{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YGAWO7HNKIFFSZFRDIHAD7ZC6O","short_pith_number":"pith:YGAWO7HN","schema_version":"1.0","canonical_sha256":"c181677ced520a5964b11a0e01ff22f383929a5c6c100baec1cccdfc8593c724","source":{"kind":"arxiv","id":"2306.06561","version":2},"attestation_state":"computed","paper":{"title":"Learning World Models with Identifiable Factorization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Biwei Huang, Honglong Tian, Kun Zhang, Mingming Gong, Yang Yu, Yu-Ren Liu, Zhengmao Zhu","submitted_at":"2023-06-11T02:25:15Z","abstract_excerpt":"Extracting a stable and compact representation of the environment is crucial for efficient reinforcement learning in high-dimensional, noisy, and non-stationary environments. Different categories of information coexist in such environments -- how to effectively extract and disentangle these information remains a challenging problem. In this paper, we propose IFactor, a general framework to model four distinct categories of latent state variables that capture various aspects of information within the RL system, based on their interactions with actions and rewards. Our analysis establishes block"},"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":"2306.06561","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-11T02:25:15Z","cross_cats_sorted":[],"title_canon_sha256":"f02947bd57340e1b373a08477849903966c5e4994c756fae5e66092c6181ba70","abstract_canon_sha256":"aad0427709b1303f88b3f763787c03d992bd209140ffdeeab47d7fd2228ab722"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:50.657428Z","signature_b64":"9kaaB26GXvdPbyCkl/mWSya7US3gjWA3FwhTe9vzNEin9ntAJ7LfDtQWe5fcFLNkntPXgQIa84i5tPpaOXFgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c181677ced520a5964b11a0e01ff22f383929a5c6c100baec1cccdfc8593c724","last_reissued_at":"2026-07-05T06:24:50.656907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:50.656907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning World Models with Identifiable Factorization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Biwei Huang, Honglong Tian, Kun Zhang, Mingming Gong, Yang Yu, Yu-Ren Liu, Zhengmao Zhu","submitted_at":"2023-06-11T02:25:15Z","abstract_excerpt":"Extracting a stable and compact representation of the environment is crucial for efficient reinforcement learning in high-dimensional, noisy, and non-stationary environments. Different categories of information coexist in such environments -- how to effectively extract and disentangle these information remains a challenging problem. In this paper, we propose IFactor, a general framework to model four distinct categories of latent state variables that capture various aspects of information within the RL system, based on their interactions with actions and rewards. Our analysis establishes block"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06561","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/2306.06561/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":"2306.06561","created_at":"2026-07-05T06:24:50.656970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06561v2","created_at":"2026-07-05T06:24:50.656970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06561","created_at":"2026-07-05T06:24:50.656970+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGAWO7HNKIFF","created_at":"2026-07-05T06:24:50.656970+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGAWO7HNKIFFSZFR","created_at":"2026-07-05T06:24:50.656970+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGAWO7HN","created_at":"2026-07-05T06:24:50.656970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27681","citing_title":"Textual Belief States for World Models: Identifiable Representation Learning Under Strict Mediation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30542","citing_title":"Physically Viable World Models: A Case for Query-Conditioned Embodied AI","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGAWO7HNKIFFSZFRDIHAD7ZC6O","json":"https://pith.science/pith/YGAWO7HNKIFFSZFRDIHAD7ZC6O.json","graph_json":"https://pith.science/api/pith-number/YGAWO7HNKIFFSZFRDIHAD7ZC6O/graph.json","events_json":"https://pith.science/api/pith-number/YGAWO7HNKIFFSZFRDIHAD7ZC6O/events.json","paper":"https://pith.science/paper/YGAWO7HN"},"agent_actions":{"view_html":"https://pith.science/pith/YGAWO7HNKIFFSZFRDIHAD7ZC6O","download_json":"https://pith.science/pith/YGAWO7HNKIFFSZFRDIHAD7ZC6O.json","view_paper":"https://pith.science/paper/YGAWO7HN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06561&json=true","fetch_graph":"https://pith.science/api/pith-number/YGAWO7HNKIFFSZFRDIHAD7ZC6O/graph.json","fetch_events":"https://pith.science/api/pith-number/YGAWO7HNKIFFSZFRDIHAD7ZC6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGAWO7HNKIFFSZFRDIHAD7ZC6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGAWO7HNKIFFSZFRDIHAD7ZC6O/action/storage_attestation","attest_author":"https://pith.science/pith/YGAWO7HNKIFFSZFRDIHAD7ZC6O/action/author_attestation","sign_citation":"https://pith.science/pith/YGAWO7HNKIFFSZFRDIHAD7ZC6O/action/citation_signature","submit_replication":"https://pith.science/pith/YGAWO7HNKIFFSZFRDIHAD7ZC6O/action/replication_record"}},"created_at":"2026-07-05T06:24:50.656970+00:00","updated_at":"2026-07-05T06:24:50.656970+00:00"}