{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AY2IHJ332PKDS4LZ6PKDTKEOAI","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":"8fe244ea15d8ca2998b0accca4dd927b6b3e77b532ee63fa5e930516914934be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-04T17:07:37Z","title_canon_sha256":"943c8e3fcaf255eb5f9bac10d7a045869e24636790882c53f6d325af50dc413b"},"schema_version":"1.0","source":{"id":"2604.03799","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.03799","created_at":"2026-05-28T01:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2604.03799v2","created_at":"2026-05-28T01:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03799","created_at":"2026-05-28T01:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"AY2IHJ332PKD","created_at":"2026-05-28T01:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"AY2IHJ332PKDS4LZ","created_at":"2026-05-28T01:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"AY2IHJ33","created_at":"2026-05-28T01:04:39Z"}],"graph_snapshots":[{"event_id":"sha256:5e740f8294dfcd30c12f93e02817ae9b8af0195146aa69e91226797a416bcd40","target":"graph","created_at":"2026-05-28T01:04:39Z","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":"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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A next-scale autoregressive model generates text-to-motion sequences hierarchically from coarse to fine temporal resolutions."}],"snapshot_sha256":"932dccec8ff54fd13f1a87f54763e3865992a9fb60aae87a5a965aab99e2e04c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.03799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lingjie Liu, Mingmin Zhao, Shibo Jin, Zhiwei Zheng","cross_cats":[],"headline":"A next-scale autoregressive model generates text-to-motion sequences hierarchically from coarse to fine temporal resolutions.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-04T17:07:37Z","title":"Next-Scale Autoregressive Models for Text-to-Motion Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.03799","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T17:24:27.969157Z","id":"20ab3674-782d-40cc-beb5-13d9ab28aee8","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"A next-scale autoregressive model generates text-to-motion sequences hierarchically from coarse to fine temporal resolutions.","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.","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."}},"verdict_id":"20ab3674-782d-40cc-beb5-13d9ab28aee8"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8b60365828c33b4979c59498fc408594f1eeda7dba9fc2a72486615a4a281b44","target":"record","created_at":"2026-05-28T01:04:39Z","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":"8fe244ea15d8ca2998b0accca4dd927b6b3e77b532ee63fa5e930516914934be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-04T17:07:37Z","title_canon_sha256":"943c8e3fcaf255eb5f9bac10d7a045869e24636790882c53f6d325af50dc413b"},"schema_version":"1.0","source":{"id":"2604.03799","kind":"arxiv","version":2}},"canonical_sha256":"063483a77bd3d4397179f3d439a88e021ff776c72d78a2108613981b2a3141b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"063483a77bd3d4397179f3d439a88e021ff776c72d78a2108613981b2a3141b7","first_computed_at":"2026-05-28T01:04:39.421959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:39.421959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G6xXtvVvmKYyFOR25yWDtSzZ9b1rpP7/R5/qoKtc40oubKAkpHvNBwgK++vDbS+2IF3JlzmJmvpXJvVqoOG6BQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:39.422510Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.03799","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b60365828c33b4979c59498fc408594f1eeda7dba9fc2a72486615a4a281b44","sha256:5e740f8294dfcd30c12f93e02817ae9b8af0195146aa69e91226797a416bcd40"],"state_sha256":"176e55840f136b9607652f9a3fe6d137957d05dee5cfbc43a2210c60030e97f5"}