{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZRNOJULPU65QV3NHQH3E2AH2GD","short_pith_number":"pith:ZRNOJULP","schema_version":"1.0","canonical_sha256":"cc5ae4d16fa7bb0aeda781f64d00fa30c310cfb89cba1d70ed46815b7c0288c3","source":{"kind":"arxiv","id":"2409.09542","version":2},"attestation_state":"computed","paper":{"title":"MANGO: Learning Disentangled Image Transformation Manifolds with Grouped Operators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Alex Saad-Falcon, Belen Martin-Urcelay, Brighton Ancelin, Chiraag Kaushik, Nakul Singh, Peimeng Guan, Yenho Chen","submitted_at":"2024-09-14T21:42:38Z","abstract_excerpt":"Learning semantically meaningful image transformations (i.e. rotation, thickness, blur) directly from examples can be a challenging task. Recently, the Manifold Autoencoder (MAE) proposed using a set of Lie group operators to learn image transformations directly from examples. However, this approach has limitations, as the learned operators are not guaranteed to be disentangled and the training routine is prohibitively expensive when scaling up the model. To address these limitations, we propose MANGO (transformation Manifolds with Grouped Operators) for learning disentangled operators that de"},"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":"2409.09542","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2024-09-14T21:42:38Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"e40604003d817d4068ddbcb3b0afcbde93512d190118ddfb7a2f1e22b162abad","abstract_canon_sha256":"34aa6db31b5a2da121c02bbbf44049477ba3ee64db590bbf6db6058c096feba4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:25.591555Z","signature_b64":"c7N3VMtYTA3wkJkvZ0MvRddgEUiIUtT/fJF5vU7H09uS1aMIAiCo6nQG4w5gdQD48TLaYpquzzUWByjijt97BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc5ae4d16fa7bb0aeda781f64d00fa30c310cfb89cba1d70ed46815b7c0288c3","last_reissued_at":"2026-07-05T10:51:25.591063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:25.591063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MANGO: Learning Disentangled Image Transformation Manifolds with Grouped Operators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Alex Saad-Falcon, Belen Martin-Urcelay, Brighton Ancelin, Chiraag Kaushik, Nakul Singh, Peimeng Guan, Yenho Chen","submitted_at":"2024-09-14T21:42:38Z","abstract_excerpt":"Learning semantically meaningful image transformations (i.e. rotation, thickness, blur) directly from examples can be a challenging task. Recently, the Manifold Autoencoder (MAE) proposed using a set of Lie group operators to learn image transformations directly from examples. However, this approach has limitations, as the learned operators are not guaranteed to be disentangled and the training routine is prohibitively expensive when scaling up the model. To address these limitations, we propose MANGO (transformation Manifolds with Grouped Operators) for learning disentangled operators that de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09542","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/2409.09542/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":"2409.09542","created_at":"2026-07-05T10:51:25.591122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09542v2","created_at":"2026-07-05T10:51:25.591122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09542","created_at":"2026-07-05T10:51:25.591122+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRNOJULPU65Q","created_at":"2026-07-05T10:51:25.591122+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRNOJULPU65QV3NH","created_at":"2026-07-05T10:51:25.591122+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRNOJULP","created_at":"2026-07-05T10:51:25.591122+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/ZRNOJULPU65QV3NHQH3E2AH2GD","json":"https://pith.science/pith/ZRNOJULPU65QV3NHQH3E2AH2GD.json","graph_json":"https://pith.science/api/pith-number/ZRNOJULPU65QV3NHQH3E2AH2GD/graph.json","events_json":"https://pith.science/api/pith-number/ZRNOJULPU65QV3NHQH3E2AH2GD/events.json","paper":"https://pith.science/paper/ZRNOJULP"},"agent_actions":{"view_html":"https://pith.science/pith/ZRNOJULPU65QV3NHQH3E2AH2GD","download_json":"https://pith.science/pith/ZRNOJULPU65QV3NHQH3E2AH2GD.json","view_paper":"https://pith.science/paper/ZRNOJULP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09542&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRNOJULPU65QV3NHQH3E2AH2GD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRNOJULPU65QV3NHQH3E2AH2GD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRNOJULPU65QV3NHQH3E2AH2GD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRNOJULPU65QV3NHQH3E2AH2GD/action/storage_attestation","attest_author":"https://pith.science/pith/ZRNOJULPU65QV3NHQH3E2AH2GD/action/author_attestation","sign_citation":"https://pith.science/pith/ZRNOJULPU65QV3NHQH3E2AH2GD/action/citation_signature","submit_replication":"https://pith.science/pith/ZRNOJULPU65QV3NHQH3E2AH2GD/action/replication_record"}},"created_at":"2026-07-05T10:51:25.591122+00:00","updated_at":"2026-07-05T10:51:25.591122+00:00"}