{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C6SDXUPQGLNXQNZPBIO25VED3J","short_pith_number":"pith:C6SDXUPQ","schema_version":"1.0","canonical_sha256":"17a43bd1f032db78372f0a1daed483da7fbe9d1f57282d305e89fd7433fcc30b","source":{"kind":"arxiv","id":"2508.10897","version":1},"attestation_state":"computed","paper":{"title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deheng Ye, Mengyuan Liu, Ming-Hsuan Yang, Songtao Wu, Tao Tang, Xia Li, Xiangtai Li, Xinshun Wang, Zhongbin Fang","submitted_at":"2025-08-14T17:59:23Z","abstract_excerpt":"This paper aims to model 3D human motion across domains, where a single model is expected to handle multiple modalities, tasks, and datasets. Existing cross-domain models often rely on domain-specific components and multi-stage training, which limits their practicality and scalability. To overcome these challenges, we propose a new setting to train a unified cross-domain model through a single process, eliminating the need for domain-specific components and multi-stage training. We first introduce Pose-in-Context (PiC), which leverages in-context learning to create a pose-centric cross-domain "},"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":"2508.10897","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T17:59:23Z","cross_cats_sorted":[],"title_canon_sha256":"9c29f97dfd594dc9896079d5d449fd3ab2101a10929e0ebb493c634b4be30c6a","abstract_canon_sha256":"97fde96139951249f0810eb664bc8c63490e064bcef614ea98b58621b02c869c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:04.788269Z","signature_b64":"XF2/YyrL8huPMhZVWOOWndBr9HLG+4GztEMwJxZcKTX7jV+/dcTgTau2MKVPATSvSb1Y45TKVrfWdA8te9bqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17a43bd1f032db78372f0a1daed483da7fbe9d1f57282d305e89fd7433fcc30b","last_reissued_at":"2026-07-05T11:54:04.787786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:04.787786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deheng Ye, Mengyuan Liu, Ming-Hsuan Yang, Songtao Wu, Tao Tang, Xia Li, Xiangtai Li, Xinshun Wang, Zhongbin Fang","submitted_at":"2025-08-14T17:59:23Z","abstract_excerpt":"This paper aims to model 3D human motion across domains, where a single model is expected to handle multiple modalities, tasks, and datasets. Existing cross-domain models often rely on domain-specific components and multi-stage training, which limits their practicality and scalability. To overcome these challenges, we propose a new setting to train a unified cross-domain model through a single process, eliminating the need for domain-specific components and multi-stage training. We first introduce Pose-in-Context (PiC), which leverages in-context learning to create a pose-centric cross-domain "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10897","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/2508.10897/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":"2508.10897","created_at":"2026-07-05T11:54:04.787844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10897v1","created_at":"2026-07-05T11:54:04.787844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10897","created_at":"2026-07-05T11:54:04.787844+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6SDXUPQGLNX","created_at":"2026-07-05T11:54:04.787844+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6SDXUPQGLNXQNZP","created_at":"2026-07-05T11:54:04.787844+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6SDXUPQ","created_at":"2026-07-05T11:54:04.787844+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02845","citing_title":"Deformation-based In-Context Learning for Point Cloud Understanding","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6SDXUPQGLNXQNZPBIO25VED3J","json":"https://pith.science/pith/C6SDXUPQGLNXQNZPBIO25VED3J.json","graph_json":"https://pith.science/api/pith-number/C6SDXUPQGLNXQNZPBIO25VED3J/graph.json","events_json":"https://pith.science/api/pith-number/C6SDXUPQGLNXQNZPBIO25VED3J/events.json","paper":"https://pith.science/paper/C6SDXUPQ"},"agent_actions":{"view_html":"https://pith.science/pith/C6SDXUPQGLNXQNZPBIO25VED3J","download_json":"https://pith.science/pith/C6SDXUPQGLNXQNZPBIO25VED3J.json","view_paper":"https://pith.science/paper/C6SDXUPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10897&json=true","fetch_graph":"https://pith.science/api/pith-number/C6SDXUPQGLNXQNZPBIO25VED3J/graph.json","fetch_events":"https://pith.science/api/pith-number/C6SDXUPQGLNXQNZPBIO25VED3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6SDXUPQGLNXQNZPBIO25VED3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6SDXUPQGLNXQNZPBIO25VED3J/action/storage_attestation","attest_author":"https://pith.science/pith/C6SDXUPQGLNXQNZPBIO25VED3J/action/author_attestation","sign_citation":"https://pith.science/pith/C6SDXUPQGLNXQNZPBIO25VED3J/action/citation_signature","submit_replication":"https://pith.science/pith/C6SDXUPQGLNXQNZPBIO25VED3J/action/replication_record"}},"created_at":"2026-07-05T11:54:04.787844+00:00","updated_at":"2026-07-05T11:54:04.787844+00:00"}