{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QYHSIOMGFVXAUQAQYFDLCH7RUO","short_pith_number":"pith:QYHSIOMG","schema_version":"1.0","canonical_sha256":"860f2439862d6e0a4010c146b11ff1a3a3d7fb11162ab8eb8d241b8bce6d6857","source":{"kind":"arxiv","id":"2303.12722","version":1},"attestation_state":"computed","paper":{"title":"Learning Fractals by Gradient Descent","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng-Hao Tu, David Carlyn, Hong-You Chen, Wei-Lun Chao","submitted_at":"2023-03-14T17:20:25Z","abstract_excerpt":"Fractals are geometric shapes that can display complex and self-similar patterns found in nature (e.g., clouds and plants). Recent works in visual recognition have leveraged this property to create random fractal images for model pre-training. In this paper, we study the inverse problem -- given a target image (not necessarily a fractal), we aim to generate a fractal image that looks like it. We propose a novel approach that learns the parameters underlying a fractal image via gradient descent. We show that our approach can find fractal parameters of high visual quality and be compatible with "},"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":"2303.12722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-14T17:20:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8c43298860c4cdad0b11ea138c65866817cadefa5242e340590c93e807f935b1","abstract_canon_sha256":"ca1387d71e4fe8990a28b06f872015047322000d80bd3cb074d44a6c75715a34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:44.316605Z","signature_b64":"zcF0EmHYH94Ag4FEqnPh+WlW7dTyD4COgoY9lsILT7HXYf3MvykzoRXDOSYYLIZmXJxgSLvqwLlIW4C4EA/MCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"860f2439862d6e0a4010c146b11ff1a3a3d7fb11162ab8eb8d241b8bce6d6857","last_reissued_at":"2026-07-05T05:53:44.316089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:44.316089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Fractals by Gradient Descent","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng-Hao Tu, David Carlyn, Hong-You Chen, Wei-Lun Chao","submitted_at":"2023-03-14T17:20:25Z","abstract_excerpt":"Fractals are geometric shapes that can display complex and self-similar patterns found in nature (e.g., clouds and plants). Recent works in visual recognition have leveraged this property to create random fractal images for model pre-training. In this paper, we study the inverse problem -- given a target image (not necessarily a fractal), we aim to generate a fractal image that looks like it. We propose a novel approach that learns the parameters underlying a fractal image via gradient descent. We show that our approach can find fractal parameters of high visual quality and be compatible with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12722","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/2303.12722/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":"2303.12722","created_at":"2026-07-05T05:53:44.316160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.12722v1","created_at":"2026-07-05T05:53:44.316160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12722","created_at":"2026-07-05T05:53:44.316160+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYHSIOMGFVXA","created_at":"2026-07-05T05:53:44.316160+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYHSIOMGFVXAUQAQ","created_at":"2026-07-05T05:53:44.316160+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYHSIOMG","created_at":"2026-07-05T05:53:44.316160+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/QYHSIOMGFVXAUQAQYFDLCH7RUO","json":"https://pith.science/pith/QYHSIOMGFVXAUQAQYFDLCH7RUO.json","graph_json":"https://pith.science/api/pith-number/QYHSIOMGFVXAUQAQYFDLCH7RUO/graph.json","events_json":"https://pith.science/api/pith-number/QYHSIOMGFVXAUQAQYFDLCH7RUO/events.json","paper":"https://pith.science/paper/QYHSIOMG"},"agent_actions":{"view_html":"https://pith.science/pith/QYHSIOMGFVXAUQAQYFDLCH7RUO","download_json":"https://pith.science/pith/QYHSIOMGFVXAUQAQYFDLCH7RUO.json","view_paper":"https://pith.science/paper/QYHSIOMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.12722&json=true","fetch_graph":"https://pith.science/api/pith-number/QYHSIOMGFVXAUQAQYFDLCH7RUO/graph.json","fetch_events":"https://pith.science/api/pith-number/QYHSIOMGFVXAUQAQYFDLCH7RUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYHSIOMGFVXAUQAQYFDLCH7RUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYHSIOMGFVXAUQAQYFDLCH7RUO/action/storage_attestation","attest_author":"https://pith.science/pith/QYHSIOMGFVXAUQAQYFDLCH7RUO/action/author_attestation","sign_citation":"https://pith.science/pith/QYHSIOMGFVXAUQAQYFDLCH7RUO/action/citation_signature","submit_replication":"https://pith.science/pith/QYHSIOMGFVXAUQAQYFDLCH7RUO/action/replication_record"}},"created_at":"2026-07-05T05:53:44.316160+00:00","updated_at":"2026-07-05T05:53:44.316160+00:00"}