{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GJA3ROWMBE7U6PGMYRMDWRKZYP","short_pith_number":"pith:GJA3ROWM","schema_version":"1.0","canonical_sha256":"3241b8bacc093f4f3cccc4583b4559c3e85d51a0a273b2d49dd97fad6d0ad32d","source":{"kind":"arxiv","id":"2306.07580","version":3},"attestation_state":"computed","paper":{"title":"SayTap: Language to Quadrupedal Locomotion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aleksandra Faust, Heiga Zen, Jie Tan, Tatsuya Harada, Wenhao Yu, Yujin Tang","submitted_at":"2023-06-13T07:09:11Z","abstract_excerpt":"Large language models (LLMs) have demonstrated the potential to perform high-level planning. Yet, it remains a challenge for LLMs to comprehend low-level commands, such as joint angle targets or motor torques. This paper proposes an approach to use foot contact patterns as an interface that bridges human commands in natural language and a locomotion controller that outputs these low-level commands. This results in an interactive system for quadrupedal robots that allows the users to craft diverse locomotion behaviors flexibly. We contribute an LLM prompt design, a reward function, and a method"},"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":"2306.07580","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-06-13T07:09:11Z","cross_cats_sorted":[],"title_canon_sha256":"e45c54da8403675950b0a31fe8aa6482a5f68fcf563414441f5f0e92683a2334","abstract_canon_sha256":"8bb04ec0d68f743fa9fb7186a100ad67553c70b5a40264638a6c35bc50a7700e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:40.883880Z","signature_b64":"59ed2ZM3qCzNuT82rxNpHwAWr2GRNdnfj32D7+3Xu+teogOw5O9OjHTj9NmP8HCham7FUkZfWCYf1u5IZtQ3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3241b8bacc093f4f3cccc4583b4559c3e85d51a0a273b2d49dd97fad6d0ad32d","last_reissued_at":"2026-07-05T06:50:40.883220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:40.883220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SayTap: Language to Quadrupedal Locomotion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aleksandra Faust, Heiga Zen, Jie Tan, Tatsuya Harada, Wenhao Yu, Yujin Tang","submitted_at":"2023-06-13T07:09:11Z","abstract_excerpt":"Large language models (LLMs) have demonstrated the potential to perform high-level planning. Yet, it remains a challenge for LLMs to comprehend low-level commands, such as joint angle targets or motor torques. This paper proposes an approach to use foot contact patterns as an interface that bridges human commands in natural language and a locomotion controller that outputs these low-level commands. This results in an interactive system for quadrupedal robots that allows the users to craft diverse locomotion behaviors flexibly. We contribute an LLM prompt design, a reward function, and a method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07580","kind":"arxiv","version":3},"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/2306.07580/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":"2306.07580","created_at":"2026-07-05T06:50:40.883293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07580v3","created_at":"2026-07-05T06:50:40.883293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07580","created_at":"2026-07-05T06:50:40.883293+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJA3ROWMBE7U","created_at":"2026-07-05T06:50:40.883293+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJA3ROWMBE7U6PGM","created_at":"2026-07-05T06:50:40.883293+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJA3ROWM","created_at":"2026-07-05T06:50:40.883293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30719","citing_title":"When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30719","citing_title":"When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02911","citing_title":"Learning Task-Invariant Properties via Dreamer: Enabling Efficient Policy Transfer for Quadruped Robots","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJA3ROWMBE7U6PGMYRMDWRKZYP","json":"https://pith.science/pith/GJA3ROWMBE7U6PGMYRMDWRKZYP.json","graph_json":"https://pith.science/api/pith-number/GJA3ROWMBE7U6PGMYRMDWRKZYP/graph.json","events_json":"https://pith.science/api/pith-number/GJA3ROWMBE7U6PGMYRMDWRKZYP/events.json","paper":"https://pith.science/paper/GJA3ROWM"},"agent_actions":{"view_html":"https://pith.science/pith/GJA3ROWMBE7U6PGMYRMDWRKZYP","download_json":"https://pith.science/pith/GJA3ROWMBE7U6PGMYRMDWRKZYP.json","view_paper":"https://pith.science/paper/GJA3ROWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07580&json=true","fetch_graph":"https://pith.science/api/pith-number/GJA3ROWMBE7U6PGMYRMDWRKZYP/graph.json","fetch_events":"https://pith.science/api/pith-number/GJA3ROWMBE7U6PGMYRMDWRKZYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJA3ROWMBE7U6PGMYRMDWRKZYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJA3ROWMBE7U6PGMYRMDWRKZYP/action/storage_attestation","attest_author":"https://pith.science/pith/GJA3ROWMBE7U6PGMYRMDWRKZYP/action/author_attestation","sign_citation":"https://pith.science/pith/GJA3ROWMBE7U6PGMYRMDWRKZYP/action/citation_signature","submit_replication":"https://pith.science/pith/GJA3ROWMBE7U6PGMYRMDWRKZYP/action/replication_record"}},"created_at":"2026-07-05T06:50:40.883293+00:00","updated_at":"2026-07-05T06:50:40.883293+00:00"}