{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OSGZZ5IOHSOH5W7K4WGMDER2I2","short_pith_number":"pith:OSGZZ5IO","schema_version":"1.0","canonical_sha256":"748d9cf50e3c9c7edbeae58cc1923a46989da16cb5cc40d132030ed88a6d3251","source":{"kind":"arxiv","id":"2206.09027","version":1},"attestation_state":"computed","paper":{"title":"Landscape Learning for Neural Network Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Carl Vondrick, Chengzhi Mao, Hao Wang, Purva Tendulkar, Ruoshi Liu","submitted_at":"2022-06-17T22:05:29Z","abstract_excerpt":"Many machine learning methods operate by inverting a neural network at inference time, which has become a popular technique for solving inverse problems in computer vision, robotics, and graphics. However, these methods often involve gradient descent through a highly non-convex loss landscape, causing the optimization process to be unstable and slow. We introduce a method that learns a loss landscape where gradient descent is efficient, bringing massive improvement and acceleration to the inversion process. We demonstrate this advantage on a number of methods for both generative and discrimina"},"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":"2206.09027","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-17T22:05:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7c8abd3155828b380b7c8f1901d42cba0170073a98116e810937d8d68ec52e9c","abstract_canon_sha256":"58c5b1af516b4135dc127f7401f95844dc012d5ffcbb5f39b4e465727a2972b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:02.979402Z","signature_b64":"Hj1FHCE7LEERiHw8+xHiD/Fhqr851HH6GbaIIEpzoHezuGc53cqoPJxabDHqEIGU/RQDDVeEDvQogMnK3CnKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"748d9cf50e3c9c7edbeae58cc1923a46989da16cb5cc40d132030ed88a6d3251","last_reissued_at":"2026-07-05T04:33:02.978951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:02.978951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Landscape Learning for Neural Network Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Carl Vondrick, Chengzhi Mao, Hao Wang, Purva Tendulkar, Ruoshi Liu","submitted_at":"2022-06-17T22:05:29Z","abstract_excerpt":"Many machine learning methods operate by inverting a neural network at inference time, which has become a popular technique for solving inverse problems in computer vision, robotics, and graphics. However, these methods often involve gradient descent through a highly non-convex loss landscape, causing the optimization process to be unstable and slow. We introduce a method that learns a loss landscape where gradient descent is efficient, bringing massive improvement and acceleration to the inversion process. We demonstrate this advantage on a number of methods for both generative and discrimina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09027","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/2206.09027/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":"2206.09027","created_at":"2026-07-05T04:33:02.979010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.09027v1","created_at":"2026-07-05T04:33:02.979010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09027","created_at":"2026-07-05T04:33:02.979010+00:00"},{"alias_kind":"pith_short_12","alias_value":"OSGZZ5IOHSOH","created_at":"2026-07-05T04:33:02.979010+00:00"},{"alias_kind":"pith_short_16","alias_value":"OSGZZ5IOHSOH5W7K","created_at":"2026-07-05T04:33:02.979010+00:00"},{"alias_kind":"pith_short_8","alias_value":"OSGZZ5IO","created_at":"2026-07-05T04:33:02.979010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23010","citing_title":"Investigating the Invertibility of Multimodal Latent Spaces: Limitations of Optimization-Based Methods","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OSGZZ5IOHSOH5W7K4WGMDER2I2","json":"https://pith.science/pith/OSGZZ5IOHSOH5W7K4WGMDER2I2.json","graph_json":"https://pith.science/api/pith-number/OSGZZ5IOHSOH5W7K4WGMDER2I2/graph.json","events_json":"https://pith.science/api/pith-number/OSGZZ5IOHSOH5W7K4WGMDER2I2/events.json","paper":"https://pith.science/paper/OSGZZ5IO"},"agent_actions":{"view_html":"https://pith.science/pith/OSGZZ5IOHSOH5W7K4WGMDER2I2","download_json":"https://pith.science/pith/OSGZZ5IOHSOH5W7K4WGMDER2I2.json","view_paper":"https://pith.science/paper/OSGZZ5IO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.09027&json=true","fetch_graph":"https://pith.science/api/pith-number/OSGZZ5IOHSOH5W7K4WGMDER2I2/graph.json","fetch_events":"https://pith.science/api/pith-number/OSGZZ5IOHSOH5W7K4WGMDER2I2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OSGZZ5IOHSOH5W7K4WGMDER2I2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OSGZZ5IOHSOH5W7K4WGMDER2I2/action/storage_attestation","attest_author":"https://pith.science/pith/OSGZZ5IOHSOH5W7K4WGMDER2I2/action/author_attestation","sign_citation":"https://pith.science/pith/OSGZZ5IOHSOH5W7K4WGMDER2I2/action/citation_signature","submit_replication":"https://pith.science/pith/OSGZZ5IOHSOH5W7K4WGMDER2I2/action/replication_record"}},"created_at":"2026-07-05T04:33:02.979010+00:00","updated_at":"2026-07-05T04:33:02.979010+00:00"}