{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QZRSC3BN43ZLMH7JBZAYSX6K4T","short_pith_number":"pith:QZRSC3BN","schema_version":"1.0","canonical_sha256":"8663216c2de6f2b61fe90e41895fcae4e6a422b190271795c5e3bc3341a062ed","source":{"kind":"arxiv","id":"2311.01462","version":1},"attestation_state":"computed","paper":{"title":"Idempotent Generative Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Amil Dravid, Assaf Shocher, Inbar Mosseri, Michael Rubinstein, Yossi Gandelsman","submitted_at":"2023-11-02T17:59:55Z","abstract_excerpt":"We propose a new approach for generative modeling based on training a neural network to be idempotent. An idempotent operator is one that can be applied sequentially without changing the result beyond the initial application, namely $f(f(z))=f(z)$. The proposed model $f$ is trained to map a source distribution (e.g, Gaussian noise) to a target distribution (e.g. realistic images) using the following objectives: (1) Instances from the target distribution should map to themselves, namely $f(x)=x$. We define the target manifold as the set of all instances that $f$ maps to themselves. (2) Instance"},"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":"2311.01462","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T17:59:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"35f9f84f6c8ff4409669ece1d7b76abf73ba77fb940bdfdf69bc1fc08dbc9576","abstract_canon_sha256":"7b2dc8adbaa0188c01394e7a3720e17b5baa5540e98880904d1f3241482fddfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:26.684829Z","signature_b64":"Mfvews0vJaZWQ/bpp+fo45BK/HkWJCN/h3AlgZMencTtWispjvW7UE5xxpycRuI3WGSC2AlmBK77wersjG78CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8663216c2de6f2b61fe90e41895fcae4e6a422b190271795c5e3bc3341a062ed","last_reissued_at":"2026-07-05T07:08:26.684376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:26.684376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Idempotent Generative Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Amil Dravid, Assaf Shocher, Inbar Mosseri, Michael Rubinstein, Yossi Gandelsman","submitted_at":"2023-11-02T17:59:55Z","abstract_excerpt":"We propose a new approach for generative modeling based on training a neural network to be idempotent. An idempotent operator is one that can be applied sequentially without changing the result beyond the initial application, namely $f(f(z))=f(z)$. The proposed model $f$ is trained to map a source distribution (e.g, Gaussian noise) to a target distribution (e.g. realistic images) using the following objectives: (1) Instances from the target distribution should map to themselves, namely $f(x)=x$. We define the target manifold as the set of all instances that $f$ maps to themselves. (2) Instance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01462","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/2311.01462/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":"2311.01462","created_at":"2026-07-05T07:08:26.684434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01462v1","created_at":"2026-07-05T07:08:26.684434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01462","created_at":"2026-07-05T07:08:26.684434+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZRSC3BN43ZL","created_at":"2026-07-05T07:08:26.684434+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZRSC3BN43ZLMH7J","created_at":"2026-07-05T07:08:26.684434+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZRSC3BN","created_at":"2026-07-05T07:08:26.684434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22304","citing_title":"Encoder-Decoder Manifold Alignment for Idempotent Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19629","citing_title":"RIVET: Robust Idempotent Voice Attribute Editing","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZRSC3BN43ZLMH7JBZAYSX6K4T","json":"https://pith.science/pith/QZRSC3BN43ZLMH7JBZAYSX6K4T.json","graph_json":"https://pith.science/api/pith-number/QZRSC3BN43ZLMH7JBZAYSX6K4T/graph.json","events_json":"https://pith.science/api/pith-number/QZRSC3BN43ZLMH7JBZAYSX6K4T/events.json","paper":"https://pith.science/paper/QZRSC3BN"},"agent_actions":{"view_html":"https://pith.science/pith/QZRSC3BN43ZLMH7JBZAYSX6K4T","download_json":"https://pith.science/pith/QZRSC3BN43ZLMH7JBZAYSX6K4T.json","view_paper":"https://pith.science/paper/QZRSC3BN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01462&json=true","fetch_graph":"https://pith.science/api/pith-number/QZRSC3BN43ZLMH7JBZAYSX6K4T/graph.json","fetch_events":"https://pith.science/api/pith-number/QZRSC3BN43ZLMH7JBZAYSX6K4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZRSC3BN43ZLMH7JBZAYSX6K4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZRSC3BN43ZLMH7JBZAYSX6K4T/action/storage_attestation","attest_author":"https://pith.science/pith/QZRSC3BN43ZLMH7JBZAYSX6K4T/action/author_attestation","sign_citation":"https://pith.science/pith/QZRSC3BN43ZLMH7JBZAYSX6K4T/action/citation_signature","submit_replication":"https://pith.science/pith/QZRSC3BN43ZLMH7JBZAYSX6K4T/action/replication_record"}},"created_at":"2026-07-05T07:08:26.684434+00:00","updated_at":"2026-07-05T07:08:26.684434+00:00"}