{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ISKSGUX6EMPZZNTFX5ZBJZXS27","short_pith_number":"pith:ISKSGUX6","schema_version":"1.0","canonical_sha256":"44952352fe231f9cb665bf7214e6f2d7e7f2dd4a8048be3d51584e4ca4ced77a","source":{"kind":"arxiv","id":"2006.04176","version":2},"attestation_state":"computed","paper":{"title":"Deep active inference agents using Monte-Carlo methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"q-bio.NC","authors_text":"Karl Friston, Noor Sajid, Pedro A.M. Mediano, Zafeirios Fountas","submitted_at":"2020-06-07T15:10:42Z","abstract_excerpt":"Active inference is a Bayesian framework for understanding biological intelligence. The underlying theory brings together perception and action under one single imperative: minimizing free energy. However, despite its theoretical utility in explaining intelligence, computational implementations have been restricted to low-dimensional and idealized situations. In this paper, we present a neural architecture for building deep active inference agents operating in complex, continuous state-spaces using multiple forms of Monte-Carlo (MC) sampling. For this, we introduce a number of techniques, nove"},"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":"2006.04176","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2020-06-07T15:10:42Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ebb7ae98dcd54f44b63a29188306a3f2747abf636b73557272fecfe4a4a42868","abstract_canon_sha256":"48235085d835ecdcee75d74f31a1b2dae471abe05416a4904f7ed64c8ae294fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:03.955393Z","signature_b64":"FDcGpuNX6CG9eluSZdrESZtrg0BZSfB0AdDCFStFYSnRn2mc1x19ZB6BB4TQ+exozpTn/30x4Ic3ecy69R5gAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44952352fe231f9cb665bf7214e6f2d7e7f2dd4a8048be3d51584e4ca4ced77a","last_reissued_at":"2026-07-05T01:45:03.954901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:03.954901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep active inference agents using Monte-Carlo methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"q-bio.NC","authors_text":"Karl Friston, Noor Sajid, Pedro A.M. Mediano, Zafeirios Fountas","submitted_at":"2020-06-07T15:10:42Z","abstract_excerpt":"Active inference is a Bayesian framework for understanding biological intelligence. The underlying theory brings together perception and action under one single imperative: minimizing free energy. However, despite its theoretical utility in explaining intelligence, computational implementations have been restricted to low-dimensional and idealized situations. In this paper, we present a neural architecture for building deep active inference agents operating in complex, continuous state-spaces using multiple forms of Monte-Carlo (MC) sampling. For this, we introduce a number of techniques, nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04176","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/2006.04176/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":"2006.04176","created_at":"2026-07-05T01:45:03.954960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04176v2","created_at":"2026-07-05T01:45:03.954960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04176","created_at":"2026-07-05T01:45:03.954960+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISKSGUX6EMPZ","created_at":"2026-07-05T01:45:03.954960+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISKSGUX6EMPZZNTF","created_at":"2026-07-05T01:45:03.954960+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISKSGUX6","created_at":"2026-07-05T01:45:03.954960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00604","citing_title":"Affinity Is Not Enough: Recovering the Free Energy Principle in Mixture-of-Experts","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ISKSGUX6EMPZZNTFX5ZBJZXS27","json":"https://pith.science/pith/ISKSGUX6EMPZZNTFX5ZBJZXS27.json","graph_json":"https://pith.science/api/pith-number/ISKSGUX6EMPZZNTFX5ZBJZXS27/graph.json","events_json":"https://pith.science/api/pith-number/ISKSGUX6EMPZZNTFX5ZBJZXS27/events.json","paper":"https://pith.science/paper/ISKSGUX6"},"agent_actions":{"view_html":"https://pith.science/pith/ISKSGUX6EMPZZNTFX5ZBJZXS27","download_json":"https://pith.science/pith/ISKSGUX6EMPZZNTFX5ZBJZXS27.json","view_paper":"https://pith.science/paper/ISKSGUX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04176&json=true","fetch_graph":"https://pith.science/api/pith-number/ISKSGUX6EMPZZNTFX5ZBJZXS27/graph.json","fetch_events":"https://pith.science/api/pith-number/ISKSGUX6EMPZZNTFX5ZBJZXS27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISKSGUX6EMPZZNTFX5ZBJZXS27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISKSGUX6EMPZZNTFX5ZBJZXS27/action/storage_attestation","attest_author":"https://pith.science/pith/ISKSGUX6EMPZZNTFX5ZBJZXS27/action/author_attestation","sign_citation":"https://pith.science/pith/ISKSGUX6EMPZZNTFX5ZBJZXS27/action/citation_signature","submit_replication":"https://pith.science/pith/ISKSGUX6EMPZZNTFX5ZBJZXS27/action/replication_record"}},"created_at":"2026-07-05T01:45:03.954960+00:00","updated_at":"2026-07-05T01:45:03.954960+00:00"}