{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MSBKTCEYFW3UZ5YLZF4YGBCV7H","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":"448cbb4b03ed9d73cfa5ffb355e7d171fb2864cd27a97120356b7e04e76477ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T17:16:25Z","title_canon_sha256":"8553020504dc527824895cb3f29a91f0cebb6e08f4abee0ad658fb16b62a95b0"},"schema_version":"1.0","source":{"id":"2608.01392","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01392","created_at":"2026-08-04T02:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01392v1","created_at":"2026-08-04T02:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01392","created_at":"2026-08-04T02:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"MSBKTCEYFW3U","created_at":"2026-08-04T02:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"MSBKTCEYFW3UZ5YL","created_at":"2026-08-04T02:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"MSBKTCEY","created_at":"2026-08-04T02:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:0ca9870ee33300ed0d9e1b64253eec726c53c26c360155831d8f15d0a7aa0410","target":"graph","created_at":"2026-08-04T02:04:56Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.01392/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-conditioned human motion generation has made rapid progress with the emergence of large-scale motion--language datasets. However, even datasets with rich long-form descriptions typically provide supervision only at the clip level, without explicit temporal correspondence between motion frames and language. This limits fine-grained motion--text grounding and temporally precise generation. We propose FineMoLA, a weakly supervised framework that learns fine-grained frame--phrase correspondence directly from clip-level annotations. Our method first segments long-form descriptions into action-","authors_text":"Aniket Bera, Baijian Yang, Muhan Lin, Shengyang Luo, Tongyan Wang, Yifan Shen, Yingjie Victor Chen, Zhengyuan Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T17:16:25Z","title":"FineMoLA: Towards Fine-Grained Motion-Language Alignment from Clip-Level Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01392","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bae9a7854a88083717feaf2eeebd3ca0ccf73fa9d67969f31cda167cd9194db8","target":"record","created_at":"2026-08-04T02:04:56Z","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":"448cbb4b03ed9d73cfa5ffb355e7d171fb2864cd27a97120356b7e04e76477ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T17:16:25Z","title_canon_sha256":"8553020504dc527824895cb3f29a91f0cebb6e08f4abee0ad658fb16b62a95b0"},"schema_version":"1.0","source":{"id":"2608.01392","kind":"arxiv","version":1}},"canonical_sha256":"6482a988982db74cf70bc979830455f9fe4ca339739331f0d0253fbe0eab8184","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6482a988982db74cf70bc979830455f9fe4ca339739331f0d0253fbe0eab8184","first_computed_at":"2026-08-04T02:04:56.556185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:04:56.556185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cgciJOGvw/9ZUvnldi0CwgkBs1a/vcn8NxJ87d+y6PCOkM7Hn0sNYZKkwlJVJPJFw+PQY1x0mOQtRaZ1P6QDCQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:04:56.558079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01392","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bae9a7854a88083717feaf2eeebd3ca0ccf73fa9d67969f31cda167cd9194db8","sha256:0ca9870ee33300ed0d9e1b64253eec726c53c26c360155831d8f15d0a7aa0410"],"state_sha256":"bc96bcea0998c7afd91a6ab61c499918f0af4f287770a88524c72fb00c8dc251"}