{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BNT62Q4E26TGAN7XGI6EVRA3RT","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":"c9ab2fca951bc8b1e355b7bb84bc43f730af8b6df545dd542cbf4706ddd9c397","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-09-12T21:36:58Z","title_canon_sha256":"b033475665a75f447573345395967794038ab0c8f9e56460b9f8c0e5463a1081"},"schema_version":"1.0","source":{"id":"2209.05629","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.05629","created_at":"2026-07-05T07:10:20Z"},{"alias_kind":"arxiv_version","alias_value":"2209.05629v2","created_at":"2026-07-05T07:10:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05629","created_at":"2026-07-05T07:10:20Z"},{"alias_kind":"pith_short_12","alias_value":"BNT62Q4E26TG","created_at":"2026-07-05T07:10:20Z"},{"alias_kind":"pith_short_16","alias_value":"BNT62Q4E26TGAN7X","created_at":"2026-07-05T07:10:20Z"},{"alias_kind":"pith_short_8","alias_value":"BNT62Q4E","created_at":"2026-07-05T07:10:20Z"}],"graph_snapshots":[{"event_id":"sha256:cec372200f7ec19df3b809e355b1b91e52677e87c30ddcf7e95bf0178d8fa6d1","target":"graph","created_at":"2026-07-05T07:10:20Z","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/2209.05629/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Abstract semantic 3D scene understanding is a problem of critical importance in robotics. As robots still lack the common-sense knowledge about household objects and locations of an average human, we investigate the use of pre-trained language models to impart common sense for scene understanding. We introduce and compare a wide range of scene classification paradigms that leverage language only (zero-shot, embedding-based, and structured-language) or vision and language (zero-shot and fine-tuned). We find that the best approaches in both categories yield $\\sim 70\\%$ room classification accura","authors_text":"Luca Carlone, Rajat Talak, Siyi Hu, William Chen","cross_cats":["cs.CL","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-09-12T21:36:58Z","title":"Leveraging Large (Visual) Language Models for Robot 3D Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.05629","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:bd780f23fac196da5027ab3fe368cf581a0dad30d60acd1790f514ec226c38fb","target":"record","created_at":"2026-07-05T07:10:20Z","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":"c9ab2fca951bc8b1e355b7bb84bc43f730af8b6df545dd542cbf4706ddd9c397","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-09-12T21:36:58Z","title_canon_sha256":"b033475665a75f447573345395967794038ab0c8f9e56460b9f8c0e5463a1081"},"schema_version":"1.0","source":{"id":"2209.05629","kind":"arxiv","version":2}},"canonical_sha256":"0b67ed4384d7a66037f7323c4ac41b8cff4f8572b927be83ce653944fb6f40d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b67ed4384d7a66037f7323c4ac41b8cff4f8572b927be83ce653944fb6f40d0","first_computed_at":"2026-07-05T07:10:20.940704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:20.940704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LNCl68AVhTO9oo3+ypHE+WDT2A+NOoClBJwuwb8FAygAAQdKm4wp/HE5b12BEbYXAaBPabVVGfWuvArOJqIfBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:20.941226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.05629","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd780f23fac196da5027ab3fe368cf581a0dad30d60acd1790f514ec226c38fb","sha256:cec372200f7ec19df3b809e355b1b91e52677e87c30ddcf7e95bf0178d8fa6d1"],"state_sha256":"5f129237086ee7a1420e2a9bb25675004590a5cda197f3bf76bd807d7b98458b"}