{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Q2YF7JWRDEKJNF67FTC53Q6WH4","short_pith_number":"pith:Q2YF7JWR","schema_version":"1.0","canonical_sha256":"86b05fa6d119149697df2cc5ddc3d63f3c6152bd7f0a1dc34611c30f4810ed18","source":{"kind":"arxiv","id":"2203.03570","version":1},"attestation_state":"computed","paper":{"title":"Kubric: A scalable dataset generator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhijit Kundu, Andrea Tagliasacchi, Austin Stone, Carl Doersch, Cengiz Oztireli, Charles Herrmann, Dan Gnanapragasam, Daniel Duckworth, Daniel Rebain, David J. Fleet, Deqing Sun, Derek Nowrouzezahrai, Dmitry Lagun, Etienne Pot, Fangcheng Zhong, Florian Golemo, Francois Belletti, Henning Meyer, Hsueh-Ti (Derek) Liu, Issam Laradji, Klaus Greff, Kwang Moo Yi, Lucas Beyer, Matan Sela, Mehdi S. M. Sajjadi, Noha Radwan, Sara Sabour, Suhani Vora, Thomas Kipf, Tianhao Wu, Vincent Sitzmann, Yilun Du, Yishu Miao, Ziyu Wang","submitted_at":"2022-03-07T18:13:59Z","abstract_excerpt":"Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details. But collecting, processing and annotating real data at scale is difficult, expensive, and frequently raises additional privacy, fairness and legal concerns. Synthetic data is a powerful tool with the potential to address these shortcomings: 1) it is cheap 2) supports rich ground-truth annotations 3) offers full control over data and 4) can circumvent or mitigate problems regarding bias, privacy and licensi"},"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":"2203.03570","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-07T18:13:59Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"e25aeb01b25d864784ee002a33f7656dc98aafcc17f07d289e851bef62150d02","abstract_canon_sha256":"22952ec0e2a5319163656ec4b4ce51d40eee5536bf075f2843b9d50088e57826"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:35.943674Z","signature_b64":"b+kdvN+wr/VdB9Vf9I+wIqLrIb5nkF0lrLv95bJxrqFjKRvJqQ9bv7EpRtgYUg1aNptn66UkTGKwnSTM6M+3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86b05fa6d119149697df2cc5ddc3d63f3c6152bd7f0a1dc34611c30f4810ed18","last_reissued_at":"2026-07-05T04:02:35.943157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:35.943157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kubric: A scalable dataset generator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhijit Kundu, Andrea Tagliasacchi, Austin Stone, Carl Doersch, Cengiz Oztireli, Charles Herrmann, Dan Gnanapragasam, Daniel Duckworth, Daniel Rebain, David J. Fleet, Deqing Sun, Derek Nowrouzezahrai, Dmitry Lagun, Etienne Pot, Fangcheng Zhong, Florian Golemo, Francois Belletti, Henning Meyer, Hsueh-Ti (Derek) Liu, Issam Laradji, Klaus Greff, Kwang Moo Yi, Lucas Beyer, Matan Sela, Mehdi S. M. Sajjadi, Noha Radwan, Sara Sabour, Suhani Vora, Thomas Kipf, Tianhao Wu, Vincent Sitzmann, Yilun Du, Yishu Miao, Ziyu Wang","submitted_at":"2022-03-07T18:13:59Z","abstract_excerpt":"Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details. But collecting, processing and annotating real data at scale is difficult, expensive, and frequently raises additional privacy, fairness and legal concerns. Synthetic data is a powerful tool with the potential to address these shortcomings: 1) it is cheap 2) supports rich ground-truth annotations 3) offers full control over data and 4) can circumvent or mitigate problems regarding bias, privacy and licensi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03570","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/2203.03570/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":"2203.03570","created_at":"2026-07-05T04:02:35.943222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.03570v1","created_at":"2026-07-05T04:02:35.943222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03570","created_at":"2026-07-05T04:02:35.943222+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2YF7JWRDEKJ","created_at":"2026-07-05T04:02:35.943222+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2YF7JWRDEKJNF67","created_at":"2026-07-05T04:02:35.943222+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2YF7JWR","created_at":"2026-07-05T04:02:35.943222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17511","citing_title":"MagicSim: A Unified Infrastructure for Executable Embodied Interaction","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22190","citing_title":"No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10333","citing_title":"Zero-shot World Models Are Developmentally Efficient Learners","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q2YF7JWRDEKJNF67FTC53Q6WH4","json":"https://pith.science/pith/Q2YF7JWRDEKJNF67FTC53Q6WH4.json","graph_json":"https://pith.science/api/pith-number/Q2YF7JWRDEKJNF67FTC53Q6WH4/graph.json","events_json":"https://pith.science/api/pith-number/Q2YF7JWRDEKJNF67FTC53Q6WH4/events.json","paper":"https://pith.science/paper/Q2YF7JWR"},"agent_actions":{"view_html":"https://pith.science/pith/Q2YF7JWRDEKJNF67FTC53Q6WH4","download_json":"https://pith.science/pith/Q2YF7JWRDEKJNF67FTC53Q6WH4.json","view_paper":"https://pith.science/paper/Q2YF7JWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.03570&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2YF7JWRDEKJNF67FTC53Q6WH4/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2YF7JWRDEKJNF67FTC53Q6WH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2YF7JWRDEKJNF67FTC53Q6WH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2YF7JWRDEKJNF67FTC53Q6WH4/action/storage_attestation","attest_author":"https://pith.science/pith/Q2YF7JWRDEKJNF67FTC53Q6WH4/action/author_attestation","sign_citation":"https://pith.science/pith/Q2YF7JWRDEKJNF67FTC53Q6WH4/action/citation_signature","submit_replication":"https://pith.science/pith/Q2YF7JWRDEKJNF67FTC53Q6WH4/action/replication_record"}},"created_at":"2026-07-05T04:02:35.943222+00:00","updated_at":"2026-07-05T04:02:35.943222+00:00"}