{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CRF3XW4CZSIB4LPIM64TCZL7U3","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":"cf3a4d4e007f7086358661c7978ce4a9ccf331de62182feefc7c33d01517ec66","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-04-02T13:25:16Z","title_canon_sha256":"3600a406a3ed0bdb9c45360bf4b35e84d8cbe549c31eeee96f367833c8b40c24"},"schema_version":"1.0","source":{"id":"2404.01932","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01932","created_at":"2026-07-05T11:11:20Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01932v2","created_at":"2026-07-05T11:11:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01932","created_at":"2026-07-05T11:11:20Z"},{"alias_kind":"pith_short_12","alias_value":"CRF3XW4CZSIB","created_at":"2026-07-05T11:11:20Z"},{"alias_kind":"pith_short_16","alias_value":"CRF3XW4CZSIB4LPI","created_at":"2026-07-05T11:11:20Z"},{"alias_kind":"pith_short_8","alias_value":"CRF3XW4C","created_at":"2026-07-05T11:11:20Z"}],"graph_snapshots":[{"event_id":"sha256:c4dca52d3fa829e788aee02436ba1c7e1a6e67f78424dad5c516598934f112b1","target":"graph","created_at":"2026-07-05T11:11:20Z","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/2404.01932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we focus on unsupervised vision-language-action mapping in the area of robotic manipulation. Recently, multiple approaches employing pre-trained large language and vision models have been proposed for this task. However, they are computationally demanding and require careful fine-tuning of the produced outputs. A more lightweight alternative would be the implementation of multimodal Variational Autoencoders (VAEs) which can extract the latent features of the data and integrate them into a joint representation, as has been demonstrated mostly on image-image or image-text data for ","authors_text":"Gabriela Sejnova, Karla Stepanova, Michal Vavrecka","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-04-02T13:25:16Z","title":"Bridging Language, Vision and Action: Multimodal VAEs in Robotic Manipulation Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01932","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":"sha256:9ca26a4cd297a98cdf558ad44df877b43780707311faffbe00e1a2af06c79ef5","target":"record","created_at":"2026-07-05T11:11:20Z","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":"cf3a4d4e007f7086358661c7978ce4a9ccf331de62182feefc7c33d01517ec66","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-04-02T13:25:16Z","title_canon_sha256":"3600a406a3ed0bdb9c45360bf4b35e84d8cbe549c31eeee96f367833c8b40c24"},"schema_version":"1.0","source":{"id":"2404.01932","kind":"arxiv","version":2}},"canonical_sha256":"144bbbdb82cc901e2de867b931657fa6d1d1c212d3933ca09b389b31bd4a9450","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"144bbbdb82cc901e2de867b931657fa6d1d1c212d3933ca09b389b31bd4a9450","first_computed_at":"2026-07-05T11:11:20.284429Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:20.284429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6mQxPrCwFLim1ZxrP1VlvX0ORmC6nyN7LNPPSuzU0jtpBJNk4K79na2SluqsjbdG4GvTz0oepGRqkwPf07+GCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:20.284913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01932","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ca26a4cd297a98cdf558ad44df877b43780707311faffbe00e1a2af06c79ef5","sha256:c4dca52d3fa829e788aee02436ba1c7e1a6e67f78424dad5c516598934f112b1"],"state_sha256":"b2b7ee2f85d9ef725edb52d6eb7d1df215f3664bc70901dfca26e9516e81f93e"}