{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VFYMBYO6IT7APQQ3ENZDM24W3J","short_pith_number":"pith:VFYMBYO6","schema_version":"1.0","canonical_sha256":"a970c0e1de44fe07c21b2372366b96da6217d35a1a866990c58154e8fadedfc8","source":{"kind":"arxiv","id":"2501.18299","version":1},"attestation_state":"computed","paper":{"title":"Model-Free RL Agents Demonstrate System 1-Like Intentionality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hal Ashton, Matija Franklin","submitted_at":"2025-01-30T12:21:50Z","abstract_excerpt":"This paper argues that model-free reinforcement learning (RL) agents, while lacking explicit planning mechanisms, exhibit behaviours that can be analogised to System 1 (\"thinking fast\") processes in human cognition. Unlike model-based RL agents, which operate akin to System 2 (\"thinking slow\") reasoning by leveraging internal representations for planning, model-free agents react to environmental stimuli without anticipatory modelling. We propose a novel framework linking the dichotomy of System 1 and System 2 to the distinction between model-free and model-based RL. This framing challenges the"},"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":"2501.18299","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-30T12:21:50Z","cross_cats_sorted":[],"title_canon_sha256":"a538068f0fe6a4267e7adb428c75a49c598b3f0269e12f5fc4b752a692459316","abstract_canon_sha256":"17be79727353a700fff979e911a49eb652eeeaf736e416cbad7a9bcff0d6be48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:32.340364Z","signature_b64":"je8VUdKN3aFo2nAGvXWW5nkfP1CruxMos4GRVmWaw7ARn+6Ir3iW8p169lZ+vvOHp1Pc/QwP/OZV7+0MYvJmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a970c0e1de44fe07c21b2372366b96da6217d35a1a866990c58154e8fadedfc8","last_reissued_at":"2026-07-05T10:07:32.339946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:32.339946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Free RL Agents Demonstrate System 1-Like Intentionality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hal Ashton, Matija Franklin","submitted_at":"2025-01-30T12:21:50Z","abstract_excerpt":"This paper argues that model-free reinforcement learning (RL) agents, while lacking explicit planning mechanisms, exhibit behaviours that can be analogised to System 1 (\"thinking fast\") processes in human cognition. Unlike model-based RL agents, which operate akin to System 2 (\"thinking slow\") reasoning by leveraging internal representations for planning, model-free agents react to environmental stimuli without anticipatory modelling. We propose a novel framework linking the dichotomy of System 1 and System 2 to the distinction between model-free and model-based RL. This framing challenges the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18299","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/2501.18299/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":"2501.18299","created_at":"2026-07-05T10:07:32.340005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18299v1","created_at":"2026-07-05T10:07:32.340005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18299","created_at":"2026-07-05T10:07:32.340005+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFYMBYO6IT7A","created_at":"2026-07-05T10:07:32.340005+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFYMBYO6IT7APQQ3","created_at":"2026-07-05T10:07:32.340005+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFYMBYO6","created_at":"2026-07-05T10:07:32.340005+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/VFYMBYO6IT7APQQ3ENZDM24W3J","json":"https://pith.science/pith/VFYMBYO6IT7APQQ3ENZDM24W3J.json","graph_json":"https://pith.science/api/pith-number/VFYMBYO6IT7APQQ3ENZDM24W3J/graph.json","events_json":"https://pith.science/api/pith-number/VFYMBYO6IT7APQQ3ENZDM24W3J/events.json","paper":"https://pith.science/paper/VFYMBYO6"},"agent_actions":{"view_html":"https://pith.science/pith/VFYMBYO6IT7APQQ3ENZDM24W3J","download_json":"https://pith.science/pith/VFYMBYO6IT7APQQ3ENZDM24W3J.json","view_paper":"https://pith.science/paper/VFYMBYO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18299&json=true","fetch_graph":"https://pith.science/api/pith-number/VFYMBYO6IT7APQQ3ENZDM24W3J/graph.json","fetch_events":"https://pith.science/api/pith-number/VFYMBYO6IT7APQQ3ENZDM24W3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFYMBYO6IT7APQQ3ENZDM24W3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFYMBYO6IT7APQQ3ENZDM24W3J/action/storage_attestation","attest_author":"https://pith.science/pith/VFYMBYO6IT7APQQ3ENZDM24W3J/action/author_attestation","sign_citation":"https://pith.science/pith/VFYMBYO6IT7APQQ3ENZDM24W3J/action/citation_signature","submit_replication":"https://pith.science/pith/VFYMBYO6IT7APQQ3ENZDM24W3J/action/replication_record"}},"created_at":"2026-07-05T10:07:32.340005+00:00","updated_at":"2026-07-05T10:07:32.340005+00:00"}