{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YHESBK5P5BVS2UK72CNR5Y3AOP","short_pith_number":"pith:YHESBK5P","schema_version":"1.0","canonical_sha256":"c1c920abafe86b2d515fd09b1ee36073f392b96c5fcb3b08d74291154c733411","source":{"kind":"arxiv","id":"2112.00113","version":1},"attestation_state":"computed","paper":{"title":"Beyond Flatland: Pre-training with a Strong 3D Inductive Bias","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bernhard Egger, Shubhaankar Gupta, Thomas P. O'Connell","submitted_at":"2021-11-30T21:30:24Z","abstract_excerpt":"Pre-training on large-scale databases consisting of natural images and then fine-tuning them to fit the application at hand, or transfer-learning, is a popular strategy in computer vision. However, Kataoka et al., 2020 introduced a technique to eliminate the need for natural images in supervised deep learning by proposing a novel synthetic, formula-based method to generate 2D fractals as training corpus. Using one synthetically generated fractal for each class, they achieved transfer learning results comparable to models pre-trained on natural images. In this project, we take inspiration from "},"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":"2112.00113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-30T21:30:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d9a700c5d3427e8d99d0a55fa434457309b953477428f4fbb14119502710f8a4","abstract_canon_sha256":"dc7ddbd150baed119c59526ea0de8ca334fde3a1c6ba5c95e01e5c13bfd7bdb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:42.743740Z","signature_b64":"GOvygLltUll/Dn9DnuBKjeMkluvpNQHUKNfvhFCHXukXF12bSbm/9Xta8YjmLMa1QyaREwDYDjWwo7K8pQuQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1c920abafe86b2d515fd09b1ee36073f392b96c5fcb3b08d74291154c733411","last_reissued_at":"2026-07-05T03:36:42.743229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:42.743229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Flatland: Pre-training with a Strong 3D Inductive Bias","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bernhard Egger, Shubhaankar Gupta, Thomas P. O'Connell","submitted_at":"2021-11-30T21:30:24Z","abstract_excerpt":"Pre-training on large-scale databases consisting of natural images and then fine-tuning them to fit the application at hand, or transfer-learning, is a popular strategy in computer vision. However, Kataoka et al., 2020 introduced a technique to eliminate the need for natural images in supervised deep learning by proposing a novel synthetic, formula-based method to generate 2D fractals as training corpus. Using one synthetically generated fractal for each class, they achieved transfer learning results comparable to models pre-trained on natural images. In this project, we take inspiration from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00113","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/2112.00113/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":"2112.00113","created_at":"2026-07-05T03:36:42.743289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.00113v1","created_at":"2026-07-05T03:36:42.743289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00113","created_at":"2026-07-05T03:36:42.743289+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHESBK5P5BVS","created_at":"2026-07-05T03:36:42.743289+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHESBK5P5BVS2UK7","created_at":"2026-07-05T03:36:42.743289+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHESBK5P","created_at":"2026-07-05T03:36:42.743289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHESBK5P5BVS2UK72CNR5Y3AOP","json":"https://pith.science/pith/YHESBK5P5BVS2UK72CNR5Y3AOP.json","graph_json":"https://pith.science/api/pith-number/YHESBK5P5BVS2UK72CNR5Y3AOP/graph.json","events_json":"https://pith.science/api/pith-number/YHESBK5P5BVS2UK72CNR5Y3AOP/events.json","paper":"https://pith.science/paper/YHESBK5P"},"agent_actions":{"view_html":"https://pith.science/pith/YHESBK5P5BVS2UK72CNR5Y3AOP","download_json":"https://pith.science/pith/YHESBK5P5BVS2UK72CNR5Y3AOP.json","view_paper":"https://pith.science/paper/YHESBK5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.00113&json=true","fetch_graph":"https://pith.science/api/pith-number/YHESBK5P5BVS2UK72CNR5Y3AOP/graph.json","fetch_events":"https://pith.science/api/pith-number/YHESBK5P5BVS2UK72CNR5Y3AOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHESBK5P5BVS2UK72CNR5Y3AOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHESBK5P5BVS2UK72CNR5Y3AOP/action/storage_attestation","attest_author":"https://pith.science/pith/YHESBK5P5BVS2UK72CNR5Y3AOP/action/author_attestation","sign_citation":"https://pith.science/pith/YHESBK5P5BVS2UK72CNR5Y3AOP/action/citation_signature","submit_replication":"https://pith.science/pith/YHESBK5P5BVS2UK72CNR5Y3AOP/action/replication_record"}},"created_at":"2026-07-05T03:36:42.743289+00:00","updated_at":"2026-07-05T03:36:42.743289+00:00"}