{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BBU6DL2DDF5ALV5YROCBN3HVOC","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":"1b92f8d9fbf72e847876294acea4bbb4635700402bb4aa8ac777282205ae7264","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T19:31:56Z","title_canon_sha256":"8b3068e6c1522856b81d2e5d4eb6ef76c27399097235c3eaf154370af6979122"},"schema_version":"1.0","source":{"id":"2606.20888","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20888","created_at":"2026-06-23T00:12:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20888v1","created_at":"2026-06-23T00:12:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20888","created_at":"2026-06-23T00:12:01Z"},{"alias_kind":"pith_short_12","alias_value":"BBU6DL2DDF5A","created_at":"2026-06-23T00:12:01Z"},{"alias_kind":"pith_short_16","alias_value":"BBU6DL2DDF5ALV5Y","created_at":"2026-06-23T00:12:01Z"},{"alias_kind":"pith_short_8","alias_value":"BBU6DL2D","created_at":"2026-06-23T00:12:01Z"}],"graph_snapshots":[{"event_id":"sha256:d0d42a0254cb8bdf44c4723cfe795ebe3bf96a31f8fd714d537682e6b66e6a7a","target":"graph","created_at":"2026-06-23T00:12:01Z","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/2606.20888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we propose \\methodname, an LLM-based model for fine-grained human motion understanding that represents motion as a sequence of skeletal poses with explicit timestamps for each pose. Each pose encodes body joint positions and is temporally grounded with timestamp tokens, allowing the model to reason about motion order, duration, and rhythm. To study what supervision is needed for motion-language reasoning, we construct a diverse training mixture spanning pose captioning, pose question answering, motion captioning, and motion question answering. Our ablations show that the primary ","authors_text":"Jan van Gemert, Jouh Yeong Chew, Thomas Markhorst, Xucong Zhang, Zhi-Yi Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T19:31:56Z","title":"Fine-grained Human Motion Understanding with Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20888","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":"sha256:1f343bfeb1417b0b3226cf1fd543801e21379355c6fb61789ebe4f13257927b4","target":"record","created_at":"2026-06-23T00:12:01Z","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":"1b92f8d9fbf72e847876294acea4bbb4635700402bb4aa8ac777282205ae7264","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T19:31:56Z","title_canon_sha256":"8b3068e6c1522856b81d2e5d4eb6ef76c27399097235c3eaf154370af6979122"},"schema_version":"1.0","source":{"id":"2606.20888","kind":"arxiv","version":1}},"canonical_sha256":"0869e1af43197a05d7b88b8416ecf57092eee477b7c116ef6385ce006120a6a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0869e1af43197a05d7b88b8416ecf57092eee477b7c116ef6385ce006120a6a3","first_computed_at":"2026-06-23T00:12:01.851124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T00:12:01.851124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jrN/jKA5woA2I9LHPbS+iXdOFK3wiWhLaMA6YAmT8E13n8jg9CPvmmbXjDU7N6WOL0FEpefqOt7JC5OljYQoCw==","signature_status":"signed_v1","signed_at":"2026-06-23T00:12:01.851625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20888","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f343bfeb1417b0b3226cf1fd543801e21379355c6fb61789ebe4f13257927b4","sha256:d0d42a0254cb8bdf44c4723cfe795ebe3bf96a31f8fd714d537682e6b66e6a7a"],"state_sha256":"9f7ddb0b8c91a33bf145773183f8ff29a2d60dfbacf9d25f0303f7213be95b29"}