{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TIH647K3IUPW5WXOAVHHOOJ2WV","short_pith_number":"pith:TIH647K3","schema_version":"1.0","canonical_sha256":"9a0fee7d5b451f6edaee054e77393ab56c054664725112628f58e7e309adf5bb","source":{"kind":"arxiv","id":"2605.11704","version":2},"attestation_state":"computed","paper":{"title":"ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"ScaleMoGen generates human motions by autoregressively predicting discrete tokens from coarse to fine skeletal-temporal scales.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Zhou, Chuan Guo, Hojun Jang, Inwoo Hwang, Jian Wang, Young Min Kim","submitted_at":"2026-05-12T07:58:58Z","abstract_excerpt":"We present ScaleMoGen, a scale-wise autoregressive framework for text-driven human motion generation. Unlike conventional autoregressive approaches that rely on standard next-token prediction, ScaleMoGen frames motion generation as a coarse-to-fine process. We quantize 3D motions into compositional discrete tokens across multiple skeletal-emporal scales of increasing granularity, learning to generate motion by autoregressively predicting next-scale token maps. To maintain structural integrity, our motion tokenizers and quantizers are explicitly designed so that discrete tokens at every scale s"},"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":"2605.11704","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T07:58:58Z","cross_cats_sorted":[],"title_canon_sha256":"82458e8199abdc58887ab37d94cd7d2900ba3287a795e4cca217b7127d298518","abstract_canon_sha256":"029f2390748dcfb23e65b4c19efb9e9185375da087e3ae9e37299de78bb30921"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:23:57.267252Z","signature_b64":"FFC/vUzL7IUtHfKmWQbS5cKkACu8PjQkSuGhDIK8rosLg/Uxw81MMcmo+xWUgqPD7gNiRaZ/LsKBgSdWuBeXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a0fee7d5b451f6edaee054e77393ab56c054664725112628f58e7e309adf5bb","last_reissued_at":"2026-07-22T01:23:57.266373Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:23:57.266373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"ScaleMoGen generates human motions by autoregressively predicting discrete tokens from coarse to fine skeletal-temporal scales.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Zhou, Chuan Guo, Hojun Jang, Inwoo Hwang, Jian Wang, Young Min Kim","submitted_at":"2026-05-12T07:58:58Z","abstract_excerpt":"We present ScaleMoGen, a scale-wise autoregressive framework for text-driven human motion generation. Unlike conventional autoregressive approaches that rely on standard next-token prediction, ScaleMoGen frames motion generation as a coarse-to-fine process. We quantize 3D motions into compositional discrete tokens across multiple skeletal-emporal scales of increasing granularity, learning to generate motion by autoregressively predicting next-scale token maps. To maintain structural integrity, our motion tokenizers and quantizers are explicitly designed so that discrete tokens at every scale s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ScaleMoGen achieves state-of-the-art performance, establishing an FID of 0.030 (vs. 0.045 for MoMask) on HumanML3D and a CLIP Score of 0.693 (vs. 0.685 for MoMask++) on the SnapMoGen dataset, while enabling training-free text-guided motion editing.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That quantizing 3D motions into compositional discrete tokens across multiple skeletal-temporal scales strictly preserves the skeletal hierarchy and that bitwise quantization stabilizes optimization for high-detail motions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ScaleMoGen introduces a scale-wise autoregressive framework that quantizes motions into hierarchical discrete tokens and predicts next-scale maps to achieve SOTA FID 0.030 on HumanML3D and text-guided editing.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ScaleMoGen generates human motions by autoregressively predicting discrete tokens from coarse to fine skeletal-temporal scales.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"86cfba83bde1190a64f5e13bb3c6c4e35c18503b54c4952deaed972502ca7d50"},"source":{"id":"2605.11704","kind":"arxiv","version":2},"verdict":{"id":"0f5be8e1-0bb7-4cd7-8d8b-b28ce2498e6f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T06:20:11.668434Z","strongest_claim":"ScaleMoGen achieves state-of-the-art performance, establishing an FID of 0.030 (vs. 0.045 for MoMask) on HumanML3D and a CLIP Score of 0.693 (vs. 0.685 for MoMask++) on the SnapMoGen dataset, while enabling training-free text-guided motion editing.","one_line_summary":"ScaleMoGen introduces a scale-wise autoregressive framework that quantizes motions into hierarchical discrete tokens and predicts next-scale maps to achieve SOTA FID 0.030 on HumanML3D and text-guided editing.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That quantizing 3D motions into compositional discrete tokens across multiple skeletal-temporal scales strictly preserves the skeletal hierarchy and that bitwise quantization stabilizes optimization for high-detail motions.","pith_extraction_headline":"ScaleMoGen generates human motions by autoregressively predicting discrete tokens from coarse to fine skeletal-temporal scales."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.11704/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-21T00:01:32.042021Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T13:55:12.273920Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-20T03:42:00.474062Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T11:39:30.464506Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d46587df6bbbe9ce7f3ebc65ec28a458c45c6a38c1d9e831faa7a5e1036bfc0e"},"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":"2605.11704","created_at":"2026-07-22T01:23:57.266821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.11704v2","created_at":"2026-07-22T01:23:57.266821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11704","created_at":"2026-07-22T01:23:57.266821+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIH647K3IUPW","created_at":"2026-07-22T01:23:57.266821+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIH647K3IUPW5WXO","created_at":"2026-07-22T01:23:57.266821+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIH647K3","created_at":"2026-07-22T01:23:57.266821+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03127","citing_title":"DigitCode: Symbolic Tokenization of Hand Motion by Anatomical Units","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV","json":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV.json","graph_json":"https://pith.science/api/pith-number/TIH647K3IUPW5WXOAVHHOOJ2WV/graph.json","events_json":"https://pith.science/api/pith-number/TIH647K3IUPW5WXOAVHHOOJ2WV/events.json","paper":"https://pith.science/paper/TIH647K3"},"agent_actions":{"view_html":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV","download_json":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV.json","view_paper":"https://pith.science/paper/TIH647K3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.11704&json=true","fetch_graph":"https://pith.science/api/pith-number/TIH647K3IUPW5WXOAVHHOOJ2WV/graph.json","fetch_events":"https://pith.science/api/pith-number/TIH647K3IUPW5WXOAVHHOOJ2WV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV/action/storage_attestation","attest_author":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV/action/author_attestation","sign_citation":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV/action/citation_signature","submit_replication":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV/action/replication_record"}},"created_at":"2026-07-22T01:23:57.266821+00:00","updated_at":"2026-07-22T01:23:57.266821+00:00"}