{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TIH647K3IUPW5WXOAVHHOOJ2WV","short_pith_number":"pith:TIH647K3","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"},"canonical_sha256":"9a0fee7d5b451f6edaee054e77393ab56c054664725112628f58e7e309adf5bb","source":{"kind":"arxiv","id":"2605.11704","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.11704","created_at":"2026-07-22T01:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.11704v2","created_at":"2026-07-22T01:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11704","created_at":"2026-07-22T01:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"TIH647K3IUPW","created_at":"2026-07-22T01:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"TIH647K3IUPW5WXO","created_at":"2026-07-22T01:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"TIH647K3","created_at":"2026-07-22T01:23:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TIH647K3IUPW5WXOAVHHOOJ2WV","target":"record","payload":{"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"},"canonical_sha256":"9a0fee7d5b451f6edaee054e77393ab56c054664725112628f58e7e309adf5bb","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"},"source_kind":"arxiv","source_id":"2605.11704","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-22T01:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"juMFTIilmEeF7K2XKH10dXe2w2BnFBTaU6dKJuTAblGiTSkLGVRWZei36w7YyKFgyolvXPv5oXubbJ4ftLfQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:18:47.131101Z"},"content_sha256":"5f8ad1f6bd00400ab2f08b720c42c97ab96f16d0e71d6e8a2d6dfe081471f19c","schema_version":"1.0","event_id":"sha256:5f8ad1f6bd00400ab2f08b720c42c97ab96f16d0e71d6e8a2d6dfe081471f19c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TIH647K3IUPW5WXOAVHHOOJ2WV","target":"graph","payload":{"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"},"verdict_id":"0f5be8e1-0bb7-4cd7-8d8b-b28ce2498e6f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-22T01:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HGedidJhJpaqHjhLpoOBfGxXHR76qS+4Fk407GePtyaNUTnWHM0O0yBMHpwkx2OQOo4UUUznJWwyB+k+YMIYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:18:47.131825Z"},"content_sha256":"9a6f005fc131bd34befa76a8a7e35fce043ddb26dffb5a61e2d4af660753553e","schema_version":"1.0","event_id":"sha256:9a6f005fc131bd34befa76a8a7e35fce043ddb26dffb5a61e2d4af660753553e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV/bundle.json","state_url":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TIH647K3IUPW5WXOAVHHOOJ2WV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T11:18:47Z","links":{"resolver":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV","bundle":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV/bundle.json","state":"https://pith.science/pith/TIH647K3IUPW5WXOAVHHOOJ2WV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TIH647K3IUPW5WXOAVHHOOJ2WV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TIH647K3IUPW5WXOAVHHOOJ2WV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"029f2390748dcfb23e65b4c19efb9e9185375da087e3ae9e37299de78bb30921","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T07:58:58Z","title_canon_sha256":"82458e8199abdc58887ab37d94cd7d2900ba3287a795e4cca217b7127d298518"},"schema_version":"1.0","source":{"id":"2605.11704","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.11704","created_at":"2026-07-22T01:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.11704v2","created_at":"2026-07-22T01:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11704","created_at":"2026-07-22T01:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"TIH647K3IUPW","created_at":"2026-07-22T01:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"TIH647K3IUPW5WXO","created_at":"2026-07-22T01:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"TIH647K3","created_at":"2026-07-22T01:23:57Z"}],"graph_snapshots":[{"event_id":"sha256:9a6f005fc131bd34befa76a8a7e35fce043ddb26dffb5a61e2d4af660753553e","target":"graph","created_at":"2026-07-22T01:23:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ScaleMoGen generates human motions by autoregressively predicting discrete tokens from coarse to fine skeletal-temporal scales."}],"snapshot_sha256":"86cfba83bde1190a64f5e13bb3c6c4e35c18503b54c4952deaed972502ca7d50"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.11704/integrity.json","findings":[],"snapshot_sha256":"d46587df6bbbe9ce7f3ebc65ec28a458c45c6a38c1d9e831faa7a5e1036bfc0e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bing Zhou, Chuan Guo, Hojun Jang, Inwoo Hwang, Jian Wang, Young Min Kim","cross_cats":[],"headline":"ScaleMoGen generates human motions by autoregressively predicting discrete tokens from coarse to fine skeletal-temporal scales.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T07:58:58Z","title":"ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.11704","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T06:20:11.668434Z","id":"0f5be8e1-0bb7-4cd7-8d8b-b28ce2498e6f","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"ScaleMoGen generates human motions by autoregressively predicting discrete tokens from coarse to fine skeletal-temporal scales.","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.","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."}},"verdict_id":"0f5be8e1-0bb7-4cd7-8d8b-b28ce2498e6f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5f8ad1f6bd00400ab2f08b720c42c97ab96f16d0e71d6e8a2d6dfe081471f19c","target":"record","created_at":"2026-07-22T01:23:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"029f2390748dcfb23e65b4c19efb9e9185375da087e3ae9e37299de78bb30921","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T07:58:58Z","title_canon_sha256":"82458e8199abdc58887ab37d94cd7d2900ba3287a795e4cca217b7127d298518"},"schema_version":"1.0","source":{"id":"2605.11704","kind":"arxiv","version":2}},"canonical_sha256":"9a0fee7d5b451f6edaee054e77393ab56c054664725112628f58e7e309adf5bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a0fee7d5b451f6edaee054e77393ab56c054664725112628f58e7e309adf5bb","first_computed_at":"2026-07-22T01:23:57.266373Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:23:57.266373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FFC/vUzL7IUtHfKmWQbS5cKkACu8PjQkSuGhDIK8rosLg/Uxw81MMcmo+xWUgqPD7gNiRaZ/LsKBgSdWuBeXBQ==","signature_status":"signed_v1","signed_at":"2026-07-22T01:23:57.267252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.11704","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f8ad1f6bd00400ab2f08b720c42c97ab96f16d0e71d6e8a2d6dfe081471f19c","sha256:9a6f005fc131bd34befa76a8a7e35fce043ddb26dffb5a61e2d4af660753553e"],"state_sha256":"6cae67a2cbee72d1cf951b1f1652d9ecb422e8a5d12a87ee75c2811b3d69c332"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7NHi3cTZ6LkFEKSVOrYzcQlyI4GMyv7T4rMvw2s+BiIeXo5WImrR3Jr2QtNw6COhtIuTGFUf6PmgbsipTKpXDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:18:47.135692Z","bundle_sha256":"688005e471496d52a7c953670d55fc2ee7ac102ceb3439904c3dd263928bbbd1"}}