{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CR44T46NZHDHBGRWKPHJCKNS7G","short_pith_number":"pith:CR44T46N","schema_version":"1.0","canonical_sha256":"1479c9f3cdc9c6709a3653ce9129b2f9aeefedf4a5f5a7b2741e6e6a6be61d37","source":{"kind":"arxiv","id":"1907.02392","version":3},"attestation_state":"computed","paper":{"title":"Guided Image Generation with Conditional Invertible Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Carsten L\\\"uth, Carsten Rother, Jakob Kruse, Lynton Ardizzone, Ullrich K\\\"othe","submitted_at":"2019-07-04T13:20:57Z","abstract_excerpt":"In this work, we address the task of natural image generation guided by a conditioning input. We introduce a new architecture called conditional invertible neural network (cINN). The cINN combines the purely generative INN model with an unconstrained feed-forward network, which efficiently preprocesses the conditioning input into useful features. All parameters of the cINN are jointly optimized with a stable, maximum likelihood-based training procedure. By construction, the cINN does not experience mode collapse and generates diverse samples, in contrast to e.g. cGANs. At the same time our mod"},"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":"1907.02392","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-04T13:20:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4313fa916088282841c24c8f678970511ed282b3333b78b6d1597f0778c1bd06","abstract_canon_sha256":"48525bce320bfcca183f13ff0bbe684bb01a6af6a071b1228c0d778ce58a967e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:00.514521Z","signature_b64":"eZceOYO5CECdkXwL6RZJJe5/7K0Di3YaLvBXW7ErAUGbu4O1aGTJBvh66IQAjW6WnnWdGZ0R1hqrUOHitqc+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1479c9f3cdc9c6709a3653ce9129b2f9aeefedf4a5f5a7b2741e6e6a6be61d37","last_reissued_at":"2026-05-17T23:41:00.513810Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:00.513810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guided Image Generation with Conditional Invertible Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Carsten L\\\"uth, Carsten Rother, Jakob Kruse, Lynton Ardizzone, Ullrich K\\\"othe","submitted_at":"2019-07-04T13:20:57Z","abstract_excerpt":"In this work, we address the task of natural image generation guided by a conditioning input. We introduce a new architecture called conditional invertible neural network (cINN). The cINN combines the purely generative INN model with an unconstrained feed-forward network, which efficiently preprocesses the conditioning input into useful features. All parameters of the cINN are jointly optimized with a stable, maximum likelihood-based training procedure. By construction, the cINN does not experience mode collapse and generates diverse samples, in contrast to e.g. cGANs. At the same time our mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02392","kind":"arxiv","version":3},"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":"1907.02392","created_at":"2026-05-17T23:41:00.513931+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.02392v3","created_at":"2026-05-17T23:41:00.513931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02392","created_at":"2026-05-17T23:41:00.513931+00:00"},{"alias_kind":"pith_short_12","alias_value":"CR44T46NZHDH","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"CR44T46NZHDHBGRW","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"CR44T46N","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17511","citing_title":"A flow-matching generative model for event-by-event jet-induced hydro response in high-energy heavy-ion collisions","ref_index":103,"is_internal_anchor":true},{"citing_arxiv_id":"2209.14687","citing_title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26055","citing_title":"Extending Evidence Accumulation Models to Bounded Continuous Self-report Data","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08999","citing_title":"Non-Parametric Rehearsal Learning via Conditional Mean Embeddings","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26055","citing_title":"Extending Evidence Accumulation Models to Bounded Continuous Self-report Data","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24322","citing_title":"Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04955","citing_title":"Order-based Rehearsal Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CR44T46NZHDHBGRWKPHJCKNS7G","json":"https://pith.science/pith/CR44T46NZHDHBGRWKPHJCKNS7G.json","graph_json":"https://pith.science/api/pith-number/CR44T46NZHDHBGRWKPHJCKNS7G/graph.json","events_json":"https://pith.science/api/pith-number/CR44T46NZHDHBGRWKPHJCKNS7G/events.json","paper":"https://pith.science/paper/CR44T46N"},"agent_actions":{"view_html":"https://pith.science/pith/CR44T46NZHDHBGRWKPHJCKNS7G","download_json":"https://pith.science/pith/CR44T46NZHDHBGRWKPHJCKNS7G.json","view_paper":"https://pith.science/paper/CR44T46N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.02392&json=true","fetch_graph":"https://pith.science/api/pith-number/CR44T46NZHDHBGRWKPHJCKNS7G/graph.json","fetch_events":"https://pith.science/api/pith-number/CR44T46NZHDHBGRWKPHJCKNS7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CR44T46NZHDHBGRWKPHJCKNS7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CR44T46NZHDHBGRWKPHJCKNS7G/action/storage_attestation","attest_author":"https://pith.science/pith/CR44T46NZHDHBGRWKPHJCKNS7G/action/author_attestation","sign_citation":"https://pith.science/pith/CR44T46NZHDHBGRWKPHJCKNS7G/action/citation_signature","submit_replication":"https://pith.science/pith/CR44T46NZHDHBGRWKPHJCKNS7G/action/replication_record"}},"created_at":"2026-05-17T23:41:00.513931+00:00","updated_at":"2026-05-17T23:41:00.513931+00:00"}