{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AY2IHJ332PKDS4LZ6PKDTKEOAI","short_pith_number":"pith:AY2IHJ33","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"},"canonical_sha256":"063483a77bd3d4397179f3d439a88e021ff776c72d78a2108613981b2a3141b7","source":{"kind":"arxiv","id":"2604.03799","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AY2IHJ332PKDS4LZ6PKDTKEOAI","target":"record","payload":{"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"},"canonical_sha256":"063483a77bd3d4397179f3d439a88e021ff776c72d78a2108613981b2a3141b7","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"},"source_kind":"arxiv","source_id":"2604.03799","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":"2026-05-28T01:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bJ9AfgCVmurB4SDd3s681vb5cfakYKfoE7sauzl0uSGnv5z6vt42tbtXKF5l9AJXlfMDWC6m7KNCyCJ/5sxHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:58:27.780304Z"},"content_sha256":"8b60365828c33b4979c59498fc408594f1eeda7dba9fc2a72486615a4a281b44","schema_version":"1.0","event_id":"sha256:8b60365828c33b4979c59498fc408594f1eeda7dba9fc2a72486615a4a281b44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AY2IHJ332PKDS4LZ6PKDTKEOAI","target":"graph","payload":{"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"},"verdict_id":"20ab3674-782d-40cc-beb5-13d9ab28aee8"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2NHU4pUvbME1n0UZbQBHJ0whl4fUqtJeWj/stydmO37/qd4RAOSOBnn38z1Lbm+VUBghCeqjVEuGuNODbfpYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:58:27.780800Z"},"content_sha256":"5e740f8294dfcd30c12f93e02817ae9b8af0195146aa69e91226797a416bcd40","schema_version":"1.0","event_id":"sha256:5e740f8294dfcd30c12f93e02817ae9b8af0195146aa69e91226797a416bcd40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI/bundle.json","state_url":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI/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":"2026-06-05T14:58:27Z","links":{"resolver":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI","bundle":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI/bundle.json","state":"https://pith.science/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AY2IHJ332PKDS4LZ6PKDTKEOAI/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cDkHmSmnspz7tRFvP3nmmyV22vw2XfvtdofipOjRU41gc1+H/3VsFAlb3SrYlec6NZWHDkyXM04CJa6viy+YDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T14:58:27.783000Z","bundle_sha256":"e1517dd71b9c824c4b8f2b7e78d0cf8477bc1128dc8ebdf7414c42052655d5ef"}}