{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VRGWINNQSKFHXZGUNY7MGH52CH","short_pith_number":"pith:VRGWINNQ","canonical_record":{"source":{"id":"2109.02823","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-07T02:26:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6b921846eac7863b15f85a24c9aba41600188413b51273dad33ef4d23cbfbef4","abstract_canon_sha256":"715690546c72f7b8f6db58cb598154e56f86b4dbfa7bad2f5aab0fd83824ab58"},"schema_version":"1.0"},"canonical_sha256":"ac4d6435b0928a7be4d46e3ec31fba11d26013108aa8c62590d72d309d3ae48d","source":{"kind":"arxiv","id":"2109.02823","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02823","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02823v3","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02823","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"pith_short_12","alias_value":"VRGWINNQSKFH","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"pith_short_16","alias_value":"VRGWINNQSKFHXZGU","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"pith_short_8","alias_value":"VRGWINNQ","created_at":"2026-07-05T05:47:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VRGWINNQSKFHXZGUNY7MGH52CH","target":"record","payload":{"canonical_record":{"source":{"id":"2109.02823","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-07T02:26:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6b921846eac7863b15f85a24c9aba41600188413b51273dad33ef4d23cbfbef4","abstract_canon_sha256":"715690546c72f7b8f6db58cb598154e56f86b4dbfa7bad2f5aab0fd83824ab58"},"schema_version":"1.0"},"canonical_sha256":"ac4d6435b0928a7be4d46e3ec31fba11d26013108aa8c62590d72d309d3ae48d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:55.830656Z","signature_b64":"kW55SWZVZ1qAugZuDgv8+gJZgpMm6uinEAiPeUSzSvzVnt8soh0DqG66+3RWvyZ3zIkjmNeEFbXyLlPPrMzdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac4d6435b0928a7be4d46e3ec31fba11d26013108aa8c62590d72d309d3ae48d","last_reissued_at":"2026-07-05T05:47:55.830112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:55.830112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.02823","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:47:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jk1DEre1OrIAr9yGCJLMfd+qVI3Fys91OrFcV3PPN+1Q8Du6GB0AE2PT8hwbVV6r592IOc5LEEVj1ZC87UQaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:44:58.441786Z"},"content_sha256":"b7765d7600bbe1bd34933fb1e6e32937cfbf0f1f57313caeaf4cf2e8e0250165","schema_version":"1.0","event_id":"sha256:b7765d7600bbe1bd34933fb1e6e32937cfbf0f1f57313caeaf4cf2e8e0250165"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VRGWINNQSKFHXZGUNY7MGH52CH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Visual-Audio Representations for Voice-Controlled Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"D. Livingston McPherson, Katherine Driggs-Campbell, Peixin Chang, Shuijing Liu","submitted_at":"2021-09-07T02:26:54Z","abstract_excerpt":"Based on the recent advancements in representation learning, we propose a novel pipeline for task-oriented voice-controlled robots with raw sensor inputs. Previous methods rely on a large number of labels and task-specific reward functions. Not only can such an approach hardly be improved after the deployment, but also has limited generalization across robotic platforms and tasks. To address these problems, our pipeline first learns a visual-audio representation (VAR) that associates images and sound commands. Then the robot learns to fulfill the sound command via reinforcement learning using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02823","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/2109.02823/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":"2026-07-05T05:47:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yRfO419P6ZSisJyoDu5YwyM+sqVxAaHoI9P0HcA5Tl+TEXuBJgsTP3KNgnQoVZtaWLj/q3UBG++6rIw40KMtAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:44:58.442695Z"},"content_sha256":"d2cd712f927018840e194ccf44e15538ac3f25b5f04e4eb5e4ba3bad18993d77","schema_version":"1.0","event_id":"sha256:d2cd712f927018840e194ccf44e15538ac3f25b5f04e4eb5e4ba3bad18993d77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VRGWINNQSKFHXZGUNY7MGH52CH/bundle.json","state_url":"https://pith.science/pith/VRGWINNQSKFHXZGUNY7MGH52CH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VRGWINNQSKFHXZGUNY7MGH52CH/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":"2026-08-03T17:44:58Z","links":{"resolver":"https://pith.science/pith/VRGWINNQSKFHXZGUNY7MGH52CH","bundle":"https://pith.science/pith/VRGWINNQSKFHXZGUNY7MGH52CH/bundle.json","state":"https://pith.science/pith/VRGWINNQSKFHXZGUNY7MGH52CH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VRGWINNQSKFHXZGUNY7MGH52CH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VRGWINNQSKFHXZGUNY7MGH52CH","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":"715690546c72f7b8f6db58cb598154e56f86b4dbfa7bad2f5aab0fd83824ab58","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-07T02:26:54Z","title_canon_sha256":"6b921846eac7863b15f85a24c9aba41600188413b51273dad33ef4d23cbfbef4"},"schema_version":"1.0","source":{"id":"2109.02823","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02823","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02823v3","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02823","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"pith_short_12","alias_value":"VRGWINNQSKFH","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"pith_short_16","alias_value":"VRGWINNQSKFHXZGU","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"pith_short_8","alias_value":"VRGWINNQ","created_at":"2026-07-05T05:47:55Z"}],"graph_snapshots":[{"event_id":"sha256:d2cd712f927018840e194ccf44e15538ac3f25b5f04e4eb5e4ba3bad18993d77","target":"graph","created_at":"2026-07-05T05:47:55Z","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/2109.02823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Based on the recent advancements in representation learning, we propose a novel pipeline for task-oriented voice-controlled robots with raw sensor inputs. Previous methods rely on a large number of labels and task-specific reward functions. Not only can such an approach hardly be improved after the deployment, but also has limited generalization across robotic platforms and tasks. To address these problems, our pipeline first learns a visual-audio representation (VAR) that associates images and sound commands. Then the robot learns to fulfill the sound command via reinforcement learning using ","authors_text":"D. Livingston McPherson, Katherine Driggs-Campbell, Peixin Chang, Shuijing Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-07T02:26:54Z","title":"Learning Visual-Audio Representations for Voice-Controlled Robots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02823","kind":"arxiv","version":3},"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:b7765d7600bbe1bd34933fb1e6e32937cfbf0f1f57313caeaf4cf2e8e0250165","target":"record","created_at":"2026-07-05T05:47:55Z","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":"715690546c72f7b8f6db58cb598154e56f86b4dbfa7bad2f5aab0fd83824ab58","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-07T02:26:54Z","title_canon_sha256":"6b921846eac7863b15f85a24c9aba41600188413b51273dad33ef4d23cbfbef4"},"schema_version":"1.0","source":{"id":"2109.02823","kind":"arxiv","version":3}},"canonical_sha256":"ac4d6435b0928a7be4d46e3ec31fba11d26013108aa8c62590d72d309d3ae48d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac4d6435b0928a7be4d46e3ec31fba11d26013108aa8c62590d72d309d3ae48d","first_computed_at":"2026-07-05T05:47:55.830112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:55.830112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kW55SWZVZ1qAugZuDgv8+gJZgpMm6uinEAiPeUSzSvzVnt8soh0DqG66+3RWvyZ3zIkjmNeEFbXyLlPPrMzdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:55.830656Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.02823","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7765d7600bbe1bd34933fb1e6e32937cfbf0f1f57313caeaf4cf2e8e0250165","sha256:d2cd712f927018840e194ccf44e15538ac3f25b5f04e4eb5e4ba3bad18993d77"],"state_sha256":"bb78bd347e8e85122bf304d8aae53bc58531c1cdcbc20ce5346e79468e9cee14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HjNI3P2dqFubeBCo16I9r2eu0SfQzeW0E0uzVwU7tNIqMrR3SM2EnXUmG/kGghGERV+sYxk/T1MYE/FP8NEBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:44:58.446765Z","bundle_sha256":"52661ba1dbe58e40352db00a2cddfe4a3aefd09677d65461cb032ab382642142"}}