{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MNZEIT74ZTVOBBPFZRALECHCB4","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":"39d35a094555047c384b1fbbb6ece81e8dca3680813b45a148ea355559c71fe4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-14T16:48:53Z","title_canon_sha256":"2764292f7fc22a0acb794737e7de012bf832667aee3b4c0d2c47e49b436082bd"},"schema_version":"1.0","source":{"id":"2307.07468","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07468","created_at":"2026-07-05T08:07:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07468v2","created_at":"2026-07-05T08:07:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07468","created_at":"2026-07-05T08:07:57Z"},{"alias_kind":"pith_short_12","alias_value":"MNZEIT74ZTVO","created_at":"2026-07-05T08:07:57Z"},{"alias_kind":"pith_short_16","alias_value":"MNZEIT74ZTVOBBPF","created_at":"2026-07-05T08:07:57Z"},{"alias_kind":"pith_short_8","alias_value":"MNZEIT74","created_at":"2026-07-05T08:07:57Z"}],"graph_snapshots":[{"event_id":"sha256:677ae8c861bb9903b81187d9b9210b5070bfd1897ddd028beedd36001c0d714e","target":"graph","created_at":"2026-07-05T08:07:57Z","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/2307.07468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The spoken language serves as an accessible and efficient interface, enabling non-experts and disabled users to interact with complex assistant robots. However, accurately grounding language utterances gives a significant challenge due to the acoustic variability in speakers' voices and environmental noise. In this work, we propose a novel speech-scene graph grounding network (SGGNet$^2$) that robustly grounds spoken utterances by leveraging the acoustic similarity between correctly recognized and misrecognized words obtained from automatic speech recognition (ASR) systems. To incorporate the ","authors_text":"Daehyung Park, Dohyun Kim, Jaehwi Jang, Minjae Song, Woojin Choi, Yeseung Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-14T16:48:53Z","title":"SGGNet$^2$: Speech-Scene Graph Grounding Network for Speech-guided Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07468","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":"sha256:9c48874309a553171ac6adbacf2d76a5f2b83daca80c274fe524a8001a83d6e3","target":"record","created_at":"2026-07-05T08:07:57Z","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":"39d35a094555047c384b1fbbb6ece81e8dca3680813b45a148ea355559c71fe4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-14T16:48:53Z","title_canon_sha256":"2764292f7fc22a0acb794737e7de012bf832667aee3b4c0d2c47e49b436082bd"},"schema_version":"1.0","source":{"id":"2307.07468","kind":"arxiv","version":2}},"canonical_sha256":"6372444ffccceae085e5cc40b208e20f1d4208ffea06db0a1368002ad0f9af87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6372444ffccceae085e5cc40b208e20f1d4208ffea06db0a1368002ad0f9af87","first_computed_at":"2026-07-05T08:07:57.252878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:57.252878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4yt1G/uy3x09yFzkeOhLYdGCyx3tzUqDQE1gPkZVVInvdmmMuiHKGJE+FHEczujnEV8ji69CZt+rOL6tNmVGAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:57.253304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.07468","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c48874309a553171ac6adbacf2d76a5f2b83daca80c274fe524a8001a83d6e3","sha256:677ae8c861bb9903b81187d9b9210b5070bfd1897ddd028beedd36001c0d714e"],"state_sha256":"b1d1c18a3d04da696ca75ca0b0dcbcbf5bd77291d33cb0fdafeb1b531023701c"}