{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P2JIFRQ7SZOGPAYNJ2W2275TYY","short_pith_number":"pith:P2JIFRQ7","schema_version":"1.0","canonical_sha256":"7e9282c61f965c67830d4eadad7fb3c6202df84fe2ea45e82e4972c4791fa07b","source":{"kind":"arxiv","id":"2505.20137","version":5},"attestation_state":"computed","paper":{"title":"ePC: Fast and Deep Predictive Coding in Digital Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"C\\'edric Goemaere, Gaspard Oliviers, Rafal Bogacz, Thomas Demeester","submitted_at":"2025-05-26T15:39:16Z","abstract_excerpt":"Predictive Coding (PC) offers a brain-inspired alternative to backpropagation for neural network training, described as a physical system minimizing its internal energy. However, in practice, PC is predominantly digitally simulated, requiring excessive amounts of compute while struggling to scale to deeper architectures. This paper reformulates PC to overcome this hardware-algorithm mismatch. First, we uncover how the canonical state-based formulation of PC (sPC) is, by design, deeply inefficient in digital simulation, inevitably resulting in exponential signal decay that stalls the entire min"},"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":"2505.20137","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T15:39:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f3d1012eeae4f11fc9a7b23f258c09ed83f31695559acc095be1da0dddccd44","abstract_canon_sha256":"55140c1579f1d140ac4c3801eecf50f29f12da82c7073ca4a30fad4f0f77b6b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:04.131425Z","signature_b64":"knoPYB755OPnLtgbySRy0jHqgCIDN82dGXnyoORIMdtHZNaLsuPZLaC1Yr30WrSUvy9dyE/fcT2FcjP3U1KrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e9282c61f965c67830d4eadad7fb3c6202df84fe2ea45e82e4972c4791fa07b","last_reissued_at":"2026-06-09T02:07:04.130400Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:04.130400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ePC: Fast and Deep Predictive Coding in Digital Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"C\\'edric Goemaere, Gaspard Oliviers, Rafal Bogacz, Thomas Demeester","submitted_at":"2025-05-26T15:39:16Z","abstract_excerpt":"Predictive Coding (PC) offers a brain-inspired alternative to backpropagation for neural network training, described as a physical system minimizing its internal energy. However, in practice, PC is predominantly digitally simulated, requiring excessive amounts of compute while struggling to scale to deeper architectures. This paper reformulates PC to overcome this hardware-algorithm mismatch. First, we uncover how the canonical state-based formulation of PC (sPC) is, by design, deeply inefficient in digital simulation, inevitably resulting in exponential signal decay that stalls the entire min"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20137","kind":"arxiv","version":5},"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/2505.20137/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":"2505.20137","created_at":"2026-06-09T02:07:04.130533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20137v5","created_at":"2026-06-09T02:07:04.130533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20137","created_at":"2026-06-09T02:07:04.130533+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2JIFRQ7SZOG","created_at":"2026-06-09T02:07:04.130533+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2JIFRQ7SZOGPAYN","created_at":"2026-06-09T02:07:04.130533+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2JIFRQ7","created_at":"2026-06-09T02:07:04.130533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.20293","citing_title":"Closed-form predictive coding via hierarchical Gaussian filters","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11911","citing_title":"Understanding Sample Efficiency in Predictive Coding","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21286","citing_title":"Cross-Entropy Is Load-Bearing: A Pre-Registered Scope Test of the K-Way Energy Probe on Bidirectional Predictive Coding","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2JIFRQ7SZOGPAYNJ2W2275TYY","json":"https://pith.science/pith/P2JIFRQ7SZOGPAYNJ2W2275TYY.json","graph_json":"https://pith.science/api/pith-number/P2JIFRQ7SZOGPAYNJ2W2275TYY/graph.json","events_json":"https://pith.science/api/pith-number/P2JIFRQ7SZOGPAYNJ2W2275TYY/events.json","paper":"https://pith.science/paper/P2JIFRQ7"},"agent_actions":{"view_html":"https://pith.science/pith/P2JIFRQ7SZOGPAYNJ2W2275TYY","download_json":"https://pith.science/pith/P2JIFRQ7SZOGPAYNJ2W2275TYY.json","view_paper":"https://pith.science/paper/P2JIFRQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20137&json=true","fetch_graph":"https://pith.science/api/pith-number/P2JIFRQ7SZOGPAYNJ2W2275TYY/graph.json","fetch_events":"https://pith.science/api/pith-number/P2JIFRQ7SZOGPAYNJ2W2275TYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2JIFRQ7SZOGPAYNJ2W2275TYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2JIFRQ7SZOGPAYNJ2W2275TYY/action/storage_attestation","attest_author":"https://pith.science/pith/P2JIFRQ7SZOGPAYNJ2W2275TYY/action/author_attestation","sign_citation":"https://pith.science/pith/P2JIFRQ7SZOGPAYNJ2W2275TYY/action/citation_signature","submit_replication":"https://pith.science/pith/P2JIFRQ7SZOGPAYNJ2W2275TYY/action/replication_record"}},"created_at":"2026-06-09T02:07:04.130533+00:00","updated_at":"2026-06-09T02:07:04.130533+00:00"}