{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AY2IHJ332PKDS4LZ6PKDTKEOAI","short_pith_number":"pith:AY2IHJ33","schema_version":"1.0","canonical_sha256":"063483a77bd3d4397179f3d439a88e021ff776c72d78a2108613981b2a3141b7","source":{"kind":"arxiv","id":"2604.03799","version":2},"attestation_state":"computed","paper":{"title":"Next-Scale Autoregressive Models for Text-to-Motion Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A next-scale autoregressive model generates text-to-motion sequences hierarchically from coarse to fine temporal resolutions.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingjie Liu, Mingmin Zhao, Shibo Jin, Zhiwei Zheng","submitted_at":"2026-04-04T17:07:37Z","abstract_excerpt":"Autoregressive (AR) models offer stable and efficient training, but standard next-token prediction is not well aligned with the temporal structure required for text-conditioned motion generation. We introduce MoScale, a next-scale AR framework that generates motion hierarchically from coarse to fine temporal resolutions. By providing global semantics at the coarsest scale and refining them progressively, MoScale establishes a causal hierarchy better suited for long-range motion structure. To improve robustness under limited text-motion data, we further incorporate cross-scale hierarchical refi"},"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":"2604.03799","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-04T17:07:37Z","cross_cats_sorted":[],"title_canon_sha256":"943c8e3fcaf255eb5f9bac10d7a045869e24636790882c53f6d325af50dc413b","abstract_canon_sha256":"8fe244ea15d8ca2998b0accca4dd927b6b3e77b532ee63fa5e930516914934be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:39.422510Z","signature_b64":"G6xXtvVvmKYyFOR25yWDtSzZ9b1rpP7/R5/qoKtc40oubKAkpHvNBwgK++vDbS+2IF3JlzmJmvpXJvVqoOG6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"063483a77bd3d4397179f3d439a88e021ff776c72d78a2108613981b2a3141b7","last_reissued_at":"2026-05-28T01:04:39.421959Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:39.421959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Next-Scale Autoregressive Models for Text-to-Motion Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A next-scale autoregressive model generates text-to-motion sequences hierarchically from coarse to fine temporal resolutions.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingjie Liu, Mingmin Zhao, Shibo Jin, Zhiwei Zheng","submitted_at":"2026-04-04T17:07:37Z","abstract_excerpt":"Autoregressive (AR) models offer stable and efficient training, but standard next-token prediction is not well aligned with the temporal structure required for text-conditioned motion generation. We introduce MoScale, a next-scale AR framework that generates motion hierarchically from coarse to fine temporal resolutions. By providing global semantics at the coarsest scale and refining them progressively, MoScale establishes a causal hierarchy better suited for long-range motion structure. To improve robustness under limited text-motion data, we further incorporate cross-scale hierarchical refi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MoScale achieves SOTA text-to-motion performance with high training efficiency, scales effectively with model size, and generalizes zero-shot to diverse motion generation and editing tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that providing global semantics at the coarsest scale and refining progressively establishes a causal hierarchy better suited for long-range motion structure than standard next-token prediction.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MoScale introduces a hierarchical next-scale autoregressive framework for text-to-motion generation that achieves state-of-the-art performance by refining motions from coarse to fine temporal resolutions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A next-scale autoregressive model generates text-to-motion sequences hierarchically from coarse to fine temporal resolutions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"932dccec8ff54fd13f1a87f54763e3865992a9fb60aae87a5a965aab99e2e04c"},"source":{"id":"2604.03799","kind":"arxiv","version":2},"verdict":{"id":"20ab3674-782d-40cc-beb5-13d9ab28aee8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T17:24:27.969157Z","strongest_claim":"MoScale achieves SOTA text-to-motion performance with high training efficiency, scales effectively with model size, and generalizes zero-shot to diverse motion generation and editing tasks.","one_line_summary":"MoScale introduces a hierarchical next-scale autoregressive framework for text-to-motion generation that achieves state-of-the-art performance by refining motions from coarse to fine temporal resolutions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that providing global semantics at the coarsest scale and refining progressively establishes a causal hierarchy better suited for long-range motion structure than standard next-token prediction.","pith_extraction_headline":"A next-scale autoregressive model generates text-to-motion sequences hierarchically from coarse to fine temporal resolutions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.03799/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":"2604.03799","created_at":"2026-05-28T01:04:39.422026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.03799v2","created_at":"2026-05-28T01:04:39.422026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03799","created_at":"2026-05-28T01:04:39.422026+00:00"},{"alias_kind":"pith_short_12","alias_value":"AY2IHJ332PKD","created_at":"2026-05-28T01:04:39.422026+00:00"},{"alias_kind":"pith_short_16","alias_value":"AY2IHJ332PKDS4LZ","created_at":"2026-05-28T01:04:39.422026+00:00"},{"alias_kind":"pith_short_8","alias_value":"AY2IHJ33","created_at":"2026-05-28T01:04:39.422026+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/AY2IHJ332PKDS4LZ6PKDTKEOAI","json":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI.json","graph_json":"https://pith.science/api/pith-number/AY2IHJ332PKDS4LZ6PKDTKEOAI/graph.json","events_json":"https://pith.science/api/pith-number/AY2IHJ332PKDS4LZ6PKDTKEOAI/events.json","paper":"https://pith.science/paper/AY2IHJ33"},"agent_actions":{"view_html":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI","download_json":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI.json","view_paper":"https://pith.science/paper/AY2IHJ33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.03799&json=true","fetch_graph":"https://pith.science/api/pith-number/AY2IHJ332PKDS4LZ6PKDTKEOAI/graph.json","fetch_events":"https://pith.science/api/pith-number/AY2IHJ332PKDS4LZ6PKDTKEOAI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI/action/storage_attestation","attest_author":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI/action/author_attestation","sign_citation":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI/action/citation_signature","submit_replication":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI/action/replication_record"}},"created_at":"2026-05-28T01:04:39.422026+00:00","updated_at":"2026-05-28T01:04:39.422026+00:00"}