{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CIBPJGK2ENCZFJLMIWWUGFZVPG","short_pith_number":"pith:CIBPJGK2","schema_version":"1.0","canonical_sha256":"1202f4995a234592a56c45ad43173579bf69dc43dc52167b27c7fcfc8f166a01","source":{"kind":"arxiv","id":"2310.20323","version":2},"attestation_state":"computed","paper":{"title":"SemanticBoost: Elevating Motion Generation with Augmented Textual Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.HC"],"primary_cat":"cs.CV","authors_text":"Chao Weng, Shaoli Huang, Xiaohang Zhan, Xin He, Ying Shan","submitted_at":"2023-10-31T09:58:11Z","abstract_excerpt":"Current techniques face difficulties in generating motions from intricate semantic descriptions, primarily due to insufficient semantic annotations in datasets and weak contextual understanding. To address these issues, we present SemanticBoost, a novel framework that tackles both challenges simultaneously. Our framework comprises a Semantic Enhancement module and a Context-Attuned Motion Denoiser (CAMD). The Semantic Enhancement module extracts supplementary semantics from motion data, enriching the dataset's textual description and ensuring precise alignment between text and motion data with"},"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":"2310.20323","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-31T09:58:11Z","cross_cats_sorted":["cs.AI","cs.GR","cs.HC"],"title_canon_sha256":"270be169c64fef47aad29cc451d268d54482ff73514f9a32441777aa74e7a283","abstract_canon_sha256":"195ab9401024d66943bb54f4f3ab390f9b56a64e785df0b92db82ad5a90bf978"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:33.505859Z","signature_b64":"KD0Y/CLQ2gYSSpNz6GQ8xUGTF91UTWgptclADEJfvOU3DkzXTR/5k4oqPUVHY6z/9TKKO8ffYhWL9SgQ78DDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1202f4995a234592a56c45ad43173579bf69dc43dc52167b27c7fcfc8f166a01","last_reissued_at":"2026-07-05T07:17:33.505367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:33.505367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemanticBoost: Elevating Motion Generation with Augmented Textual Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.HC"],"primary_cat":"cs.CV","authors_text":"Chao Weng, Shaoli Huang, Xiaohang Zhan, Xin He, Ying Shan","submitted_at":"2023-10-31T09:58:11Z","abstract_excerpt":"Current techniques face difficulties in generating motions from intricate semantic descriptions, primarily due to insufficient semantic annotations in datasets and weak contextual understanding. To address these issues, we present SemanticBoost, a novel framework that tackles both challenges simultaneously. Our framework comprises a Semantic Enhancement module and a Context-Attuned Motion Denoiser (CAMD). The Semantic Enhancement module extracts supplementary semantics from motion data, enriching the dataset's textual description and ensuring precise alignment between text and motion data with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20323","kind":"arxiv","version":2},"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/2310.20323/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":"2310.20323","created_at":"2026-07-05T07:17:33.505426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.20323v2","created_at":"2026-07-05T07:17:33.505426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20323","created_at":"2026-07-05T07:17:33.505426+00:00"},{"alias_kind":"pith_short_12","alias_value":"CIBPJGK2ENCZ","created_at":"2026-07-05T07:17:33.505426+00:00"},{"alias_kind":"pith_short_16","alias_value":"CIBPJGK2ENCZFJLM","created_at":"2026-07-05T07:17:33.505426+00:00"},{"alias_kind":"pith_short_8","alias_value":"CIBPJGK2","created_at":"2026-07-05T07:17:33.505426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18956","citing_title":"MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13729","citing_title":"Coordinating Multiple Conditions for Trajectory-Controlled Human Motion Generation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CIBPJGK2ENCZFJLMIWWUGFZVPG","json":"https://pith.science/pith/CIBPJGK2ENCZFJLMIWWUGFZVPG.json","graph_json":"https://pith.science/api/pith-number/CIBPJGK2ENCZFJLMIWWUGFZVPG/graph.json","events_json":"https://pith.science/api/pith-number/CIBPJGK2ENCZFJLMIWWUGFZVPG/events.json","paper":"https://pith.science/paper/CIBPJGK2"},"agent_actions":{"view_html":"https://pith.science/pith/CIBPJGK2ENCZFJLMIWWUGFZVPG","download_json":"https://pith.science/pith/CIBPJGK2ENCZFJLMIWWUGFZVPG.json","view_paper":"https://pith.science/paper/CIBPJGK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.20323&json=true","fetch_graph":"https://pith.science/api/pith-number/CIBPJGK2ENCZFJLMIWWUGFZVPG/graph.json","fetch_events":"https://pith.science/api/pith-number/CIBPJGK2ENCZFJLMIWWUGFZVPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CIBPJGK2ENCZFJLMIWWUGFZVPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CIBPJGK2ENCZFJLMIWWUGFZVPG/action/storage_attestation","attest_author":"https://pith.science/pith/CIBPJGK2ENCZFJLMIWWUGFZVPG/action/author_attestation","sign_citation":"https://pith.science/pith/CIBPJGK2ENCZFJLMIWWUGFZVPG/action/citation_signature","submit_replication":"https://pith.science/pith/CIBPJGK2ENCZFJLMIWWUGFZVPG/action/replication_record"}},"created_at":"2026-07-05T07:17:33.505426+00:00","updated_at":"2026-07-05T07:17:33.505426+00:00"}