{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C3JM7Z2KICNSPBPTUDNM2IFF6N","short_pith_number":"pith:C3JM7Z2K","schema_version":"1.0","canonical_sha256":"16d2cfe74a409b2785f3a0dacd20a5f362715eb9f5479791c2371d51822ce005","source":{"kind":"arxiv","id":"2603.29452","version":3},"attestation_state":"computed","paper":{"title":"CReF: Cross-modal and Recurrent Fusion for Depth-conditioned Humanoid Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guoteng Zhang, Jun Wu, Qiuguo Zhu, Ruiqi Yu, Shixin Luo, Yuan Hao","submitted_at":"2026-03-31T08:56:29Z","abstract_excerpt":"Stable traversal over geometrically complex terrain increasingly requires exteroceptive perception, yet prior perceptive humanoid locomotion methods often remain tied to explicit geometric abstractions, either by mediating control through robot-centric 2.5D terrain representations or by shaping depth learning with auxiliary geometry-related targets. While effective, these approaches introduce additional map-construction procedures or multi-stage skill-transfer processes beyond direct depth-to-control learning. We propose CReF (Cross-modal and Recurrent Fusion), a single-stage depth-conditioned"},"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":"2603.29452","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-03-31T08:56:29Z","cross_cats_sorted":[],"title_canon_sha256":"2a13473a93b8b8837ea3826951504b52cd648030c1bb7ebabfe8f99f79676ef1","abstract_canon_sha256":"e35d9e7a0ce0f2defdd16319d6435281e748bd346cc68a1601e8372040dac46a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:23:29.400437Z","signature_b64":"YVQKFuAHNkhbyStVGgVKHC2EPd93iqlYKX9RhUMaSqbGn5WZ+NvUAtslfLFqGnvPlUqekNaKBZRFryHL7dckBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16d2cfe74a409b2785f3a0dacd20a5f362715eb9f5479791c2371d51822ce005","last_reissued_at":"2026-07-28T02:23:29.399445Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:23:29.399445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CReF: Cross-modal and Recurrent Fusion for Depth-conditioned Humanoid Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guoteng Zhang, Jun Wu, Qiuguo Zhu, Ruiqi Yu, Shixin Luo, Yuan Hao","submitted_at":"2026-03-31T08:56:29Z","abstract_excerpt":"Stable traversal over geometrically complex terrain increasingly requires exteroceptive perception, yet prior perceptive humanoid locomotion methods often remain tied to explicit geometric abstractions, either by mediating control through robot-centric 2.5D terrain representations or by shaping depth learning with auxiliary geometry-related targets. While effective, these approaches introduce additional map-construction procedures or multi-stage skill-transfer processes beyond direct depth-to-control learning. We propose CReF (Cross-modal and Recurrent Fusion), a single-stage depth-conditioned"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.29452","kind":"arxiv","version":3},"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/2603.29452/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":"2603.29452","created_at":"2026-07-28T02:23:29.399913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.29452v3","created_at":"2026-07-28T02:23:29.399913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29452","created_at":"2026-07-28T02:23:29.399913+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3JM7Z2KICNS","created_at":"2026-07-28T02:23:29.399913+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3JM7Z2KICNSPBPT","created_at":"2026-07-28T02:23:29.399913+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3JM7Z2K","created_at":"2026-07-28T02:23:29.399913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.05880","citing_title":"TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C3JM7Z2KICNSPBPTUDNM2IFF6N","json":"https://pith.science/pith/C3JM7Z2KICNSPBPTUDNM2IFF6N.json","graph_json":"https://pith.science/api/pith-number/C3JM7Z2KICNSPBPTUDNM2IFF6N/graph.json","events_json":"https://pith.science/api/pith-number/C3JM7Z2KICNSPBPTUDNM2IFF6N/events.json","paper":"https://pith.science/paper/C3JM7Z2K"},"agent_actions":{"view_html":"https://pith.science/pith/C3JM7Z2KICNSPBPTUDNM2IFF6N","download_json":"https://pith.science/pith/C3JM7Z2KICNSPBPTUDNM2IFF6N.json","view_paper":"https://pith.science/paper/C3JM7Z2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.29452&json=true","fetch_graph":"https://pith.science/api/pith-number/C3JM7Z2KICNSPBPTUDNM2IFF6N/graph.json","fetch_events":"https://pith.science/api/pith-number/C3JM7Z2KICNSPBPTUDNM2IFF6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3JM7Z2KICNSPBPTUDNM2IFF6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3JM7Z2KICNSPBPTUDNM2IFF6N/action/storage_attestation","attest_author":"https://pith.science/pith/C3JM7Z2KICNSPBPTUDNM2IFF6N/action/author_attestation","sign_citation":"https://pith.science/pith/C3JM7Z2KICNSPBPTUDNM2IFF6N/action/citation_signature","submit_replication":"https://pith.science/pith/C3JM7Z2KICNSPBPTUDNM2IFF6N/action/replication_record"}},"created_at":"2026-07-28T02:23:29.399913+00:00","updated_at":"2026-07-28T02:23:29.399913+00:00"}