{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:D324RSQRML5XPIOVUTEW3MVT77","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":"8f73016eb52db8100810f33e274fde137737c615e4dc1fb192d7d2b14a0e2ca3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-01-23T22:40:18Z","title_canon_sha256":"b278b18c617791e23cbfca2b743be9a37e9436a25e8ca363d6bd8d5f3cc92709"},"schema_version":"1.0","source":{"id":"2301.09749","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.09749","created_at":"2026-07-05T07:01:24Z"},{"alias_kind":"arxiv_version","alias_value":"2301.09749v2","created_at":"2026-07-05T07:01:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09749","created_at":"2026-07-05T07:01:24Z"},{"alias_kind":"pith_short_12","alias_value":"D324RSQRML5X","created_at":"2026-07-05T07:01:24Z"},{"alias_kind":"pith_short_16","alias_value":"D324RSQRML5XPIOV","created_at":"2026-07-05T07:01:24Z"},{"alias_kind":"pith_short_8","alias_value":"D324RSQR","created_at":"2026-07-05T07:01:24Z"}],"graph_snapshots":[{"event_id":"sha256:c5c0cb32985ea3efc4d6f49e87dbb2a91e056cfe828a343e95ce45404fc5dec0","target":"graph","created_at":"2026-07-05T07:01:24Z","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/2301.09749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A command-following robot that serves people in everyday life must continually improve itself in deployment domains with minimal help from its end users, instead of engineers. Previous methods are either difficult to continuously improve after the deployment or require a large number of new labels during fine-tuning. Motivated by (self-)supervised contrastive learning, we propose a novel representation that generates an intrinsic reward function for command-following robot tasks by associating images with sound commands. After the robot is deployed in a new domain, the representation can be up","authors_text":"Kaiwen Hong, Katherine Driggs-Campbell, Neeloy Chakraborty, Peixin Chang, Shuijing Liu, Tianchen Ji","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-01-23T22:40:18Z","title":"A Data-Efficient Visual-Audio Representation with Intuitive Fine-tuning for Voice-Controlled Robots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09749","kind":"arxiv","version":2},"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:e0395dace8f4e260ac6facbe028992543f1122e8f5836cb26544f77fe5a7edd8","target":"record","created_at":"2026-07-05T07:01:24Z","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":"8f73016eb52db8100810f33e274fde137737c615e4dc1fb192d7d2b14a0e2ca3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-01-23T22:40:18Z","title_canon_sha256":"b278b18c617791e23cbfca2b743be9a37e9436a25e8ca363d6bd8d5f3cc92709"},"schema_version":"1.0","source":{"id":"2301.09749","kind":"arxiv","version":2}},"canonical_sha256":"1ef5c8ca1162fb77a1d5a4c96db2b3ffdb70a1655a4b9e2b609e105c82814fec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ef5c8ca1162fb77a1d5a4c96db2b3ffdb70a1655a4b9e2b609e105c82814fec","first_computed_at":"2026-07-05T07:01:24.236678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:24.236678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t55wxWVGvSD/htaozTyPux5h4j4E9YxU2CBatQBTyfVEtMe/koJZiLGTggkxiJLCZQ2nO/rO1Xaf32nPx35tBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:24.237171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.09749","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0395dace8f4e260ac6facbe028992543f1122e8f5836cb26544f77fe5a7edd8","sha256:c5c0cb32985ea3efc4d6f49e87dbb2a91e056cfe828a343e95ce45404fc5dec0"],"state_sha256":"8906f6498126835ce465d8ed764dd1c5ff213267196b2f3cca3888bbca69d7bc"}