{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OYKCKVI2FFHNTFXGUX6IKLH6NU","short_pith_number":"pith:OYKCKVI2","schema_version":"1.0","canonical_sha256":"761425551a294ed996e6a5fc852cfe6d1123acab090e71a9163cfed405b5051e","source":{"kind":"arxiv","id":"2209.04066","version":2},"attestation_state":"computed","paper":{"title":"TEACH: Temporal Action Composition for 3D Humans","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"G\\\"ul Varol, Mathis Petrovich, Michael J. Black, Nikos Athanasiou","submitted_at":"2022-09-09T00:33:40Z","abstract_excerpt":"Given a series of natural language descriptions, our task is to generate 3D human motions that correspond semantically to the text, and follow the temporal order of the instructions. In particular, our goal is to enable the synthesis of a series of actions, which we refer to as temporal action composition. The current state of the art in text-conditioned motion synthesis only takes a single action or a single sentence as input. This is partially due to lack of suitable training data containing action sequences, but also due to the computational complexity of their non-autoregressive model form"},"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":"2209.04066","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-09T00:33:40Z","cross_cats_sorted":[],"title_canon_sha256":"9c97a7c91f300e9538fa411c14b7ee3559d9f1d81df7a17984349c22438f2afe","abstract_canon_sha256":"e4a7eb48625a69b891a424894e361e10a467379a548dc8e0da32c71950459d50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:56:21.277492Z","signature_b64":"l6jgnOA0TAWTVvdDjG3FvAd37jE+mvqjxp+DPFio1dxIQVkt13aV9u390nsnLRXht4UBE7YK0bXmRknMt8BbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"761425551a294ed996e6a5fc852cfe6d1123acab090e71a9163cfed405b5051e","last_reissued_at":"2026-07-05T04:56:21.277076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:56:21.277076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TEACH: Temporal Action Composition for 3D Humans","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"G\\\"ul Varol, Mathis Petrovich, Michael J. Black, Nikos Athanasiou","submitted_at":"2022-09-09T00:33:40Z","abstract_excerpt":"Given a series of natural language descriptions, our task is to generate 3D human motions that correspond semantically to the text, and follow the temporal order of the instructions. In particular, our goal is to enable the synthesis of a series of actions, which we refer to as temporal action composition. The current state of the art in text-conditioned motion synthesis only takes a single action or a single sentence as input. This is partially due to lack of suitable training data containing action sequences, but also due to the computational complexity of their non-autoregressive model form"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04066","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/2209.04066/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":"2209.04066","created_at":"2026-07-05T04:56:21.277139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.04066v2","created_at":"2026-07-05T04:56:21.277139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04066","created_at":"2026-07-05T04:56:21.277139+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYKCKVI2FFHN","created_at":"2026-07-05T04:56:21.277139+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYKCKVI2FFHNTFXG","created_at":"2026-07-05T04:56:21.277139+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYKCKVI2","created_at":"2026-07-05T04:56:21.277139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02452","citing_title":"ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYKCKVI2FFHNTFXGUX6IKLH6NU","json":"https://pith.science/pith/OYKCKVI2FFHNTFXGUX6IKLH6NU.json","graph_json":"https://pith.science/api/pith-number/OYKCKVI2FFHNTFXGUX6IKLH6NU/graph.json","events_json":"https://pith.science/api/pith-number/OYKCKVI2FFHNTFXGUX6IKLH6NU/events.json","paper":"https://pith.science/paper/OYKCKVI2"},"agent_actions":{"view_html":"https://pith.science/pith/OYKCKVI2FFHNTFXGUX6IKLH6NU","download_json":"https://pith.science/pith/OYKCKVI2FFHNTFXGUX6IKLH6NU.json","view_paper":"https://pith.science/paper/OYKCKVI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.04066&json=true","fetch_graph":"https://pith.science/api/pith-number/OYKCKVI2FFHNTFXGUX6IKLH6NU/graph.json","fetch_events":"https://pith.science/api/pith-number/OYKCKVI2FFHNTFXGUX6IKLH6NU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYKCKVI2FFHNTFXGUX6IKLH6NU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYKCKVI2FFHNTFXGUX6IKLH6NU/action/storage_attestation","attest_author":"https://pith.science/pith/OYKCKVI2FFHNTFXGUX6IKLH6NU/action/author_attestation","sign_citation":"https://pith.science/pith/OYKCKVI2FFHNTFXGUX6IKLH6NU/action/citation_signature","submit_replication":"https://pith.science/pith/OYKCKVI2FFHNTFXGUX6IKLH6NU/action/replication_record"}},"created_at":"2026-07-05T04:56:21.277139+00:00","updated_at":"2026-07-05T04:56:21.277139+00:00"}