{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CPRFZDD7LLU2QAC7J4D7VWL3LG","short_pith_number":"pith:CPRFZDD7","schema_version":"1.0","canonical_sha256":"13e25c8c7f5ae9a8005f4f07fad97b598010b5a26e818411160a6082ef38655d","source":{"kind":"arxiv","id":"2410.04708","version":1},"attestation_state":"computed","paper":{"title":"Tight Stability, Convergence, and Robustness Bounds for Predictive Coding Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Ororbia, Ankur Mali, Tommaso Salvatori","submitted_at":"2024-10-07T02:57:26Z","abstract_excerpt":"Energy-based learning algorithms, such as predictive coding (PC), have garnered significant attention in the machine learning community due to their theoretical properties, such as local operations and biologically plausible mechanisms for error correction. In this work, we rigorously analyze the stability, robustness, and convergence of PC through the lens of dynamical systems theory. We show that, first, PC is Lyapunov stable under mild assumptions on its loss and residual energy functions, which implies intrinsic robustness to small random perturbations due to its well-defined energy-minimi"},"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":"2410.04708","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T02:57:26Z","cross_cats_sorted":["cs.AI","cs.NE","math.OC","stat.ML"],"title_canon_sha256":"21c14822f521c59236d5cbed189022b32109ea2be93b3ce87e2d5a655e0b639c","abstract_canon_sha256":"c4dea1ee3f5e2bfbf9cbf6981b8d375031d499ef34b305a2bf5814515f439174"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:54.978344Z","signature_b64":"QXROSeY2cU5AC8lOC6c41iBUfieXZF6Gz8PEGJlZo0AV2wty6Ul8OkwrKsaRmf2iIREBYg/bGiVgMGWWKwE8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13e25c8c7f5ae9a8005f4f07fad97b598010b5a26e818411160a6082ef38655d","last_reissued_at":"2026-07-05T09:16:54.977867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:54.977867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tight Stability, Convergence, and Robustness Bounds for Predictive Coding Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Ororbia, Ankur Mali, Tommaso Salvatori","submitted_at":"2024-10-07T02:57:26Z","abstract_excerpt":"Energy-based learning algorithms, such as predictive coding (PC), have garnered significant attention in the machine learning community due to their theoretical properties, such as local operations and biologically plausible mechanisms for error correction. In this work, we rigorously analyze the stability, robustness, and convergence of PC through the lens of dynamical systems theory. We show that, first, PC is Lyapunov stable under mild assumptions on its loss and residual energy functions, which implies intrinsic robustness to small random perturbations due to its well-defined energy-minimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04708","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/2410.04708/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":"2410.04708","created_at":"2026-07-05T09:16:54.977917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04708v1","created_at":"2026-07-05T09:16:54.977917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04708","created_at":"2026-07-05T09:16:54.977917+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPRFZDD7LLU2","created_at":"2026-07-05T09:16:54.977917+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPRFZDD7LLU2QAC7","created_at":"2026-07-05T09:16:54.977917+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPRFZDD7","created_at":"2026-07-05T09:16:54.977917+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":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPRFZDD7LLU2QAC7J4D7VWL3LG","json":"https://pith.science/pith/CPRFZDD7LLU2QAC7J4D7VWL3LG.json","graph_json":"https://pith.science/api/pith-number/CPRFZDD7LLU2QAC7J4D7VWL3LG/graph.json","events_json":"https://pith.science/api/pith-number/CPRFZDD7LLU2QAC7J4D7VWL3LG/events.json","paper":"https://pith.science/paper/CPRFZDD7"},"agent_actions":{"view_html":"https://pith.science/pith/CPRFZDD7LLU2QAC7J4D7VWL3LG","download_json":"https://pith.science/pith/CPRFZDD7LLU2QAC7J4D7VWL3LG.json","view_paper":"https://pith.science/paper/CPRFZDD7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04708&json=true","fetch_graph":"https://pith.science/api/pith-number/CPRFZDD7LLU2QAC7J4D7VWL3LG/graph.json","fetch_events":"https://pith.science/api/pith-number/CPRFZDD7LLU2QAC7J4D7VWL3LG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPRFZDD7LLU2QAC7J4D7VWL3LG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPRFZDD7LLU2QAC7J4D7VWL3LG/action/storage_attestation","attest_author":"https://pith.science/pith/CPRFZDD7LLU2QAC7J4D7VWL3LG/action/author_attestation","sign_citation":"https://pith.science/pith/CPRFZDD7LLU2QAC7J4D7VWL3LG/action/citation_signature","submit_replication":"https://pith.science/pith/CPRFZDD7LLU2QAC7J4D7VWL3LG/action/replication_record"}},"created_at":"2026-07-05T09:16:54.977917+00:00","updated_at":"2026-07-05T09:16:54.977917+00:00"}