{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L6K6I3ODKSGO55PCQH6S66IVXB","short_pith_number":"pith:L6K6I3OD","schema_version":"1.0","canonical_sha256":"5f95e46dc3548ceef5e281fd2f7915b840d14c8ac520eedd0f898905bbf37c3c","source":{"kind":"arxiv","id":"2306.15644","version":1},"attestation_state":"computed","paper":{"title":"Style-transfer based Speech and Audio-visual Scene Understanding for Robot Action Sequence Acquisition from Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chiori Hori, David Harwath, Devesh Jha, Diego Romeres, Jonathan Le Roux, Kei Ota, Puyuan Peng, Radu Corcodel, Siddarth Jain, Xinyu Liu","submitted_at":"2023-06-27T17:37:53Z","abstract_excerpt":"To realize human-robot collaboration, robots need to execute actions for new tasks according to human instructions given finite prior knowledge. Human experts can share their knowledge of how to perform a task with a robot through multi-modal instructions in their demonstrations, showing a sequence of short-horizon steps to achieve a long-horizon goal. This paper introduces a method for robot action sequence generation from instruction videos using (1) an audio-visual Transformer that converts audio-visual features and instruction speech to a sequence of robot actions called dynamic movement p"},"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":"2306.15644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T17:37:53Z","cross_cats_sorted":[],"title_canon_sha256":"bccba81243ae189c325c3169e6183f97728e96a861b9d513eedaf74139af8d1d","abstract_canon_sha256":"3a6a2466cb522782de66010e952e96e2ff3b265f7f43b9fc88490c799c796b07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:35.226432Z","signature_b64":"jj9WupFy58rzaLIYj4K/kTeenCs3+dUrcxQZDiE/fHhQ1nCOhp0L8kDj3erEM7k+JNHVmljIiI4WqZTDTrhcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f95e46dc3548ceef5e281fd2f7915b840d14c8ac520eedd0f898905bbf37c3c","last_reissued_at":"2026-07-05T06:25:35.225986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:35.225986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Style-transfer based Speech and Audio-visual Scene Understanding for Robot Action Sequence Acquisition from Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chiori Hori, David Harwath, Devesh Jha, Diego Romeres, Jonathan Le Roux, Kei Ota, Puyuan Peng, Radu Corcodel, Siddarth Jain, Xinyu Liu","submitted_at":"2023-06-27T17:37:53Z","abstract_excerpt":"To realize human-robot collaboration, robots need to execute actions for new tasks according to human instructions given finite prior knowledge. Human experts can share their knowledge of how to perform a task with a robot through multi-modal instructions in their demonstrations, showing a sequence of short-horizon steps to achieve a long-horizon goal. This paper introduces a method for robot action sequence generation from instruction videos using (1) an audio-visual Transformer that converts audio-visual features and instruction speech to a sequence of robot actions called dynamic movement p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15644","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/2306.15644/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":"2306.15644","created_at":"2026-07-05T06:25:35.226043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.15644v1","created_at":"2026-07-05T06:25:35.226043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15644","created_at":"2026-07-05T06:25:35.226043+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6K6I3ODKSGO","created_at":"2026-07-05T06:25:35.226043+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6K6I3ODKSGO55PC","created_at":"2026-07-05T06:25:35.226043+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6K6I3OD","created_at":"2026-07-05T06:25:35.226043+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/L6K6I3ODKSGO55PCQH6S66IVXB","json":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB.json","graph_json":"https://pith.science/api/pith-number/L6K6I3ODKSGO55PCQH6S66IVXB/graph.json","events_json":"https://pith.science/api/pith-number/L6K6I3ODKSGO55PCQH6S66IVXB/events.json","paper":"https://pith.science/paper/L6K6I3OD"},"agent_actions":{"view_html":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB","download_json":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB.json","view_paper":"https://pith.science/paper/L6K6I3OD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.15644&json=true","fetch_graph":"https://pith.science/api/pith-number/L6K6I3ODKSGO55PCQH6S66IVXB/graph.json","fetch_events":"https://pith.science/api/pith-number/L6K6I3ODKSGO55PCQH6S66IVXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB/action/storage_attestation","attest_author":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB/action/author_attestation","sign_citation":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB/action/citation_signature","submit_replication":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB/action/replication_record"}},"created_at":"2026-07-05T06:25:35.226043+00:00","updated_at":"2026-07-05T06:25:35.226043+00:00"}