{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BXK2VOLTV3II6P4LPNZRXLEEQ2","short_pith_number":"pith:BXK2VOLT","schema_version":"1.0","canonical_sha256":"0dd5aab973aed08f3f8b7b731bac8486a1fa03365e4a8c1b7bb7d1f6f585a3c5","source":{"kind":"arxiv","id":"2606.29208","version":1},"attestation_state":"computed","paper":{"title":"Zero-Gated Language-conditioned Human Motion Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ding Jiang, Guanhui Qiao, Jinqiao Wang, Lu Zhou","submitted_at":"2026-06-28T05:20:10Z","abstract_excerpt":"Pose histories provide the core kinematic evidence for 3D human motion prediction, but they lack explicit high-level semantic guidance. This paper introduces ZGL, a lightweight language-conditioned predictor that uses captions of the observed motion as a semantic prior while preserving a strong motion backbone as the main source of dynamics. We render only the observed poses, generate a one-sentence description with a vision-language model, encode the caption with a frozen CLIP-L text tower, and project it into a small set of conditioning tokens. These tokens are injected into a DCT-based spat"},"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":"2606.29208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T05:20:10Z","cross_cats_sorted":[],"title_canon_sha256":"f2fd6273b607749300a9a723ac24876be0e7a23cac41217a715e4025daa94397","abstract_canon_sha256":"6c82b573683fbc33d33caf67691f31f75b2ebe0f9d8af71e343e25aaebca3374"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:57.270969Z","signature_b64":"YQr5G006GC7+KlRVFIeKU3HeGZvdTWXifsH/8MykYq3Gn0lV3L4hfE2GwX3Ck4WqY9pTTCW8qBBhIZ0znJOICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dd5aab973aed08f3f8b7b731bac8486a1fa03365e4a8c1b7bb7d1f6f585a3c5","last_reissued_at":"2026-06-30T01:17:57.270502Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:57.270502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Gated Language-conditioned Human Motion Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ding Jiang, Guanhui Qiao, Jinqiao Wang, Lu Zhou","submitted_at":"2026-06-28T05:20:10Z","abstract_excerpt":"Pose histories provide the core kinematic evidence for 3D human motion prediction, but they lack explicit high-level semantic guidance. This paper introduces ZGL, a lightweight language-conditioned predictor that uses captions of the observed motion as a semantic prior while preserving a strong motion backbone as the main source of dynamics. We render only the observed poses, generate a one-sentence description with a vision-language model, encode the caption with a frozen CLIP-L text tower, and project it into a small set of conditioning tokens. These tokens are injected into a DCT-based spat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29208","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/2606.29208/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":"2606.29208","created_at":"2026-06-30T01:17:57.270570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29208v1","created_at":"2026-06-30T01:17:57.270570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29208","created_at":"2026-06-30T01:17:57.270570+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXK2VOLTV3II","created_at":"2026-06-30T01:17:57.270570+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXK2VOLTV3II6P4L","created_at":"2026-06-30T01:17:57.270570+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXK2VOLT","created_at":"2026-06-30T01:17:57.270570+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXK2VOLTV3II6P4LPNZRXLEEQ2","json":"https://pith.science/pith/BXK2VOLTV3II6P4LPNZRXLEEQ2.json","graph_json":"https://pith.science/api/pith-number/BXK2VOLTV3II6P4LPNZRXLEEQ2/graph.json","events_json":"https://pith.science/api/pith-number/BXK2VOLTV3II6P4LPNZRXLEEQ2/events.json","paper":"https://pith.science/paper/BXK2VOLT"},"agent_actions":{"view_html":"https://pith.science/pith/BXK2VOLTV3II6P4LPNZRXLEEQ2","download_json":"https://pith.science/pith/BXK2VOLTV3II6P4LPNZRXLEEQ2.json","view_paper":"https://pith.science/paper/BXK2VOLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29208&json=true","fetch_graph":"https://pith.science/api/pith-number/BXK2VOLTV3II6P4LPNZRXLEEQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/BXK2VOLTV3II6P4LPNZRXLEEQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXK2VOLTV3II6P4LPNZRXLEEQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXK2VOLTV3II6P4LPNZRXLEEQ2/action/storage_attestation","attest_author":"https://pith.science/pith/BXK2VOLTV3II6P4LPNZRXLEEQ2/action/author_attestation","sign_citation":"https://pith.science/pith/BXK2VOLTV3II6P4LPNZRXLEEQ2/action/citation_signature","submit_replication":"https://pith.science/pith/BXK2VOLTV3II6P4LPNZRXLEEQ2/action/replication_record"}},"created_at":"2026-06-30T01:17:57.270570+00:00","updated_at":"2026-06-30T01:17:57.270570+00:00"}