{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:33UYG2CGEONDRYXAXMPC5J72R6","short_pith_number":"pith:33UYG2CG","schema_version":"1.0","canonical_sha256":"dee9836846239a38e2e0bb1e2ea7fa8f8f97b7659361f9622b38ca697bdec95d","source":{"kind":"arxiv","id":"2107.01358","version":1},"attestation_state":"computed","paper":{"title":"CInC Flow: Characterizable Invertible 3x3 Convolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Girish Varma, Marius Dufraisse, Sandeep Nagar","submitted_at":"2021-07-03T06:55:24Z","abstract_excerpt":"Normalizing flows are an essential alternative to GANs for generative modelling, which can be optimized directly on the maximum likelihood of the dataset. They also allow computation of the exact latent vector corresponding to an image since they are composed of invertible transformations. However, the requirement of invertibility of the transformation prevents standard and expressive neural network models such as CNNs from being directly used. Emergent convolutions were proposed to construct an invertible 3$\\times$3 CNN layer using a pair of masked CNN layers, making them inefficient. We stud"},"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":"2107.01358","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-03T06:55:24Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"9c8227884fef06f22739923ad08c587d55e260559be4af74577c6a7fee249c12","abstract_canon_sha256":"be1f0e62254c1c1c6c3b36fe9cc6df60f702607033f2d5f3448e7b4f8b8744f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:05.718266Z","signature_b64":"GcOWlhzHH2OmlohaJysYZAy5FWqOU0fm4ZckuAkeGySxsyvi0keRqjatRFNwgrROBwQAmfiCPveKyk4McfySCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dee9836846239a38e2e0bb1e2ea7fa8f8f97b7659361f9622b38ca697bdec95d","last_reissued_at":"2026-07-05T03:04:05.717860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:05.717860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CInC Flow: Characterizable Invertible 3x3 Convolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Girish Varma, Marius Dufraisse, Sandeep Nagar","submitted_at":"2021-07-03T06:55:24Z","abstract_excerpt":"Normalizing flows are an essential alternative to GANs for generative modelling, which can be optimized directly on the maximum likelihood of the dataset. They also allow computation of the exact latent vector corresponding to an image since they are composed of invertible transformations. However, the requirement of invertibility of the transformation prevents standard and expressive neural network models such as CNNs from being directly used. Emergent convolutions were proposed to construct an invertible 3$\\times$3 CNN layer using a pair of masked CNN layers, making them inefficient. We stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01358","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/2107.01358/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":"2107.01358","created_at":"2026-07-05T03:04:05.717917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.01358v1","created_at":"2026-07-05T03:04:05.717917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01358","created_at":"2026-07-05T03:04:05.717917+00:00"},{"alias_kind":"pith_short_12","alias_value":"33UYG2CGEOND","created_at":"2026-07-05T03:04:05.717917+00:00"},{"alias_kind":"pith_short_16","alias_value":"33UYG2CGEONDRYXA","created_at":"2026-07-05T03:04:05.717917+00:00"},{"alias_kind":"pith_short_8","alias_value":"33UYG2CG","created_at":"2026-07-05T03:04:05.717917+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/33UYG2CGEONDRYXAXMPC5J72R6","json":"https://pith.science/pith/33UYG2CGEONDRYXAXMPC5J72R6.json","graph_json":"https://pith.science/api/pith-number/33UYG2CGEONDRYXAXMPC5J72R6/graph.json","events_json":"https://pith.science/api/pith-number/33UYG2CGEONDRYXAXMPC5J72R6/events.json","paper":"https://pith.science/paper/33UYG2CG"},"agent_actions":{"view_html":"https://pith.science/pith/33UYG2CGEONDRYXAXMPC5J72R6","download_json":"https://pith.science/pith/33UYG2CGEONDRYXAXMPC5J72R6.json","view_paper":"https://pith.science/paper/33UYG2CG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.01358&json=true","fetch_graph":"https://pith.science/api/pith-number/33UYG2CGEONDRYXAXMPC5J72R6/graph.json","fetch_events":"https://pith.science/api/pith-number/33UYG2CGEONDRYXAXMPC5J72R6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/33UYG2CGEONDRYXAXMPC5J72R6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/33UYG2CGEONDRYXAXMPC5J72R6/action/storage_attestation","attest_author":"https://pith.science/pith/33UYG2CGEONDRYXAXMPC5J72R6/action/author_attestation","sign_citation":"https://pith.science/pith/33UYG2CGEONDRYXAXMPC5J72R6/action/citation_signature","submit_replication":"https://pith.science/pith/33UYG2CGEONDRYXAXMPC5J72R6/action/replication_record"}},"created_at":"2026-07-05T03:04:05.717917+00:00","updated_at":"2026-07-05T03:04:05.717917+00:00"}