{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:L6K6I3ODKSGO55PCQH6S66IVXB","short_pith_number":"pith:L6K6I3OD","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"},"canonical_sha256":"5f95e46dc3548ceef5e281fd2f7915b840d14c8ac520eedd0f898905bbf37c3c","source":{"kind":"arxiv","id":"2306.15644","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15644","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15644v1","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15644","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"pith_short_12","alias_value":"L6K6I3ODKSGO","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"pith_short_16","alias_value":"L6K6I3ODKSGO55PC","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"pith_short_8","alias_value":"L6K6I3OD","created_at":"2026-07-05T06:25:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:L6K6I3ODKSGO55PCQH6S66IVXB","target":"record","payload":{"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"},"canonical_sha256":"5f95e46dc3548ceef5e281fd2f7915b840d14c8ac520eedd0f898905bbf37c3c","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"},"source_kind":"arxiv","source_id":"2306.15644","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:25:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JIzI7Vtts0Ngn2kcXRU7tIjmb7g06Nd3clhZ9mWY3b0XJTNELvATwdzc7C6aIUM7uA5s1L7RjmL2K6SJxy2bBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:40:39.398969Z"},"content_sha256":"1cebfb08ebc466ace46be5bc99d8bcc30c37449893e874b3c89cdd0be2735b6b","schema_version":"1.0","event_id":"sha256:1cebfb08ebc466ace46be5bc99d8bcc30c37449893e874b3c89cdd0be2735b6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:L6K6I3ODKSGO55PCQH6S66IVXB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:25:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"elH0DjbECEl+v1T97XMeAI+SZi6Ex8pcxBybmmeA2fxTzdCnPTxVcW1rZu4qgdyPeACvKFvbvG6LPgb4y5LfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:40:39.399356Z"},"content_sha256":"ed857f0c9ffef1789cd6040260793358d637448274e15d4a00682770e70383bc","schema_version":"1.0","event_id":"sha256:ed857f0c9ffef1789cd6040260793358d637448274e15d4a00682770e70383bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB/bundle.json","state_url":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L6K6I3ODKSGO55PCQH6S66IVXB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T15:40:39Z","links":{"resolver":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB","bundle":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB/bundle.json","state":"https://pith.science/pith/L6K6I3ODKSGO55PCQH6S66IVXB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L6K6I3ODKSGO55PCQH6S66IVXB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:L6K6I3ODKSGO55PCQH6S66IVXB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3a6a2466cb522782de66010e952e96e2ff3b265f7f43b9fc88490c799c796b07","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T17:37:53Z","title_canon_sha256":"bccba81243ae189c325c3169e6183f97728e96a861b9d513eedaf74139af8d1d"},"schema_version":"1.0","source":{"id":"2306.15644","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15644","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15644v1","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15644","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"pith_short_12","alias_value":"L6K6I3ODKSGO","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"pith_short_16","alias_value":"L6K6I3ODKSGO55PC","created_at":"2026-07-05T06:25:35Z"},{"alias_kind":"pith_short_8","alias_value":"L6K6I3OD","created_at":"2026-07-05T06:25:35Z"}],"graph_snapshots":[{"event_id":"sha256:ed857f0c9ffef1789cd6040260793358d637448274e15d4a00682770e70383bc","target":"graph","created_at":"2026-07-05T06:25:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.15644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chiori Hori, David Harwath, Devesh Jha, Diego Romeres, Jonathan Le Roux, Kei Ota, Puyuan Peng, Radu Corcodel, Siddarth Jain, Xinyu Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T17:37:53Z","title":"Style-transfer based Speech and Audio-visual Scene Understanding for Robot Action Sequence Acquisition from Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15644","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1cebfb08ebc466ace46be5bc99d8bcc30c37449893e874b3c89cdd0be2735b6b","target":"record","created_at":"2026-07-05T06:25:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3a6a2466cb522782de66010e952e96e2ff3b265f7f43b9fc88490c799c796b07","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T17:37:53Z","title_canon_sha256":"bccba81243ae189c325c3169e6183f97728e96a861b9d513eedaf74139af8d1d"},"schema_version":"1.0","source":{"id":"2306.15644","kind":"arxiv","version":1}},"canonical_sha256":"5f95e46dc3548ceef5e281fd2f7915b840d14c8ac520eedd0f898905bbf37c3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f95e46dc3548ceef5e281fd2f7915b840d14c8ac520eedd0f898905bbf37c3c","first_computed_at":"2026-07-05T06:25:35.225986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:25:35.225986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jj9WupFy58rzaLIYj4K/kTeenCs3+dUrcxQZDiE/fHhQ1nCOhp0L8kDj3erEM7k+JNHVmljIiI4WqZTDTrhcCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:25:35.226432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.15644","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cebfb08ebc466ace46be5bc99d8bcc30c37449893e874b3c89cdd0be2735b6b","sha256:ed857f0c9ffef1789cd6040260793358d637448274e15d4a00682770e70383bc"],"state_sha256":"1b317eb414ceaf2b4e0534c1d26809869dedd3d276414aeed822a18cef19ca58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZKLFooYEEomfXYHv8h2KPfFnO55BIeLd5r+KxMh4UG/uYPE65x8FJKkqPJm05EVn9T5NICk//nsPk7/LZdpBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:40:39.401357Z","bundle_sha256":"36325073ecae878c8958987c52e65a0a1f3fd5573f61de390a08b983d404ff46"}}