{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DOE5TLU73DFWQNSZI4PH46EIE6","short_pith_number":"pith:DOE5TLU7","schema_version":"1.0","canonical_sha256":"1b89d9ae9fd8cb683659471e7e788827841f41b8118ae1d3791cd77c5189fdc3","source":{"kind":"arxiv","id":"2106.06927","version":5},"attestation_state":"computed","paper":{"title":"Inverting Adversarially Robust Networks for Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Minh N. Do, Raymond A. Yeh, Renan A. Rojas-Gomez","submitted_at":"2021-06-13T05:51:00Z","abstract_excerpt":"Despite unconditional feature inversion being the foundation of many image synthesis applications, training an inverter demands a high computational budget, large decoding capacity and imposing conditions such as autoregressive priors. To address these limitations, we propose the use of adversarially robust representations as a perceptual primitive for feature inversion. We train an adversarially robust encoder to extract disentangled and perceptually-aligned image representations, making them easily invertible. By training a simple generator with the mirror architecture of the encoder, we ach"},"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":"2106.06927","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-13T05:51:00Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"7a9b2445b28e91b349a6edc7c919cd24bb384e6952945e1ea74fc5db7499235e","abstract_canon_sha256":"7cea61b3560a6b119bac577511083bfbd14776e48d2a4aa0be3185f8a0d3da8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:03.938006Z","signature_b64":"FH2a+0FRveoo5nxTiIlWYYvRkG1+qhSU++hfnv7vDrxfMmcqpTb5T7KjzOL69OmYSNSXkCnZyHs7h68mnMscDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b89d9ae9fd8cb683659471e7e788827841f41b8118ae1d3791cd77c5189fdc3","last_reissued_at":"2026-07-05T05:09:03.937590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:03.937590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inverting Adversarially Robust Networks for Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Minh N. Do, Raymond A. Yeh, Renan A. Rojas-Gomez","submitted_at":"2021-06-13T05:51:00Z","abstract_excerpt":"Despite unconditional feature inversion being the foundation of many image synthesis applications, training an inverter demands a high computational budget, large decoding capacity and imposing conditions such as autoregressive priors. To address these limitations, we propose the use of adversarially robust representations as a perceptual primitive for feature inversion. We train an adversarially robust encoder to extract disentangled and perceptually-aligned image representations, making them easily invertible. By training a simple generator with the mirror architecture of the encoder, we ach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06927","kind":"arxiv","version":5},"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/2106.06927/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":"2106.06927","created_at":"2026-07-05T05:09:03.937652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06927v5","created_at":"2026-07-05T05:09:03.937652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06927","created_at":"2026-07-05T05:09:03.937652+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOE5TLU73DFW","created_at":"2026-07-05T05:09:03.937652+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOE5TLU73DFWQNSZ","created_at":"2026-07-05T05:09:03.937652+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOE5TLU7","created_at":"2026-07-05T05:09:03.937652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22486","citing_title":"Understanding Adversarial Training with Energy-based Models","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DOE5TLU73DFWQNSZI4PH46EIE6","json":"https://pith.science/pith/DOE5TLU73DFWQNSZI4PH46EIE6.json","graph_json":"https://pith.science/api/pith-number/DOE5TLU73DFWQNSZI4PH46EIE6/graph.json","events_json":"https://pith.science/api/pith-number/DOE5TLU73DFWQNSZI4PH46EIE6/events.json","paper":"https://pith.science/paper/DOE5TLU7"},"agent_actions":{"view_html":"https://pith.science/pith/DOE5TLU73DFWQNSZI4PH46EIE6","download_json":"https://pith.science/pith/DOE5TLU73DFWQNSZI4PH46EIE6.json","view_paper":"https://pith.science/paper/DOE5TLU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06927&json=true","fetch_graph":"https://pith.science/api/pith-number/DOE5TLU73DFWQNSZI4PH46EIE6/graph.json","fetch_events":"https://pith.science/api/pith-number/DOE5TLU73DFWQNSZI4PH46EIE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOE5TLU73DFWQNSZI4PH46EIE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOE5TLU73DFWQNSZI4PH46EIE6/action/storage_attestation","attest_author":"https://pith.science/pith/DOE5TLU73DFWQNSZI4PH46EIE6/action/author_attestation","sign_citation":"https://pith.science/pith/DOE5TLU73DFWQNSZI4PH46EIE6/action/citation_signature","submit_replication":"https://pith.science/pith/DOE5TLU73DFWQNSZI4PH46EIE6/action/replication_record"}},"created_at":"2026-07-05T05:09:03.937652+00:00","updated_at":"2026-07-05T05:09:03.937652+00:00"}