{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q2CXHBGXUTZWAUC2JEIWGILOMR","short_pith_number":"pith:Q2CXHBGX","schema_version":"1.0","canonical_sha256":"86857384d7a4f360505a491163216e64725417b3212fc5e42f43b66453d3acfb","source":{"kind":"arxiv","id":"2408.05834","version":2},"attestation_state":"computed","paper":{"title":"Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.NC"],"primary_cat":"stat.ML","authors_text":"Eli Sennesh, Hao Wu, Tommaso Salvatori","submitted_at":"2024-08-11T17:29:03Z","abstract_excerpt":"Unexpected stimuli induce \"error\" or \"surprise\" signals in the brain. The theory of predictive coding promises to explain these observations in terms of Bayesian inference by suggesting that the cortex implements variational inference in a probabilistic graphical model. However, when applied to machine learning tasks, this family of algorithms has yet to perform on par with other variational approaches in high-dimensional, structured inference problems. To address this, we introduce a novel predictive coding algorithm for structured generative models, that we call divide-and-conquer predictive"},"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":"2408.05834","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-11T17:29:03Z","cross_cats_sorted":["cs.AI","cs.LG","q-bio.NC"],"title_canon_sha256":"0674f1d667f2d4370d71e45380b950041d4c841da129dd1f37d537f14d686047","abstract_canon_sha256":"04f0ff686eb7b120653916a520c9bd9d99c2a7ce39c757c3d3eb57af8c9c634d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:47.710844Z","signature_b64":"0sG66L+Vd27P16bexR0NSz7+xp+f8bxpIBJA1ZX4uyx8JU1Qouq4521YXvTbzGLUEklIEoHkjJlP9UVJzeuwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86857384d7a4f360505a491163216e64725417b3212fc5e42f43b66453d3acfb","last_reissued_at":"2026-07-05T09:21:47.710147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:47.710147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.NC"],"primary_cat":"stat.ML","authors_text":"Eli Sennesh, Hao Wu, Tommaso Salvatori","submitted_at":"2024-08-11T17:29:03Z","abstract_excerpt":"Unexpected stimuli induce \"error\" or \"surprise\" signals in the brain. The theory of predictive coding promises to explain these observations in terms of Bayesian inference by suggesting that the cortex implements variational inference in a probabilistic graphical model. However, when applied to machine learning tasks, this family of algorithms has yet to perform on par with other variational approaches in high-dimensional, structured inference problems. To address this, we introduce a novel predictive coding algorithm for structured generative models, that we call divide-and-conquer predictive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05834","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/2408.05834/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":"2408.05834","created_at":"2026-07-05T09:21:47.710333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05834v2","created_at":"2026-07-05T09:21:47.710333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05834","created_at":"2026-07-05T09:21:47.710333+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2CXHBGXUTZW","created_at":"2026-07-05T09:21:47.710333+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2CXHBGXUTZWAUC2","created_at":"2026-07-05T09:21:47.710333+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2CXHBGX","created_at":"2026-07-05T09:21:47.710333+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/Q2CXHBGXUTZWAUC2JEIWGILOMR","json":"https://pith.science/pith/Q2CXHBGXUTZWAUC2JEIWGILOMR.json","graph_json":"https://pith.science/api/pith-number/Q2CXHBGXUTZWAUC2JEIWGILOMR/graph.json","events_json":"https://pith.science/api/pith-number/Q2CXHBGXUTZWAUC2JEIWGILOMR/events.json","paper":"https://pith.science/paper/Q2CXHBGX"},"agent_actions":{"view_html":"https://pith.science/pith/Q2CXHBGXUTZWAUC2JEIWGILOMR","download_json":"https://pith.science/pith/Q2CXHBGXUTZWAUC2JEIWGILOMR.json","view_paper":"https://pith.science/paper/Q2CXHBGX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05834&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2CXHBGXUTZWAUC2JEIWGILOMR/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2CXHBGXUTZWAUC2JEIWGILOMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2CXHBGXUTZWAUC2JEIWGILOMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2CXHBGXUTZWAUC2JEIWGILOMR/action/storage_attestation","attest_author":"https://pith.science/pith/Q2CXHBGXUTZWAUC2JEIWGILOMR/action/author_attestation","sign_citation":"https://pith.science/pith/Q2CXHBGXUTZWAUC2JEIWGILOMR/action/citation_signature","submit_replication":"https://pith.science/pith/Q2CXHBGXUTZWAUC2JEIWGILOMR/action/replication_record"}},"created_at":"2026-07-05T09:21:47.710333+00:00","updated_at":"2026-07-05T09:21:47.710333+00:00"}