{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FVEB2KUZ4RH5HPA5YRIYQPNCJ7","short_pith_number":"pith:FVEB2KUZ","schema_version":"1.0","canonical_sha256":"2d481d2a99e44fd3bc1dc451883da24fd822cebb38dd1dee15f6696d03ead198","source":{"kind":"arxiv","id":"1707.05363","version":5},"attestation_state":"computed","paper":{"title":"Auto-Conditioned Recurrent Networks for Extended Complex Human Motion Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chong He, Hao Li, Shuangjiu Xiao, Yi Zhou, Zeng Huang, Zimo Li","submitted_at":"2017-07-17T18:45:29Z","abstract_excerpt":"We present a real-time method for synthesizing highly complex human motions using a novel training regime we call the auto-conditioned Recurrent Neural Network (acRNN). Recently, researchers have attempted to synthesize new motion by using autoregressive techniques, but existing methods tend to freeze or diverge after a couple of seconds due to an accumulation of errors that are fed back into the network. Furthermore, such methods have only been shown to be reliable for relatively simple human motions, such as walking or running. In contrast, our approach can synthesize arbitrary motions 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":"1707.05363","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-17T18:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"ed043a638c46704de620437caf74763e886f56ad3cce51f4ec002746a8db139a","abstract_canon_sha256":"51d4ac642b57942db12411cd858b5f17ac2748e2c84d7e962e779c6cda5f9de5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:11.577959Z","signature_b64":"TOZFO5k/TmOvMOswacjsxKvQa5GNkj78HJ+ihVwByimUG7aYtEdIlXux7SQ2OlAs1yYsqRLaLvObJOvYrgyDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d481d2a99e44fd3bc1dc451883da24fd822cebb38dd1dee15f6696d03ead198","last_reissued_at":"2026-05-18T00:11:11.577145Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:11.577145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auto-Conditioned Recurrent Networks for Extended Complex Human Motion Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chong He, Hao Li, Shuangjiu Xiao, Yi Zhou, Zeng Huang, Zimo Li","submitted_at":"2017-07-17T18:45:29Z","abstract_excerpt":"We present a real-time method for synthesizing highly complex human motions using a novel training regime we call the auto-conditioned Recurrent Neural Network (acRNN). Recently, researchers have attempted to synthesize new motion by using autoregressive techniques, but existing methods tend to freeze or diverge after a couple of seconds due to an accumulation of errors that are fed back into the network. Furthermore, such methods have only been shown to be reliable for relatively simple human motions, such as walking or running. In contrast, our approach can synthesize arbitrary motions with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.05363","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1707.05363","created_at":"2026-05-18T00:11:11.577282+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.05363v5","created_at":"2026-05-18T00:11:11.577282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.05363","created_at":"2026-05-18T00:11:11.577282+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVEB2KUZ4RH5","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVEB2KUZ4RH5HPA5","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVEB2KUZ","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04662","citing_title":"Contact Matrix: Enhancing Dance Motion Synthesis with Precise Interaction Modeling","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FVEB2KUZ4RH5HPA5YRIYQPNCJ7","json":"https://pith.science/pith/FVEB2KUZ4RH5HPA5YRIYQPNCJ7.json","graph_json":"https://pith.science/api/pith-number/FVEB2KUZ4RH5HPA5YRIYQPNCJ7/graph.json","events_json":"https://pith.science/api/pith-number/FVEB2KUZ4RH5HPA5YRIYQPNCJ7/events.json","paper":"https://pith.science/paper/FVEB2KUZ"},"agent_actions":{"view_html":"https://pith.science/pith/FVEB2KUZ4RH5HPA5YRIYQPNCJ7","download_json":"https://pith.science/pith/FVEB2KUZ4RH5HPA5YRIYQPNCJ7.json","view_paper":"https://pith.science/paper/FVEB2KUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.05363&json=true","fetch_graph":"https://pith.science/api/pith-number/FVEB2KUZ4RH5HPA5YRIYQPNCJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/FVEB2KUZ4RH5HPA5YRIYQPNCJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVEB2KUZ4RH5HPA5YRIYQPNCJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVEB2KUZ4RH5HPA5YRIYQPNCJ7/action/storage_attestation","attest_author":"https://pith.science/pith/FVEB2KUZ4RH5HPA5YRIYQPNCJ7/action/author_attestation","sign_citation":"https://pith.science/pith/FVEB2KUZ4RH5HPA5YRIYQPNCJ7/action/citation_signature","submit_replication":"https://pith.science/pith/FVEB2KUZ4RH5HPA5YRIYQPNCJ7/action/replication_record"}},"created_at":"2026-05-18T00:11:11.577282+00:00","updated_at":"2026-05-18T00:11:11.577282+00:00"}