{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6KRWGZSFJRKMPKNVJ5N2S6V3VR","short_pith_number":"pith:6KRWGZSF","schema_version":"1.0","canonical_sha256":"f2a36366454c54c7a9b54f5ba97abbac485f0891a4aaab3bcf6c28da79fea884","source":{"kind":"arxiv","id":"2405.16909","version":1},"attestation_state":"computed","paper":{"title":"A Cross-Dataset Study for Text-based 3D Human Motion Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"G\\\"ul Varol, L\\'eore Bensabath, Mathis Petrovich","submitted_at":"2024-05-27T07:58:20Z","abstract_excerpt":"We provide results of our study on text-based 3D human motion retrieval and particularly focus on cross-dataset generalization. Due to practical reasons such as dataset-specific human body representations, existing works typically benchmarkby training and testing on partitions from the same dataset. Here, we employ a unified SMPL body format for all datasets, which allows us to perform training on one dataset, testing on the other, as well as training on a combination of datasets. Our results suggest that there exist dataset biases in standard text-motion benchmarks such as HumanML3D, KIT Moti"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.16909","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T07:58:20Z","cross_cats_sorted":[],"title_canon_sha256":"e9a40218f8cd1c0a38541fd0300b6515575689f9ca8ebfb0f1a5393767c8beef","abstract_canon_sha256":"ceef78f5abfaeb04f4c0aa0c99d9eae7f308eba6a9bda639562a1a39688b89cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:37.259597Z","signature_b64":"0+9lQl0cUD2MlbAKRYwJzsAooxYB4mPco6RocaW/56qcH4lzWywRzXcarkUvhgfKYrsVqinv7JIUfb18bF3BAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2a36366454c54c7a9b54f5ba97abbac485f0891a4aaab3bcf6c28da79fea884","last_reissued_at":"2026-07-05T08:23:37.259132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:37.259132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Cross-Dataset Study for Text-based 3D Human Motion Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"G\\\"ul Varol, L\\'eore Bensabath, Mathis Petrovich","submitted_at":"2024-05-27T07:58:20Z","abstract_excerpt":"We provide results of our study on text-based 3D human motion retrieval and particularly focus on cross-dataset generalization. Due to practical reasons such as dataset-specific human body representations, existing works typically benchmarkby training and testing on partitions from the same dataset. Here, we employ a unified SMPL body format for all datasets, which allows us to perform training on one dataset, testing on the other, as well as training on a combination of datasets. Our results suggest that there exist dataset biases in standard text-motion benchmarks such as HumanML3D, KIT Moti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16909","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/2405.16909/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.16909","created_at":"2026-07-05T08:23:37.259202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16909v1","created_at":"2026-07-05T08:23:37.259202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16909","created_at":"2026-07-05T08:23:37.259202+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KRWGZSFJRKM","created_at":"2026-07-05T08:23:37.259202+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KRWGZSFJRKMPKNV","created_at":"2026-07-05T08:23:37.259202+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KRWGZSF","created_at":"2026-07-05T08:23:37.259202+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.13555","citing_title":"HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KRWGZSFJRKMPKNVJ5N2S6V3VR","json":"https://pith.science/pith/6KRWGZSFJRKMPKNVJ5N2S6V3VR.json","graph_json":"https://pith.science/api/pith-number/6KRWGZSFJRKMPKNVJ5N2S6V3VR/graph.json","events_json":"https://pith.science/api/pith-number/6KRWGZSFJRKMPKNVJ5N2S6V3VR/events.json","paper":"https://pith.science/paper/6KRWGZSF"},"agent_actions":{"view_html":"https://pith.science/pith/6KRWGZSFJRKMPKNVJ5N2S6V3VR","download_json":"https://pith.science/pith/6KRWGZSFJRKMPKNVJ5N2S6V3VR.json","view_paper":"https://pith.science/paper/6KRWGZSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16909&json=true","fetch_graph":"https://pith.science/api/pith-number/6KRWGZSFJRKMPKNVJ5N2S6V3VR/graph.json","fetch_events":"https://pith.science/api/pith-number/6KRWGZSFJRKMPKNVJ5N2S6V3VR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KRWGZSFJRKMPKNVJ5N2S6V3VR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KRWGZSFJRKMPKNVJ5N2S6V3VR/action/storage_attestation","attest_author":"https://pith.science/pith/6KRWGZSFJRKMPKNVJ5N2S6V3VR/action/author_attestation","sign_citation":"https://pith.science/pith/6KRWGZSFJRKMPKNVJ5N2S6V3VR/action/citation_signature","submit_replication":"https://pith.science/pith/6KRWGZSFJRKMPKNVJ5N2S6V3VR/action/replication_record"}},"created_at":"2026-07-05T08:23:37.259202+00:00","updated_at":"2026-07-05T08:23:37.259202+00:00"}