{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WRMBMVRZDSAO4BVRWEA6KM4F55","short_pith_number":"pith:WRMBMVRZ","schema_version":"1.0","canonical_sha256":"b4581656391c80ee06b1b101e53385ef61f4d2424319eee1f639e6a6c73685de","source":{"kind":"arxiv","id":"2410.03174","version":2},"attestation_state":"computed","paper":{"title":"Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Kaipeng Zhang, Nanning Zheng, Ping Luo, Wenqi Shao, Yongqiang Ma","submitted_at":"2024-10-04T06:19:29Z","abstract_excerpt":"Capturing long-range dependencies while preserving high-resolution visual representations is crucial for dense prediction tasks such as human pose estimation. Vision Transformers (ViTs) have advanced global modeling through self-attention but suffer from quadratic computational complexity with respect to token count, limiting their efficiency and scalability to high-resolution inputs, especially on mobile and resource-constrained devices. State Space Models (SSMs), exemplified by Mamba, offer an efficient alternative by combining global receptive fields with linear computational complexity, en"},"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":"2410.03174","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T06:19:29Z","cross_cats_sorted":[],"title_canon_sha256":"c271e34869d1774ba3ed61ba59492527877c29c51e2f5b7c677edbb0dbfc7304","abstract_canon_sha256":"edf988c1fd9b5d7e469808d8d0cefc83a6a2eb4150b7aae8becbf71de87d8d4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:08.914229Z","signature_b64":"u0Ay08Zzyzwl5PPXxmk5+Vb1sUEzokeWkT0qXuPg+Qwll7RmWmD/GoqQmgjvzwI3gVsyuDGuYBRGpmROpU4pAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4581656391c80ee06b1b101e53385ef61f4d2424319eee1f639e6a6c73685de","last_reissued_at":"2026-07-05T11:54:08.913710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:08.913710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Kaipeng Zhang, Nanning Zheng, Ping Luo, Wenqi Shao, Yongqiang Ma","submitted_at":"2024-10-04T06:19:29Z","abstract_excerpt":"Capturing long-range dependencies while preserving high-resolution visual representations is crucial for dense prediction tasks such as human pose estimation. Vision Transformers (ViTs) have advanced global modeling through self-attention but suffer from quadratic computational complexity with respect to token count, limiting their efficiency and scalability to high-resolution inputs, especially on mobile and resource-constrained devices. State Space Models (SSMs), exemplified by Mamba, offer an efficient alternative by combining global receptive fields with linear computational complexity, en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03174","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/2410.03174/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":"2410.03174","created_at":"2026-07-05T11:54:08.913764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03174v2","created_at":"2026-07-05T11:54:08.913764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03174","created_at":"2026-07-05T11:54:08.913764+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRMBMVRZDSAO","created_at":"2026-07-05T11:54:08.913764+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRMBMVRZDSAO4BVR","created_at":"2026-07-05T11:54:08.913764+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRMBMVRZ","created_at":"2026-07-05T11:54:08.913764+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/WRMBMVRZDSAO4BVRWEA6KM4F55","json":"https://pith.science/pith/WRMBMVRZDSAO4BVRWEA6KM4F55.json","graph_json":"https://pith.science/api/pith-number/WRMBMVRZDSAO4BVRWEA6KM4F55/graph.json","events_json":"https://pith.science/api/pith-number/WRMBMVRZDSAO4BVRWEA6KM4F55/events.json","paper":"https://pith.science/paper/WRMBMVRZ"},"agent_actions":{"view_html":"https://pith.science/pith/WRMBMVRZDSAO4BVRWEA6KM4F55","download_json":"https://pith.science/pith/WRMBMVRZDSAO4BVRWEA6KM4F55.json","view_paper":"https://pith.science/paper/WRMBMVRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03174&json=true","fetch_graph":"https://pith.science/api/pith-number/WRMBMVRZDSAO4BVRWEA6KM4F55/graph.json","fetch_events":"https://pith.science/api/pith-number/WRMBMVRZDSAO4BVRWEA6KM4F55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRMBMVRZDSAO4BVRWEA6KM4F55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRMBMVRZDSAO4BVRWEA6KM4F55/action/storage_attestation","attest_author":"https://pith.science/pith/WRMBMVRZDSAO4BVRWEA6KM4F55/action/author_attestation","sign_citation":"https://pith.science/pith/WRMBMVRZDSAO4BVRWEA6KM4F55/action/citation_signature","submit_replication":"https://pith.science/pith/WRMBMVRZDSAO4BVRWEA6KM4F55/action/replication_record"}},"created_at":"2026-07-05T11:54:08.913764+00:00","updated_at":"2026-07-05T11:54:08.913764+00:00"}