{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JRN2VVFNEAZIQ7QQBSEECAK4LW","short_pith_number":"pith:JRN2VVFN","schema_version":"1.0","canonical_sha256":"4c5baad4ad2032887e100c8841015c5dbed7cd65c7374b7449f784de855478bf","source":{"kind":"arxiv","id":"1805.05269","version":1},"attestation_state":"computed","paper":{"title":"Normal Similarity Network for Generative Modelling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jay Nandy, Mong Li Lee, Wynne Hsu","submitted_at":"2018-05-14T16:34:20Z","abstract_excerpt":"Gaussian distributions are commonly used as a key building block in many generative models. However, their applicability has not been well explored in deep networks. In this paper, we propose a novel deep generative model named as Normal Similarity Network (NSN) where the layers are constructed with Gaussian-style filters. NSN is trained with a layer-wise non-parametric density estimation algorithm that iteratively down-samples the training images and captures the density of the down-sampled training images in the final layer. Additionally, we propose NSN-Gen for generating new samples from no"},"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":"1805.05269","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-05-14T16:34:20Z","cross_cats_sorted":[],"title_canon_sha256":"22576e516e7e5c029a868328de26b4441fd0427b89cedc827fe5ea4ae47ec589","abstract_canon_sha256":"91d817998e4a28a50dcf805b0d39dbddf0eb11f89ce41ed59f175a332505cf71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:03.572732Z","signature_b64":"Ja62XN0OdX8+oReg9jlLCegsmY3o5U2LqkwC/8va3S+hktwSXfsjKDvrn3fXdw7Y8E0bFu6irhjlINkeLNJBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c5baad4ad2032887e100c8841015c5dbed7cd65c7374b7449f784de855478bf","last_reissued_at":"2026-05-18T00:16:03.572309Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:03.572309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Normal Similarity Network for Generative Modelling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jay Nandy, Mong Li Lee, Wynne Hsu","submitted_at":"2018-05-14T16:34:20Z","abstract_excerpt":"Gaussian distributions are commonly used as a key building block in many generative models. However, their applicability has not been well explored in deep networks. In this paper, we propose a novel deep generative model named as Normal Similarity Network (NSN) where the layers are constructed with Gaussian-style filters. NSN is trained with a layer-wise non-parametric density estimation algorithm that iteratively down-samples the training images and captures the density of the down-sampled training images in the final layer. Additionally, we propose NSN-Gen for generating new samples from no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.05269","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":""},"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":"1805.05269","created_at":"2026-05-18T00:16:03.572393+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.05269v1","created_at":"2026-05-18T00:16:03.572393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.05269","created_at":"2026-05-18T00:16:03.572393+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRN2VVFNEAZI","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRN2VVFNEAZIQ7QQ","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRN2VVFN","created_at":"2026-05-18T12:32:31.084164+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/JRN2VVFNEAZIQ7QQBSEECAK4LW","json":"https://pith.science/pith/JRN2VVFNEAZIQ7QQBSEECAK4LW.json","graph_json":"https://pith.science/api/pith-number/JRN2VVFNEAZIQ7QQBSEECAK4LW/graph.json","events_json":"https://pith.science/api/pith-number/JRN2VVFNEAZIQ7QQBSEECAK4LW/events.json","paper":"https://pith.science/paper/JRN2VVFN"},"agent_actions":{"view_html":"https://pith.science/pith/JRN2VVFNEAZIQ7QQBSEECAK4LW","download_json":"https://pith.science/pith/JRN2VVFNEAZIQ7QQBSEECAK4LW.json","view_paper":"https://pith.science/paper/JRN2VVFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.05269&json=true","fetch_graph":"https://pith.science/api/pith-number/JRN2VVFNEAZIQ7QQBSEECAK4LW/graph.json","fetch_events":"https://pith.science/api/pith-number/JRN2VVFNEAZIQ7QQBSEECAK4LW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRN2VVFNEAZIQ7QQBSEECAK4LW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRN2VVFNEAZIQ7QQBSEECAK4LW/action/storage_attestation","attest_author":"https://pith.science/pith/JRN2VVFNEAZIQ7QQBSEECAK4LW/action/author_attestation","sign_citation":"https://pith.science/pith/JRN2VVFNEAZIQ7QQBSEECAK4LW/action/citation_signature","submit_replication":"https://pith.science/pith/JRN2VVFNEAZIQ7QQBSEECAK4LW/action/replication_record"}},"created_at":"2026-05-18T00:16:03.572393+00:00","updated_at":"2026-05-18T00:16:03.572393+00:00"}