{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IKZ6H2EGHOOT3WNJ7TTTPGLZSU","short_pith_number":"pith:IKZ6H2EG","schema_version":"1.0","canonical_sha256":"42b3e3e8863b9d3dd9a9fce7379979953ff4563bfff70e8aada32b312f63d405","source":{"kind":"arxiv","id":"2605.17537","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised Hierarchical Visual Reasoning with World Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Houqiang Li, Lin Liu, Mingxiao Feng, Wengang Zhou, Yuanfei Xu","submitted_at":"2026-05-17T16:42:42Z","abstract_excerpt":"3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning due to their vast state spaces. Effective reasoning representations are essential in such settings. While existing self-supervised visual foresight reasoning approaches often suffer from multi-step error accumulation, many recent studies resort to injecting domain-specific knowledge for more stable guidance. Our key insight is that the photorealistic fidelity of visual reasoning representations is secondary; what truly matters is providing informative, task-relevant signals. To this end, we"},"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":"2605.17537","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-17T16:42:42Z","cross_cats_sorted":[],"title_canon_sha256":"53b5ee01a56966385520e14c4f31271dbd0651193c2df640c10fd6e4f9bcb41f","abstract_canon_sha256":"e1d7c0f05bdbf1aefe95f265761d32f1d05d63fe13321cbe5cc372f036cc24c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:44.590028Z","signature_b64":"j8+sZ6mygtQKJudXjjkCjA9W46RI2pTE/5hEbp2abFc3MOFZ/N86i1FWrch7lv6vw/053kAHfQPk6Pzc2V5FBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42b3e3e8863b9d3dd9a9fce7379979953ff4563bfff70e8aada32b312f63d405","last_reissued_at":"2026-05-20T00:04:44.589232Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:44.589232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Hierarchical Visual Reasoning with World Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Houqiang Li, Lin Liu, Mingxiao Feng, Wengang Zhou, Yuanfei Xu","submitted_at":"2026-05-17T16:42:42Z","abstract_excerpt":"3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning due to their vast state spaces. Effective reasoning representations are essential in such settings. While existing self-supervised visual foresight reasoning approaches often suffer from multi-step error accumulation, many recent studies resort to injecting domain-specific knowledge for more stable guidance. Our key insight is that the photorealistic fidelity of visual reasoning representations is secondary; what truly matters is providing informative, task-relevant signals. To this end, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17537","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/2605.17537/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.615516Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.552329Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9a61b20a8380963d777ebca92247b8d5c7eb1ca3df9f1ad64c744b8f706a6f7f"},"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":"2605.17537","created_at":"2026-05-20T00:04:44.589374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17537v1","created_at":"2026-05-20T00:04:44.589374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17537","created_at":"2026-05-20T00:04:44.589374+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKZ6H2EGHOOT","created_at":"2026-05-20T00:04:44.589374+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKZ6H2EGHOOT3WNJ","created_at":"2026-05-20T00:04:44.589374+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKZ6H2EG","created_at":"2026-05-20T00:04:44.589374+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/IKZ6H2EGHOOT3WNJ7TTTPGLZSU","json":"https://pith.science/pith/IKZ6H2EGHOOT3WNJ7TTTPGLZSU.json","graph_json":"https://pith.science/api/pith-number/IKZ6H2EGHOOT3WNJ7TTTPGLZSU/graph.json","events_json":"https://pith.science/api/pith-number/IKZ6H2EGHOOT3WNJ7TTTPGLZSU/events.json","paper":"https://pith.science/paper/IKZ6H2EG"},"agent_actions":{"view_html":"https://pith.science/pith/IKZ6H2EGHOOT3WNJ7TTTPGLZSU","download_json":"https://pith.science/pith/IKZ6H2EGHOOT3WNJ7TTTPGLZSU.json","view_paper":"https://pith.science/paper/IKZ6H2EG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17537&json=true","fetch_graph":"https://pith.science/api/pith-number/IKZ6H2EGHOOT3WNJ7TTTPGLZSU/graph.json","fetch_events":"https://pith.science/api/pith-number/IKZ6H2EGHOOT3WNJ7TTTPGLZSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKZ6H2EGHOOT3WNJ7TTTPGLZSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKZ6H2EGHOOT3WNJ7TTTPGLZSU/action/storage_attestation","attest_author":"https://pith.science/pith/IKZ6H2EGHOOT3WNJ7TTTPGLZSU/action/author_attestation","sign_citation":"https://pith.science/pith/IKZ6H2EGHOOT3WNJ7TTTPGLZSU/action/citation_signature","submit_replication":"https://pith.science/pith/IKZ6H2EGHOOT3WNJ7TTTPGLZSU/action/replication_record"}},"created_at":"2026-05-20T00:04:44.589374+00:00","updated_at":"2026-05-20T00:04:44.589374+00:00"}