure by latent posterior sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Representing 3D scenes as stochastic latent variables decoded by a NeRF allows sampling from the posterior to perform reconstruction from diverse observations.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Azmi Haider, Dan Rosenbaum","submitted_at":"2026-05-11T16:47:25Z","abstract_excerpt":"The remarkable achievements of both generative models of 2D images and neural field representations for 3D scenes present a compelling opportunity to integrate the strengths of both approaches. In this work, we propose a methodology that combines a NeRF-based representation of 3D scenes with probabilistic modeling and reasoning using diffusion models. We view 3D reconstruction as a perception problem with inherent uncertainty that can thereby benefit from probabilistic inference methods. The core idea is to represent the 3D scene as a stochastic latent variable for which we can learn a prior a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By using the model to generate samples from the posterior we demonstrate that various 3D reconstruction tasks can be performed, differing by the type of observation used as inputs... our method can model the varying levels of inherent uncertainty associated with each task.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a single low-dimensional stochastic latent variable, once decoded by a NeRF, can faithfully represent the posterior distribution over 3D scenes for the range of observation types considered.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A two-stage latent-variable model uses diffusion-based score matching to sample 3D scenes from posteriors conditioned on varied observations via volumetric rendering likelihoods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Representing 3D scenes as stochastic latent variables decoded by a NeRF allows sampling from the posterior to perform reconstruction from diverse observations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ab4d634222559b0eecb55e1631dd6bb28e2f747467d14f2d1ab235857594812a"},"source":{"id":"2605.10830","kind":"arxiv","version":2},"verdict":{"id":"e7401d3e-edbb-41a5-977b-aa147ee4f945","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T05:08:25.132356Z","strongest_claim":"By using the model to generate samples from the posterior we demonstrate that various 3D reconstruction tasks can be performed, differing by the type of observation used as inputs... our method can model the varying levels of inherent uncertainty associated with each task.","one_line_summary":"A two-stage latent-variable model uses diffusion-based score matching to sample 3D scenes from posteriors conditioned on varied observations via volumetric rendering likelihoods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a single low-dimensional stochastic latent variable, once decoded by a NeRF, can faithfully represent the posterior distribution over 3D scenes for the range of observation types considered.","pith_extraction_headline":"Representing 3D scenes as stochastic latent variables decoded by a NeRF allows sampling from the posterior to perform reconstruction from diverse observations."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10830/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T14:34:47.840521Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T10:31:17.593197Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T08:57:26.041883Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"301f5febd28ab57a0507c553453bc3ba69fc5c76203368d0bf6093ba33178137"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"eced152d9ae14170f3635333007dbfcd4de8fe4fdb851eab6f6f81d3eb1cb2e0"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"e7401d3e-edbb-41a5-977b-aa147ee4f945"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U6cxSDYCz/yfDTD1YsaJhMMNGhS9EZf/ijMnwaVYzgXbD/aB43kQu8MgvXPWjvlz42/S6gY/TYyFtRX0bHoBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:12:23.179774Z"},"content_sha256":"8612d477a57ad55d0487c4ea6c985c162458d558b5914c54eb483d52f50d4bd7","schema_version":"1.0","event_id":"sha256:8612d477a57ad55d0487c4ea6c985c162458d558b5914c54eb483d52f50d4bd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4363P7J7DBUVD2SEOGZ5JQQM7D/bundle.json","state_url":"https://pith.science/pith/4363P7J7DBUVD2SEOGZ5JQQM7D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4363P7J7DBUVD2SEOGZ5JQQM7D/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":"2026-06-01T20:12:23Z","links":{"resolver":"https://pith.science/pith/4363P7J7DBUVD2SEOGZ5JQQM7D","bundle":"https://pith.science/pith/4363P7J7DBUVD2SEOGZ5JQQM7D/bundle.json","state":"https://pith.science/pith/4363P7J7DBUVD2SEOGZ5JQQM7D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4363P7J7DBUVD2SEOGZ5JQQM7D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4363P7J7DBUVD2SEOGZ5JQQM7D","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":"9601dec35214ba7f10838bebf57c91aa5479deb785770e1b051da09524bf7936","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T16:47:25Z","title_canon_sha256":"4a2db8cb05ab62dd9343b9ca1dcab5a58278ebb8d0a6a38697666dc5ebf42509"},"schema_version":"1.0","source":{"id":"2605.10830","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10830","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10830v2","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10830","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"pith_short_12","alias_value":"4363P7J7DBUV","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"pith_short_16","alias_value":"4363P7J7DBUVD2SE","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"pith_short_8","alias_value":"4363P7J7","created_at":"2026-05-20T00:03:17Z"}],"graph_snapshots":[{"event_id":"sha256:8612d477a57ad55d0487c4ea6c985c162458d558b5914c54eb483d52f50d4bd7","target":"graph","created_at":"2026-05-20T00:03:17Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By using the model to generate samples from the posterior we demonstrate that various 3D reconstruction tasks can be performed, differing by the type of observation used as inputs... our method can model the varying levels of inherent uncertainty associated with each task."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a single low-dimensional stochastic latent variable, once decoded by a NeRF, can faithfully represent the posterior distribution over 3D scenes for the range of observation types considered."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A two-stage latent-variable model uses diffusion-based score matching to sample 3D scenes from posteriors conditioned on varied observations via volumetric rendering likelihoods."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Representing 3D scenes as stochastic latent variables decoded by a NeRF allows sampling from the posterior to perform reconstruction from diverse observations."}],"snapshot_sha256":"ab4d634222559b0eecb55e1631dd6bb28e2f747467d14f2d1ab235857594812a"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"eced152d9ae14170f3635333007dbfcd4de8fe4fdb851eab6f6f81d3eb1cb2e0"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T14:34:47.840521Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T10:31:17.593197Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T08:57:26.041883Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.10830/integrity.json","findings":[],"snapshot_sha256":"301f5febd28ab57a0507c553453bc3ba69fc5c76203368d0bf6093ba33178137","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The remarkable achievements of both generative models of 2D images and neural field representations for 3D scenes present a compelling opportunity to integrate the strengths of both approaches. In this work, we propose a methodology that combines a NeRF-based representation of 3D scenes with probabilistic modeling and reasoning using diffusion models. We view 3D reconstruction as a perception problem with inherent uncertainty that can thereby benefit from probabilistic inference methods. The core idea is to represent the 3D scene as a stochastic latent variable for which we can learn a prior a","authors_text":"Azmi Haider, Dan Rosenbaum","cross_cats":["cs.LG"],"headline":"Representing 3D scenes as stochastic latent variables decoded by a NeRF allows sampling from the posterior to perform reconstruction from diverse observations.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T16:47:25Z","title":"Predicting 3D structure by latent posterior sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.10830","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T05:08:25.132356Z","id":"e7401d3e-edbb-41a5-977b-aa147ee4f945","model_set":{"reader":"grok-4.3"},"one_line_summary":"A two-stage latent-variable model uses diffusion-based score matching to sample 3D scenes from posteriors conditioned on varied observations via volumetric rendering likelihoods.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Representing 3D scenes as stochastic latent variables decoded by a NeRF allows sampling from the posterior to perform reconstruction from diverse observations.","strongest_claim":"By using the model to generate samples from the posterior we demonstrate that various 3D reconstruction tasks can be performed, differing by the type of observation used as inputs... our method can model the varying levels of inherent uncertainty associated with each task.","weakest_assumption":"That a single low-dimensional stochastic latent variable, once decoded by a NeRF, can faithfully represent the posterior distribution over 3D scenes for the range of observation types considered."}},"verdict_id":"e7401d3e-edbb-41a5-977b-aa147ee4f945"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e1cd93b1edc453e962d7879e61f162201d11ab61e2fe26b20f56f6f49262fd83","target":"record","created_at":"2026-05-20T00:03:17Z","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":"9601dec35214ba7f10838bebf57c91aa5479deb785770e1b051da09524bf7936","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T16:47:25Z","title_canon_sha256":"4a2db8cb05ab62dd9343b9ca1dcab5a58278ebb8d0a6a38697666dc5ebf42509"},"schema_version":"1.0","source":{"id":"2605.10830","kind":"arxiv","version":2}},"canonical_sha256":"e6fdb7fd3f186951ea4471b3d4c20cf8f70d17a291bf4fe39153e09b939efad3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6fdb7fd3f186951ea4471b3d4c20cf8f70d17a291bf4fe39153e09b939efad3","first_computed_at":"2026-05-20T00:03:17.009526Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:17.009526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ygEn/NqGlveNaYeaqZWScS+R5C1qrEvrduLhsFBRaniMtRUw+o8QCwg6Z5P/Wm2L4SMdCYB1YrUfwEaAwpJzAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:17.010820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10830","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1cd93b1edc453e962d7879e61f162201d11ab61e2fe26b20f56f6f49262fd83","sha256:8612d477a57ad55d0487c4ea6c985c162458d558b5914c54eb483d52f50d4bd7"],"state_sha256":"830931c1f9757be760f864d3b77b353716780b76b8e0a1d034a0f80ff0721317"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gIYAGh10ocChhT13KlCY+cAGfaAF++2IO55g5Me/vew4fyVqtu+TZndexNXih/taK3UOVDeWCRLmvq3ILjBXDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T20:12:23.182148Z","bundle_sha256":"0ebd19d61a185464946dea3b74c0ab6511a690cd3c97137883bdc681e58445bd"}}