{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WTHNA2TNWDLONTQE2GIOG6OJNE","short_pith_number":"pith:WTHNA2TN","schema_version":"1.0","canonical_sha256":"b4ced06a6db0d6e6ce04d190e379c96937e52ad8c71ced4e173067859d60edb9","source":{"kind":"arxiv","id":"2205.03923","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Discovery and Composition of Object Light Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Cameron Smith, Fredo Durand, Hong-Xing Yu, Jiajun Wu, Joshua B. Tenenbaum, Sergey Zakharov, Vincent Sitzmann","submitted_at":"2022-05-08T17:50:35Z","abstract_excerpt":"Neural scene representations, both continuous and discrete, have recently emerged as a powerful new paradigm for 3D scene understanding. Recent efforts have tackled unsupervised discovery of object-centric neural scene representations. However, the high cost of ray-marching, exacerbated by the fact that each object representation has to be ray-marched separately, leads to insufficiently sampled radiance fields and thus, noisy renderings, poor framerates, and high memory and time complexity during training and rendering. Here, we propose to represent objects in an object-centric, compositional "},"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":"2205.03923","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-08T17:50:35Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG","cs.MM"],"title_canon_sha256":"6ce226509d002ecc8d17360bfffce6a4a6600085d74af4c9d128d41f18c4dba2","abstract_canon_sha256":"17bb24e964f0325f0b6eed70587ba786e36b970263ef04bbdae044e42689ee84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:03.829543Z","signature_b64":"mxfTYFy0zygqAkB02jBCmKLgZ840XPalP+RKYQiGJSL0uiMP0QHWfpWnltpPOOnlPe3/dYH45BswuIx8/WBtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4ced06a6db0d6e6ce04d190e379c96937e52ad8c71ced4e173067859d60edb9","last_reissued_at":"2026-07-05T06:31:03.829059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:03.829059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Discovery and Composition of Object Light Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Cameron Smith, Fredo Durand, Hong-Xing Yu, Jiajun Wu, Joshua B. Tenenbaum, Sergey Zakharov, Vincent Sitzmann","submitted_at":"2022-05-08T17:50:35Z","abstract_excerpt":"Neural scene representations, both continuous and discrete, have recently emerged as a powerful new paradigm for 3D scene understanding. Recent efforts have tackled unsupervised discovery of object-centric neural scene representations. However, the high cost of ray-marching, exacerbated by the fact that each object representation has to be ray-marched separately, leads to insufficiently sampled radiance fields and thus, noisy renderings, poor framerates, and high memory and time complexity during training and rendering. Here, we propose to represent objects in an object-centric, compositional "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03923","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/2205.03923/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":"2205.03923","created_at":"2026-07-05T06:31:03.829121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03923v2","created_at":"2026-07-05T06:31:03.829121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03923","created_at":"2026-07-05T06:31:03.829121+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTHNA2TNWDLO","created_at":"2026-07-05T06:31:03.829121+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTHNA2TNWDLONTQE","created_at":"2026-07-05T06:31:03.829121+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTHNA2TN","created_at":"2026-07-05T06:31:03.829121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09045","citing_title":"Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WTHNA2TNWDLONTQE2GIOG6OJNE","json":"https://pith.science/pith/WTHNA2TNWDLONTQE2GIOG6OJNE.json","graph_json":"https://pith.science/api/pith-number/WTHNA2TNWDLONTQE2GIOG6OJNE/graph.json","events_json":"https://pith.science/api/pith-number/WTHNA2TNWDLONTQE2GIOG6OJNE/events.json","paper":"https://pith.science/paper/WTHNA2TN"},"agent_actions":{"view_html":"https://pith.science/pith/WTHNA2TNWDLONTQE2GIOG6OJNE","download_json":"https://pith.science/pith/WTHNA2TNWDLONTQE2GIOG6OJNE.json","view_paper":"https://pith.science/paper/WTHNA2TN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03923&json=true","fetch_graph":"https://pith.science/api/pith-number/WTHNA2TNWDLONTQE2GIOG6OJNE/graph.json","fetch_events":"https://pith.science/api/pith-number/WTHNA2TNWDLONTQE2GIOG6OJNE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTHNA2TNWDLONTQE2GIOG6OJNE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTHNA2TNWDLONTQE2GIOG6OJNE/action/storage_attestation","attest_author":"https://pith.science/pith/WTHNA2TNWDLONTQE2GIOG6OJNE/action/author_attestation","sign_citation":"https://pith.science/pith/WTHNA2TNWDLONTQE2GIOG6OJNE/action/citation_signature","submit_replication":"https://pith.science/pith/WTHNA2TNWDLONTQE2GIOG6OJNE/action/replication_record"}},"created_at":"2026-07-05T06:31:03.829121+00:00","updated_at":"2026-07-05T06:31:03.829121+00:00"}