{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QREYG6YZQ2USCOUBJ5NSQ7EUNW","short_pith_number":"pith:QREYG6YZ","schema_version":"1.0","canonical_sha256":"8449837b1986a9213a814f5b287c946da0f0cf50f62760ad7e1c1f2954d04800","source":{"kind":"arxiv","id":"2602.02401","version":2},"attestation_state":"computed","paper":{"title":"Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jason Li, Mengyuan Liu, Peiming Li, Songtao Wu, Xinshun Wang, Zhichao Deng, Zhongbin Fang, Ziyi Wang","submitted_at":"2026-02-02T17:59:01Z","abstract_excerpt":"Human motion analysis tasks, such as temporal 3D pose estimation, motion prediction, and motion in-betweening, play an essential role in computer vision. However, current paradigms suffer from severe fragmentation. First, the field is split between ``perception'' models that understand motion from video but only output text, and ``generation'' models that cannot perceive from raw visual input. Second, generative MLLMs are often limited to single-frame, static poses using dense, parametric SMPL models, failing to handle temporal motion. Third, existing motion vocabularies are built from skeleto"},"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":"2602.02401","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-02T17:59:01Z","cross_cats_sorted":[],"title_canon_sha256":"af709e1dd1504f8b6c10f37f579d0c94b2ae4f53b51999b2b34041a1a98f30a5","abstract_canon_sha256":"f25a025c98a092e79945dd99b9c92c3d531847e91f69d16eed639345d9da89c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:25.098404Z","signature_b64":"SY37pGU7yF3Dd/P6NWCR3RvEdZ4/a7ayuArcGHY2wy0JP4kEfEB042fSHc5D2VcHZ4sC30DtYYOWyVlr4/yxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8449837b1986a9213a814f5b287c946da0f0cf50f62760ad7e1c1f2954d04800","last_reissued_at":"2026-07-08T01:18:25.097809Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:25.097809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jason Li, Mengyuan Liu, Peiming Li, Songtao Wu, Xinshun Wang, Zhichao Deng, Zhongbin Fang, Ziyi Wang","submitted_at":"2026-02-02T17:59:01Z","abstract_excerpt":"Human motion analysis tasks, such as temporal 3D pose estimation, motion prediction, and motion in-betweening, play an essential role in computer vision. However, current paradigms suffer from severe fragmentation. First, the field is split between ``perception'' models that understand motion from video but only output text, and ``generation'' models that cannot perceive from raw visual input. Second, generative MLLMs are often limited to single-frame, static poses using dense, parametric SMPL models, failing to handle temporal motion. Third, existing motion vocabularies are built from skeleto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02401","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/2602.02401/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":"2602.02401","created_at":"2026-07-08T01:18:25.097874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02401v2","created_at":"2026-07-08T01:18:25.097874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02401","created_at":"2026-07-08T01:18:25.097874+00:00"},{"alias_kind":"pith_short_12","alias_value":"QREYG6YZQ2US","created_at":"2026-07-08T01:18:25.097874+00:00"},{"alias_kind":"pith_short_16","alias_value":"QREYG6YZQ2USCOUB","created_at":"2026-07-08T01:18:25.097874+00:00"},{"alias_kind":"pith_short_8","alias_value":"QREYG6YZ","created_at":"2026-07-08T01:18:25.097874+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/QREYG6YZQ2USCOUBJ5NSQ7EUNW","json":"https://pith.science/pith/QREYG6YZQ2USCOUBJ5NSQ7EUNW.json","graph_json":"https://pith.science/api/pith-number/QREYG6YZQ2USCOUBJ5NSQ7EUNW/graph.json","events_json":"https://pith.science/api/pith-number/QREYG6YZQ2USCOUBJ5NSQ7EUNW/events.json","paper":"https://pith.science/paper/QREYG6YZ"},"agent_actions":{"view_html":"https://pith.science/pith/QREYG6YZQ2USCOUBJ5NSQ7EUNW","download_json":"https://pith.science/pith/QREYG6YZQ2USCOUBJ5NSQ7EUNW.json","view_paper":"https://pith.science/paper/QREYG6YZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02401&json=true","fetch_graph":"https://pith.science/api/pith-number/QREYG6YZQ2USCOUBJ5NSQ7EUNW/graph.json","fetch_events":"https://pith.science/api/pith-number/QREYG6YZQ2USCOUBJ5NSQ7EUNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QREYG6YZQ2USCOUBJ5NSQ7EUNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QREYG6YZQ2USCOUBJ5NSQ7EUNW/action/storage_attestation","attest_author":"https://pith.science/pith/QREYG6YZQ2USCOUBJ5NSQ7EUNW/action/author_attestation","sign_citation":"https://pith.science/pith/QREYG6YZQ2USCOUBJ5NSQ7EUNW/action/citation_signature","submit_replication":"https://pith.science/pith/QREYG6YZQ2USCOUBJ5NSQ7EUNW/action/replication_record"}},"created_at":"2026-07-08T01:18:25.097874+00:00","updated_at":"2026-07-08T01:18:25.097874+00:00"}