{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V33JQVPXIRQ6E7PWTICT3E2D7Y","short_pith_number":"pith:V33JQVPX","schema_version":"1.0","canonical_sha256":"aef69855f74461e27df69a053d9343fe2e110fa0f87674c8666a98742005aa33","source":{"kind":"arxiv","id":"2606.21775","version":1},"attestation_state":"computed","paper":{"title":"Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Qi Zhang, Tianqi Du, Yifei Wang, Yisen Wang","submitted_at":"2026-06-19T21:50:15Z","abstract_excerpt":"Recently, world models have emerged as a promising paradigm for building intelligent agents by learning predictive models that estimate future environment states conditioned on observations and actions. In particular, JEPA-style latent world models provide an efficient alternative to pixel space prediction by learning action-conditioned dynamics in compact representation spaces. However, existing latent world models typically rely on one-step prediction and must be recursively rolled out for long-horizon planning, which leads to compounding errors and a mismatch between training objectives and"},"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":"2606.21775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T21:50:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d1da8f4a7940982c84b0373689d4d59b18921bbbe68c4a99cf58e1444cac3dd","abstract_canon_sha256":"413c69b2a5bbad77b36cdd306f30a6f6b232665febf1c6260bf018a64e7879af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:22.211431Z","signature_b64":"1/8ZZVn3SwmsBFeR4pA8SNBjpGEG5tlHFILuagY6lO+X+fQKvunGQOh4PEY8ua3CwIKBgoXg+e8dZBTTLTxQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aef69855f74461e27df69a053d9343fe2e110fa0f87674c8666a98742005aa33","last_reissued_at":"2026-06-23T01:13:22.210930Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:22.210930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Qi Zhang, Tianqi Du, Yifei Wang, Yisen Wang","submitted_at":"2026-06-19T21:50:15Z","abstract_excerpt":"Recently, world models have emerged as a promising paradigm for building intelligent agents by learning predictive models that estimate future environment states conditioned on observations and actions. In particular, JEPA-style latent world models provide an efficient alternative to pixel space prediction by learning action-conditioned dynamics in compact representation spaces. However, existing latent world models typically rely on one-step prediction and must be recursively rolled out for long-horizon planning, which leads to compounding errors and a mismatch between training objectives and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21775","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/2606.21775/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":"2606.21775","created_at":"2026-06-23T01:13:22.211003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21775v1","created_at":"2026-06-23T01:13:22.211003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21775","created_at":"2026-06-23T01:13:22.211003+00:00"},{"alias_kind":"pith_short_12","alias_value":"V33JQVPXIRQ6","created_at":"2026-06-23T01:13:22.211003+00:00"},{"alias_kind":"pith_short_16","alias_value":"V33JQVPXIRQ6E7PW","created_at":"2026-06-23T01:13:22.211003+00:00"},{"alias_kind":"pith_short_8","alias_value":"V33JQVPX","created_at":"2026-06-23T01:13:22.211003+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/V33JQVPXIRQ6E7PWTICT3E2D7Y","json":"https://pith.science/pith/V33JQVPXIRQ6E7PWTICT3E2D7Y.json","graph_json":"https://pith.science/api/pith-number/V33JQVPXIRQ6E7PWTICT3E2D7Y/graph.json","events_json":"https://pith.science/api/pith-number/V33JQVPXIRQ6E7PWTICT3E2D7Y/events.json","paper":"https://pith.science/paper/V33JQVPX"},"agent_actions":{"view_html":"https://pith.science/pith/V33JQVPXIRQ6E7PWTICT3E2D7Y","download_json":"https://pith.science/pith/V33JQVPXIRQ6E7PWTICT3E2D7Y.json","view_paper":"https://pith.science/paper/V33JQVPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21775&json=true","fetch_graph":"https://pith.science/api/pith-number/V33JQVPXIRQ6E7PWTICT3E2D7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/V33JQVPXIRQ6E7PWTICT3E2D7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V33JQVPXIRQ6E7PWTICT3E2D7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V33JQVPXIRQ6E7PWTICT3E2D7Y/action/storage_attestation","attest_author":"https://pith.science/pith/V33JQVPXIRQ6E7PWTICT3E2D7Y/action/author_attestation","sign_citation":"https://pith.science/pith/V33JQVPXIRQ6E7PWTICT3E2D7Y/action/citation_signature","submit_replication":"https://pith.science/pith/V33JQVPXIRQ6E7PWTICT3E2D7Y/action/replication_record"}},"created_at":"2026-06-23T01:13:22.211003+00:00","updated_at":"2026-06-23T01:13:22.211003+00:00"}