{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:AISLESSJFJECKNWLNKFHWZCWI3","short_pith_number":"pith:AISLESSJ","schema_version":"1.0","canonical_sha256":"0224b24a492a482536cb6a8a7b645646f7862bf7da6e84671e3e39fb4fb2d610","source":{"kind":"arxiv","id":"1702.04782","version":2},"attestation_state":"computed","paper":{"title":"Precise Recovery of Latent Vectors from Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Subarna Tripathi, Zachary C. Lipton","submitted_at":"2017-02-15T21:26:21Z","abstract_excerpt":"Generative adversarial networks (GANs) transform latent vectors into visually plausible images. It is generally thought that the original GAN formulation gives no out-of-the-box method to reverse the mapping, projecting images back into latent space. We introduce a simple, gradient-based technique called stochastic clipping. In experiments, for images generated by the GAN, we precisely recover their latent vector pre-images 100% of the time. Additional experiments demonstrate that this method is robust to noise. Finally, we show that even for unseen images, our method appears to recover unique"},"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":"1702.04782","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-15T21:26:21Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"2dda04cc990d36765e5b3543580df94fc033ea826c7b1791097c9bb4379407b7","abstract_canon_sha256":"0c355adfaf93e23257bbefc558a98bac607d0dbc1ea109205426d04fc6299af3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:34.923295Z","signature_b64":"DuEtSy8+fludFkJljoM6I9CJpt1JDd0TeHoPfqVS4BpBE68rcHdCTA1Tfmp1ogttPmDVPBDXt1qDvKqSq0XlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0224b24a492a482536cb6a8a7b645646f7862bf7da6e84671e3e39fb4fb2d610","last_reissued_at":"2026-05-18T00:50:34.922683Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:34.922683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Precise Recovery of Latent Vectors from Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Subarna Tripathi, Zachary C. Lipton","submitted_at":"2017-02-15T21:26:21Z","abstract_excerpt":"Generative adversarial networks (GANs) transform latent vectors into visually plausible images. It is generally thought that the original GAN formulation gives no out-of-the-box method to reverse the mapping, projecting images back into latent space. We introduce a simple, gradient-based technique called stochastic clipping. In experiments, for images generated by the GAN, we precisely recover their latent vector pre-images 100% of the time. Additional experiments demonstrate that this method is robust to noise. Finally, we show that even for unseen images, our method appears to recover unique"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.04782","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":""},"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":"1702.04782","created_at":"2026-05-18T00:50:34.922795+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.04782v2","created_at":"2026-05-18T00:50:34.922795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.04782","created_at":"2026-05-18T00:50:34.922795+00:00"},{"alias_kind":"pith_short_12","alias_value":"AISLESSJFJEC","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"AISLESSJFJECKNWL","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"AISLESSJ","created_at":"2026-05-18T12:31:05.417338+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/AISLESSJFJECKNWLNKFHWZCWI3","json":"https://pith.science/pith/AISLESSJFJECKNWLNKFHWZCWI3.json","graph_json":"https://pith.science/api/pith-number/AISLESSJFJECKNWLNKFHWZCWI3/graph.json","events_json":"https://pith.science/api/pith-number/AISLESSJFJECKNWLNKFHWZCWI3/events.json","paper":"https://pith.science/paper/AISLESSJ"},"agent_actions":{"view_html":"https://pith.science/pith/AISLESSJFJECKNWLNKFHWZCWI3","download_json":"https://pith.science/pith/AISLESSJFJECKNWLNKFHWZCWI3.json","view_paper":"https://pith.science/paper/AISLESSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.04782&json=true","fetch_graph":"https://pith.science/api/pith-number/AISLESSJFJECKNWLNKFHWZCWI3/graph.json","fetch_events":"https://pith.science/api/pith-number/AISLESSJFJECKNWLNKFHWZCWI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AISLESSJFJECKNWLNKFHWZCWI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AISLESSJFJECKNWLNKFHWZCWI3/action/storage_attestation","attest_author":"https://pith.science/pith/AISLESSJFJECKNWLNKFHWZCWI3/action/author_attestation","sign_citation":"https://pith.science/pith/AISLESSJFJECKNWLNKFHWZCWI3/action/citation_signature","submit_replication":"https://pith.science/pith/AISLESSJFJECKNWLNKFHWZCWI3/action/replication_record"}},"created_at":"2026-05-18T00:50:34.922795+00:00","updated_at":"2026-05-18T00:50:34.922795+00:00"}