{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BAJPWQSRG2XN3SOP4E4GYDYCHR","short_pith_number":"pith:BAJPWQSR","schema_version":"1.0","canonical_sha256":"0812fb425136aeddc9cfe1386c0f023c4a6587f7c94ff42e544ba66d4daa2baf","source":{"kind":"arxiv","id":"2508.11836","version":2},"attestation_state":"computed","paper":{"title":"Finite Automata Extraction: Low-data World Model Learning as Programs from Gameplay Video","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anurag Sarkar, Dave Goel, Matthew Guzdial","submitted_at":"2025-08-15T23:05:37Z","abstract_excerpt":"World models are defined as a compressed spatial and temporal learned representation of an environment. The learned representation is typically a neural network, making transfer of the learned environment dynamics and explainability a challenge. In this paper, we propose an approach, Finite Automata Extraction (FAE), that learns a neuro-symbolic world model from gameplay video represented as programs in a novel domain-specific language (DSL): Retro Coder. Compared to prior world model approaches, FAE learns a more precise model of the environment and more general code than prior DSL-based appr"},"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":"2508.11836","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-15T23:05:37Z","cross_cats_sorted":[],"title_canon_sha256":"5442d80db96f8219283ee4ab4bb94bca1f5d2cf6d7b9a42be75a1ac8abc3cfa0","abstract_canon_sha256":"92f88308aec1dd75ab2f5e313877dc6c77c9edb8d77b39cc6a4922e60a0d4083"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:53.680867Z","signature_b64":"1bb3R1npd6aAl8iH4iYCqykTwfZloh2w2c63vpy3zIXtD983k+vjyeeEI2VGv1OJRlPrE+8Su1cm6URPP3seBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0812fb425136aeddc9cfe1386c0f023c4a6587f7c94ff42e544ba66d4daa2baf","last_reissued_at":"2026-05-22T01:04:53.680251Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:53.680251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite Automata Extraction: Low-data World Model Learning as Programs from Gameplay Video","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anurag Sarkar, Dave Goel, Matthew Guzdial","submitted_at":"2025-08-15T23:05:37Z","abstract_excerpt":"World models are defined as a compressed spatial and temporal learned representation of an environment. The learned representation is typically a neural network, making transfer of the learned environment dynamics and explainability a challenge. In this paper, we propose an approach, Finite Automata Extraction (FAE), that learns a neuro-symbolic world model from gameplay video represented as programs in a novel domain-specific language (DSL): Retro Coder. Compared to prior world model approaches, FAE learns a more precise model of the environment and more general code than prior DSL-based appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11836","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/2508.11836/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":"2508.11836","created_at":"2026-05-22T01:04:53.680328+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11836v2","created_at":"2026-05-22T01:04:53.680328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11836","created_at":"2026-05-22T01:04:53.680328+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAJPWQSRG2XN","created_at":"2026-05-22T01:04:53.680328+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAJPWQSRG2XN3SOP","created_at":"2026-05-22T01:04:53.680328+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAJPWQSR","created_at":"2026-05-22T01:04:53.680328+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/BAJPWQSRG2XN3SOP4E4GYDYCHR","json":"https://pith.science/pith/BAJPWQSRG2XN3SOP4E4GYDYCHR.json","graph_json":"https://pith.science/api/pith-number/BAJPWQSRG2XN3SOP4E4GYDYCHR/graph.json","events_json":"https://pith.science/api/pith-number/BAJPWQSRG2XN3SOP4E4GYDYCHR/events.json","paper":"https://pith.science/paper/BAJPWQSR"},"agent_actions":{"view_html":"https://pith.science/pith/BAJPWQSRG2XN3SOP4E4GYDYCHR","download_json":"https://pith.science/pith/BAJPWQSRG2XN3SOP4E4GYDYCHR.json","view_paper":"https://pith.science/paper/BAJPWQSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11836&json=true","fetch_graph":"https://pith.science/api/pith-number/BAJPWQSRG2XN3SOP4E4GYDYCHR/graph.json","fetch_events":"https://pith.science/api/pith-number/BAJPWQSRG2XN3SOP4E4GYDYCHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAJPWQSRG2XN3SOP4E4GYDYCHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAJPWQSRG2XN3SOP4E4GYDYCHR/action/storage_attestation","attest_author":"https://pith.science/pith/BAJPWQSRG2XN3SOP4E4GYDYCHR/action/author_attestation","sign_citation":"https://pith.science/pith/BAJPWQSRG2XN3SOP4E4GYDYCHR/action/citation_signature","submit_replication":"https://pith.science/pith/BAJPWQSRG2XN3SOP4E4GYDYCHR/action/replication_record"}},"created_at":"2026-05-22T01:04:53.680328+00:00","updated_at":"2026-05-22T01:04:53.680328+00:00"}