{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UQUWPLGSJWFFYXJEVMGBCKAKX5","short_pith_number":"pith:UQUWPLGS","schema_version":"1.0","canonical_sha256":"a42967acd24d8a5c5d24ab0c11280abf572d59695269293538ff0d2d2d811086","source":{"kind":"arxiv","id":"2211.12047","version":2},"attestation_state":"computed","paper":{"title":"Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Ororbia, Ankur Mali","submitted_at":"2022-11-22T06:42:41Z","abstract_excerpt":"In this work, we develop convolutional neural generative coding (Conv-NGC), a generalization of predictive coding to the case of convolution/deconvolution-based computation. Specifically, we concretely implement a flexible neurobiologically-motivated algorithm that progressively refines latent state feature maps in order to dynamically form a more accurate internal representation/reconstruction model of natural images. The performance of the resulting sensory processing system is evaluated on complex datasets such as Color-MNIST, CIFAR-10, and Street House View Numbers (SVHN). We study the eff"},"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":"2211.12047","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T06:42:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c11504fc1cb43fbce9e51891646ecadd33c59e932a00d3e9c46c1ef75343d5f3","abstract_canon_sha256":"17cad96ff42e34a0c340ec43b3c4687b431700c96804e2471afc88e0f6b68b40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:45.690469Z","signature_b64":"fxyR1z2p+8N4C01syRh6DEf7Dv9CCJVg4id3nRYDyN7CFz3eS0rrtJXo2xIODMvMemjAIOMzypLDcHPk2gKvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a42967acd24d8a5c5d24ab0c11280abf572d59695269293538ff0d2d2d811086","last_reissued_at":"2026-07-05T05:38:45.690062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:45.690062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Ororbia, Ankur Mali","submitted_at":"2022-11-22T06:42:41Z","abstract_excerpt":"In this work, we develop convolutional neural generative coding (Conv-NGC), a generalization of predictive coding to the case of convolution/deconvolution-based computation. Specifically, we concretely implement a flexible neurobiologically-motivated algorithm that progressively refines latent state feature maps in order to dynamically form a more accurate internal representation/reconstruction model of natural images. The performance of the resulting sensory processing system is evaluated on complex datasets such as Color-MNIST, CIFAR-10, and Street House View Numbers (SVHN). We study the eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12047","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/2211.12047/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":"2211.12047","created_at":"2026-07-05T05:38:45.690118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12047v2","created_at":"2026-07-05T05:38:45.690118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12047","created_at":"2026-07-05T05:38:45.690118+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQUWPLGSJWFF","created_at":"2026-07-05T05:38:45.690118+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQUWPLGSJWFFYXJE","created_at":"2026-07-05T05:38:45.690118+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQUWPLGS","created_at":"2026-07-05T05:38:45.690118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14635","citing_title":"Bridging Predictive Coding and MDL: A Two-Part Code Framework for Deep Learning","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UQUWPLGSJWFFYXJEVMGBCKAKX5","json":"https://pith.science/pith/UQUWPLGSJWFFYXJEVMGBCKAKX5.json","graph_json":"https://pith.science/api/pith-number/UQUWPLGSJWFFYXJEVMGBCKAKX5/graph.json","events_json":"https://pith.science/api/pith-number/UQUWPLGSJWFFYXJEVMGBCKAKX5/events.json","paper":"https://pith.science/paper/UQUWPLGS"},"agent_actions":{"view_html":"https://pith.science/pith/UQUWPLGSJWFFYXJEVMGBCKAKX5","download_json":"https://pith.science/pith/UQUWPLGSJWFFYXJEVMGBCKAKX5.json","view_paper":"https://pith.science/paper/UQUWPLGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12047&json=true","fetch_graph":"https://pith.science/api/pith-number/UQUWPLGSJWFFYXJEVMGBCKAKX5/graph.json","fetch_events":"https://pith.science/api/pith-number/UQUWPLGSJWFFYXJEVMGBCKAKX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQUWPLGSJWFFYXJEVMGBCKAKX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQUWPLGSJWFFYXJEVMGBCKAKX5/action/storage_attestation","attest_author":"https://pith.science/pith/UQUWPLGSJWFFYXJEVMGBCKAKX5/action/author_attestation","sign_citation":"https://pith.science/pith/UQUWPLGSJWFFYXJEVMGBCKAKX5/action/citation_signature","submit_replication":"https://pith.science/pith/UQUWPLGSJWFFYXJEVMGBCKAKX5/action/replication_record"}},"created_at":"2026-07-05T05:38:45.690118+00:00","updated_at":"2026-07-05T05:38:45.690118+00:00"}