{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MHKVTQM5LPBDD56S6CHWUPDUWT","short_pith_number":"pith:MHKVTQM5","canonical_record":{"source":{"id":"2606.04773","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T11:53:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3f3c30dd7829980db2c759892c5fc3abed5b44047e5d584b9e87a0679d372adf","abstract_canon_sha256":"ed88aa5f8b92c269cd91cd7d6e1fac608f010b5ee53df0709dab5b30dc123c7e"},"schema_version":"1.0"},"canonical_sha256":"61d559c19d5bc231f7d2f08f6a3c74b4c8c21d90b5c3700b3ad320b74f2968f3","source":{"kind":"arxiv","id":"2606.04773","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04773","created_at":"2026-06-04T01:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04773v1","created_at":"2026-06-04T01:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04773","created_at":"2026-06-04T01:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"MHKVTQM5LPBD","created_at":"2026-06-04T01:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"MHKVTQM5LPBDD56S","created_at":"2026-06-04T01:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"MHKVTQM5","created_at":"2026-06-04T01:09:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MHKVTQM5LPBDD56S6CHWUPDUWT","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04773","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T11:53:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3f3c30dd7829980db2c759892c5fc3abed5b44047e5d584b9e87a0679d372adf","abstract_canon_sha256":"ed88aa5f8b92c269cd91cd7d6e1fac608f010b5ee53df0709dab5b30dc123c7e"},"schema_version":"1.0"},"canonical_sha256":"61d559c19d5bc231f7d2f08f6a3c74b4c8c21d90b5c3700b3ad320b74f2968f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:29.491881Z","signature_b64":"b2oqasYObJf0MydkCNu52FdPDcNB31HqhGtWlOR713Gv+4/IgdvMzvoGSfP2fvbARm+pDN4M7EILLk+shho5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61d559c19d5bc231f7d2f08f6a3c74b4c8c21d90b5c3700b3ad320b74f2968f3","last_reissued_at":"2026-06-04T01:09:29.491386Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:29.491386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04773","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bGG3iwZ8ehKwOobpUVvFGu2BOT2JBZK0mACzOif50r/QFVG9o12RgaK8xOXOyCMXn9zg9FC1boRLxRTPevmbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T17:20:16.556803Z"},"content_sha256":"9cfac5111f882d28d66de51543ba92e98905f7d0d018e4c325ca52d31d5ea71b","schema_version":"1.0","event_id":"sha256:9cfac5111f882d28d66de51543ba92e98905f7d0d018e4c325ca52d31d5ea71b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MHKVTQM5LPBDD56S6CHWUPDUWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NextMotionQA: Benchmarking and Judging Human Motion Understanding with Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Chuqiao Li, Gerard Pons-Moll, Xianghui Xie, Yong Cao","submitted_at":"2026-06-03T11:53:57Z","abstract_excerpt":"Reliable evaluation of human motion understanding is fundamental to advancing embodied AI, robotics, and animation. However, existing benchmarks suffer from coarse semantic granularity, undifferentiated difficulty, limited annotation quality, and pervasive answer ambiguity, leaving them unable to diagnose where current models fail. To bridge this gap, we introduce NextMotionQA, a comprehensive benchmark that leverages vision-language models (VLMs) for semi-automated, expert-verified dataset. NextMotionQA features three complementary tasks: multiple-choice question answering, video captioning, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04773","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.04773/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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hTPUmkDtoSZ4kUAdLgBgtWPpcIBnKyKWxz58lBbapPJnsRENXUNmtMrtN+ZlBj6i4xCjzqVJr+cz/a4OM8lqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T17:20:16.557173Z"},"content_sha256":"038dd292fdfb4e39e9f9330d3113020e6b23c13232a8ae1b30a0d8e96f000011","schema_version":"1.0","event_id":"sha256:038dd292fdfb4e39e9f9330d3113020e6b23c13232a8ae1b30a0d8e96f000011"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MHKVTQM5LPBDD56S6CHWUPDUWT/bundle.json","state_url":"https://pith.science/pith/MHKVTQM5LPBDD56S6CHWUPDUWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MHKVTQM5LPBDD56S6CHWUPDUWT/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":"2026-06-30T17:20:16Z","links":{"resolver":"https://pith.science/pith/MHKVTQM5LPBDD56S6CHWUPDUWT","bundle":"https://pith.science/pith/MHKVTQM5LPBDD56S6CHWUPDUWT/bundle.json","state":"https://pith.science/pith/MHKVTQM5LPBDD56S6CHWUPDUWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MHKVTQM5LPBDD56S6CHWUPDUWT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MHKVTQM5LPBDD56S6CHWUPDUWT","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":"ed88aa5f8b92c269cd91cd7d6e1fac608f010b5ee53df0709dab5b30dc123c7e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T11:53:57Z","title_canon_sha256":"3f3c30dd7829980db2c759892c5fc3abed5b44047e5d584b9e87a0679d372adf"},"schema_version":"1.0","source":{"id":"2606.04773","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04773","created_at":"2026-06-04T01:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04773v1","created_at":"2026-06-04T01:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04773","created_at":"2026-06-04T01:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"MHKVTQM5LPBD","created_at":"2026-06-04T01:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"MHKVTQM5LPBDD56S","created_at":"2026-06-04T01:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"MHKVTQM5","created_at":"2026-06-04T01:09:29Z"}],"graph_snapshots":[{"event_id":"sha256:038dd292fdfb4e39e9f9330d3113020e6b23c13232a8ae1b30a0d8e96f000011","target":"graph","created_at":"2026-06-04T01:09:29Z","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/2606.04773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reliable evaluation of human motion understanding is fundamental to advancing embodied AI, robotics, and animation. However, existing benchmarks suffer from coarse semantic granularity, undifferentiated difficulty, limited annotation quality, and pervasive answer ambiguity, leaving them unable to diagnose where current models fail. To bridge this gap, we introduce NextMotionQA, a comprehensive benchmark that leverages vision-language models (VLMs) for semi-automated, expert-verified dataset. NextMotionQA features three complementary tasks: multiple-choice question answering, video captioning, ","authors_text":"Andreas Geiger, Chuqiao Li, Gerard Pons-Moll, Xianghui Xie, Yong Cao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T11:53:57Z","title":"NextMotionQA: Benchmarking and Judging Human Motion Understanding with Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04773","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":"sha256:9cfac5111f882d28d66de51543ba92e98905f7d0d018e4c325ca52d31d5ea71b","target":"record","created_at":"2026-06-04T01:09:29Z","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":"ed88aa5f8b92c269cd91cd7d6e1fac608f010b5ee53df0709dab5b30dc123c7e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T11:53:57Z","title_canon_sha256":"3f3c30dd7829980db2c759892c5fc3abed5b44047e5d584b9e87a0679d372adf"},"schema_version":"1.0","source":{"id":"2606.04773","kind":"arxiv","version":1}},"canonical_sha256":"61d559c19d5bc231f7d2f08f6a3c74b4c8c21d90b5c3700b3ad320b74f2968f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61d559c19d5bc231f7d2f08f6a3c74b4c8c21d90b5c3700b3ad320b74f2968f3","first_computed_at":"2026-06-04T01:09:29.491386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:29.491386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b2oqasYObJf0MydkCNu52FdPDcNB31HqhGtWlOR713Gv+4/IgdvMzvoGSfP2fvbARm+pDN4M7EILLk+shho5Bg==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:29.491881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04773","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cfac5111f882d28d66de51543ba92e98905f7d0d018e4c325ca52d31d5ea71b","sha256:038dd292fdfb4e39e9f9330d3113020e6b23c13232a8ae1b30a0d8e96f000011"],"state_sha256":"7eee16b03ced2b1bb6bf63c0f097c523c27383164433313d622c09cea3905520"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4qVnonLXxyrw6qSHGRvlku7lBozFCtH2B7J2mb1tlwbovbSK6Ym+7R5dIwDzYLnxEQMhGn5d9hrnHzTz7amECw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T17:20:16.559398Z","bundle_sha256":"a029ba51e9794777a9826700ec1e4fdb3fc4048bb83144f5886ad5a9da7bb617"}}