{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XMLDQAU2IP6VNQTZGD5XZWVMSZ","short_pith_number":"pith:XMLDQAU2","schema_version":"1.0","canonical_sha256":"bb1638029a43fd56c27930fb7cdaac966b36f1791c0d22a3beb24e972f8dc0ed","source":{"kind":"arxiv","id":"2311.13664","version":2},"attestation_state":"computed","paper":{"title":"Sample as You Infer: Predictive Coding With Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Qinghai Guo, Umais Zahid, Zafeirios Fountas","submitted_at":"2023-11-22T19:36:47Z","abstract_excerpt":"We present a novel algorithm for parameter learning in generic deep generative models that builds upon the predictive coding (PC) framework of computational neuroscience. Our approach modifies the standard PC algorithm to bring performance on-par and exceeding that obtained from standard variational auto-encoder (VAE) training. By injecting Gaussian noise into the PC inference procedure we re-envision it as an overdamped Langevin sampling, which facilitates optimisation with respect to a tight evidence lower bound (ELBO). We improve the resultant encoder-free training method by incorporating a"},"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":"2311.13664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T19:36:47Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE"],"title_canon_sha256":"c4fc782ddd475ec3dc4ee9a58ec9b296777d12c1b2cb433eed9d2ea6f9391b85","abstract_canon_sha256":"99ae2cdc70251b24654b5388575c760114f5e5062a3e60db6225d7f01dc0886b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:08.391472Z","signature_b64":"PhjPWZawBfMrEodoSj71gqluNMNNCTVbeqPVSpJga5Qd59MYKTTOAd0mKmpN3B0gfKdjRS9c2wqXJ5o+VHZgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb1638029a43fd56c27930fb7cdaac966b36f1791c0d22a3beb24e972f8dc0ed","last_reissued_at":"2026-07-05T09:36:08.390996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:08.390996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample as You Infer: Predictive Coding With Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Qinghai Guo, Umais Zahid, Zafeirios Fountas","submitted_at":"2023-11-22T19:36:47Z","abstract_excerpt":"We present a novel algorithm for parameter learning in generic deep generative models that builds upon the predictive coding (PC) framework of computational neuroscience. Our approach modifies the standard PC algorithm to bring performance on-par and exceeding that obtained from standard variational auto-encoder (VAE) training. By injecting Gaussian noise into the PC inference procedure we re-envision it as an overdamped Langevin sampling, which facilitates optimisation with respect to a tight evidence lower bound (ELBO). We improve the resultant encoder-free training method by incorporating a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13664","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/2311.13664/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":"2311.13664","created_at":"2026-07-05T09:36:08.391059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13664v2","created_at":"2026-07-05T09:36:08.391059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13664","created_at":"2026-07-05T09:36:08.391059+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMLDQAU2IP6V","created_at":"2026-07-05T09:36:08.391059+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMLDQAU2IP6VNQTZ","created_at":"2026-07-05T09:36:08.391059+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMLDQAU2","created_at":"2026-07-05T09:36:08.391059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.03676","citing_title":"JPC: Flexible Inference for Predictive Coding Networks in JAX","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMLDQAU2IP6VNQTZGD5XZWVMSZ","json":"https://pith.science/pith/XMLDQAU2IP6VNQTZGD5XZWVMSZ.json","graph_json":"https://pith.science/api/pith-number/XMLDQAU2IP6VNQTZGD5XZWVMSZ/graph.json","events_json":"https://pith.science/api/pith-number/XMLDQAU2IP6VNQTZGD5XZWVMSZ/events.json","paper":"https://pith.science/paper/XMLDQAU2"},"agent_actions":{"view_html":"https://pith.science/pith/XMLDQAU2IP6VNQTZGD5XZWVMSZ","download_json":"https://pith.science/pith/XMLDQAU2IP6VNQTZGD5XZWVMSZ.json","view_paper":"https://pith.science/paper/XMLDQAU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13664&json=true","fetch_graph":"https://pith.science/api/pith-number/XMLDQAU2IP6VNQTZGD5XZWVMSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XMLDQAU2IP6VNQTZGD5XZWVMSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMLDQAU2IP6VNQTZGD5XZWVMSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMLDQAU2IP6VNQTZGD5XZWVMSZ/action/storage_attestation","attest_author":"https://pith.science/pith/XMLDQAU2IP6VNQTZGD5XZWVMSZ/action/author_attestation","sign_citation":"https://pith.science/pith/XMLDQAU2IP6VNQTZGD5XZWVMSZ/action/citation_signature","submit_replication":"https://pith.science/pith/XMLDQAU2IP6VNQTZGD5XZWVMSZ/action/replication_record"}},"created_at":"2026-07-05T09:36:08.391059+00:00","updated_at":"2026-07-05T09:36:08.391059+00:00"}