{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZJLLSOAEVBY3O57DRTI64OH4BZ","short_pith_number":"pith:ZJLLSOAE","schema_version":"1.0","canonical_sha256":"ca56b93804a871b777e38cd1ee38fc0e788bd923f474b66c74e810ed45d2432d","source":{"kind":"arxiv","id":"2304.10306","version":2},"attestation_state":"computed","paper":{"title":"FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aleksei Ivakhnenko, Anastasia Yaschenko, Andrei Spiridonov, Leonid Kostyushko, Polina Karpikova, Radionova Ekaterina, Riccardo Fabbricatore","submitted_at":"2023-04-20T13:40:49Z","abstract_excerpt":"Generative DNNs are a powerful tool for image synthesis, but they are limited by their computational load. On the other hand, given a trained model and a task, e.g. faces generation within a range of characteristics, the output image quality will be unevenly distributed among images with different characteristics. It follows, that we might restrain the models complexity on some instances, maintaining a high quality. We propose a method for diminishing computations by adding so-called early exit branches to the original architecture, and dynamically switching the computational path depending on"},"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":"2304.10306","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-20T13:40:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c5233a3f49588d27b2df048f2c6a6f379e80ea07a35a9edc5aeb664361f0e630","abstract_canon_sha256":"45c8e76f9ed02a37420993091bcb1d1fba3df8461627c1b47a37caa2fbd8ce0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:10.947467Z","signature_b64":"7IIDPCLOrUs1Ktfn+7SXwkWzFXnVI4vBaM27TKudWEbGKw5bxOUenI5c5SHP25qtE2yxfv0f5docdQOs+R/9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca56b93804a871b777e38cd1ee38fc0e788bd923f474b66c74e810ed45d2432d","last_reissued_at":"2026-07-05T07:21:10.947049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:10.947049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aleksei Ivakhnenko, Anastasia Yaschenko, Andrei Spiridonov, Leonid Kostyushko, Polina Karpikova, Radionova Ekaterina, Riccardo Fabbricatore","submitted_at":"2023-04-20T13:40:49Z","abstract_excerpt":"Generative DNNs are a powerful tool for image synthesis, but they are limited by their computational load. On the other hand, given a trained model and a task, e.g. faces generation within a range of characteristics, the output image quality will be unevenly distributed among images with different characteristics. It follows, that we might restrain the models complexity on some instances, maintaining a high quality. We propose a method for diminishing computations by adding so-called early exit branches to the original architecture, and dynamically switching the computational path depending on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10306","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/2304.10306/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":"2304.10306","created_at":"2026-07-05T07:21:10.947104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.10306v2","created_at":"2026-07-05T07:21:10.947104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10306","created_at":"2026-07-05T07:21:10.947104+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJLLSOAEVBY3","created_at":"2026-07-05T07:21:10.947104+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJLLSOAEVBY3O57D","created_at":"2026-07-05T07:21:10.947104+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJLLSOAE","created_at":"2026-07-05T07:21:10.947104+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/ZJLLSOAEVBY3O57DRTI64OH4BZ","json":"https://pith.science/pith/ZJLLSOAEVBY3O57DRTI64OH4BZ.json","graph_json":"https://pith.science/api/pith-number/ZJLLSOAEVBY3O57DRTI64OH4BZ/graph.json","events_json":"https://pith.science/api/pith-number/ZJLLSOAEVBY3O57DRTI64OH4BZ/events.json","paper":"https://pith.science/paper/ZJLLSOAE"},"agent_actions":{"view_html":"https://pith.science/pith/ZJLLSOAEVBY3O57DRTI64OH4BZ","download_json":"https://pith.science/pith/ZJLLSOAEVBY3O57DRTI64OH4BZ.json","view_paper":"https://pith.science/paper/ZJLLSOAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.10306&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJLLSOAEVBY3O57DRTI64OH4BZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJLLSOAEVBY3O57DRTI64OH4BZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJLLSOAEVBY3O57DRTI64OH4BZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJLLSOAEVBY3O57DRTI64OH4BZ/action/storage_attestation","attest_author":"https://pith.science/pith/ZJLLSOAEVBY3O57DRTI64OH4BZ/action/author_attestation","sign_citation":"https://pith.science/pith/ZJLLSOAEVBY3O57DRTI64OH4BZ/action/citation_signature","submit_replication":"https://pith.science/pith/ZJLLSOAEVBY3O57DRTI64OH4BZ/action/replication_record"}},"created_at":"2026-07-05T07:21:10.947104+00:00","updated_at":"2026-07-05T07:21:10.947104+00:00"}