{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AH4MQ2JG6PW3IOOIIOBD5ZVI64","short_pith_number":"pith:AH4MQ2JG","schema_version":"1.0","canonical_sha256":"01f8c86926f3edb439c843823ee6a8f70c346c65503fc535ca34b97e26af2fff","source":{"kind":"arxiv","id":"2006.06280","version":4},"attestation_state":"computed","paper":{"title":"NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Sang-gil Lee, Sungroh Yoon, Sungwon Kim","submitted_at":"2020-06-11T09:35:00Z","abstract_excerpt":"Normalizing flows (NFs) have become a prominent method for deep generative models that allow for an analytic probability density estimation and efficient synthesis. However, a flow-based network is considered to be inefficient in parameter complexity because of reduced expressiveness of bijective mapping, which renders the models unfeasibly expensive in terms of parameters. We present an alternative parameterization scheme called NanoFlow, which uses a single neural density estimator to model multiple transformation stages. Hence, we propose an efficient parameter decomposition method and the "},"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":"2006.06280","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T09:35:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2a514ff27a7fb8f406f2839c4f34fdc5b4fbf9753096b8e01c061a7321539f5d","abstract_canon_sha256":"9eeef8c4d823ec3036abbded4f384bea153e9ebd370e06a53c94101be1a157db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:27.545969Z","signature_b64":"zCSJM6GSZFkoZPxBnidMFiYELbHt81YLIx7MFegQq4YO2mNcH0Z01X3Zfbj7+mjf2wTSSXCfoYHuDHKesmANBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01f8c86926f3edb439c843823ee6a8f70c346c65503fc535ca34b97e26af2fff","last_reissued_at":"2026-07-05T01:45:27.545494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:27.545494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Sang-gil Lee, Sungroh Yoon, Sungwon Kim","submitted_at":"2020-06-11T09:35:00Z","abstract_excerpt":"Normalizing flows (NFs) have become a prominent method for deep generative models that allow for an analytic probability density estimation and efficient synthesis. However, a flow-based network is considered to be inefficient in parameter complexity because of reduced expressiveness of bijective mapping, which renders the models unfeasibly expensive in terms of parameters. We present an alternative parameterization scheme called NanoFlow, which uses a single neural density estimator to model multiple transformation stages. Hence, we propose an efficient parameter decomposition method and the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06280","kind":"arxiv","version":4},"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/2006.06280/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":"2006.06280","created_at":"2026-07-05T01:45:27.545549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.06280v4","created_at":"2026-07-05T01:45:27.545549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06280","created_at":"2026-07-05T01:45:27.545549+00:00"},{"alias_kind":"pith_short_12","alias_value":"AH4MQ2JG6PW3","created_at":"2026-07-05T01:45:27.545549+00:00"},{"alias_kind":"pith_short_16","alias_value":"AH4MQ2JG6PW3IOOI","created_at":"2026-07-05T01:45:27.545549+00:00"},{"alias_kind":"pith_short_8","alias_value":"AH4MQ2JG","created_at":"2026-07-05T01:45:27.545549+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/AH4MQ2JG6PW3IOOIIOBD5ZVI64","json":"https://pith.science/pith/AH4MQ2JG6PW3IOOIIOBD5ZVI64.json","graph_json":"https://pith.science/api/pith-number/AH4MQ2JG6PW3IOOIIOBD5ZVI64/graph.json","events_json":"https://pith.science/api/pith-number/AH4MQ2JG6PW3IOOIIOBD5ZVI64/events.json","paper":"https://pith.science/paper/AH4MQ2JG"},"agent_actions":{"view_html":"https://pith.science/pith/AH4MQ2JG6PW3IOOIIOBD5ZVI64","download_json":"https://pith.science/pith/AH4MQ2JG6PW3IOOIIOBD5ZVI64.json","view_paper":"https://pith.science/paper/AH4MQ2JG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.06280&json=true","fetch_graph":"https://pith.science/api/pith-number/AH4MQ2JG6PW3IOOIIOBD5ZVI64/graph.json","fetch_events":"https://pith.science/api/pith-number/AH4MQ2JG6PW3IOOIIOBD5ZVI64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AH4MQ2JG6PW3IOOIIOBD5ZVI64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AH4MQ2JG6PW3IOOIIOBD5ZVI64/action/storage_attestation","attest_author":"https://pith.science/pith/AH4MQ2JG6PW3IOOIIOBD5ZVI64/action/author_attestation","sign_citation":"https://pith.science/pith/AH4MQ2JG6PW3IOOIIOBD5ZVI64/action/citation_signature","submit_replication":"https://pith.science/pith/AH4MQ2JG6PW3IOOIIOBD5ZVI64/action/replication_record"}},"created_at":"2026-07-05T01:45:27.545549+00:00","updated_at":"2026-07-05T01:45:27.545549+00:00"}