{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2OKDC64RUCNSDJSH4EUXVFMZXM","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":"64e4d86882399f53c62fc5bc5e4339ad34f91d73a8776f31f24f57d53faf55e6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T22:32:49Z","title_canon_sha256":"9d817dc4af6db78fbefa4aee798200cf1fb63808b1dbfbb61692984afceab91b"},"schema_version":"1.0","source":{"id":"2306.04047","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04047","created_at":"2026-07-05T07:28:09Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04047v2","created_at":"2026-07-05T07:28:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04047","created_at":"2026-07-05T07:28:09Z"},{"alias_kind":"pith_short_12","alias_value":"2OKDC64RUCNS","created_at":"2026-07-05T07:28:09Z"},{"alias_kind":"pith_short_16","alias_value":"2OKDC64RUCNSDJSH","created_at":"2026-07-05T07:28:09Z"},{"alias_kind":"pith_short_8","alias_value":"2OKDC64R","created_at":"2026-07-05T07:28:09Z"}],"graph_snapshots":[{"event_id":"sha256:de70cba5dc1da30c0f170fc1d48da3d53146b69e31535fc54d11a1b3adbb9d6d","target":"graph","created_at":"2026-07-05T07:28:09Z","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/2306.04047/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual navigation of an agent towards locating an audio goal is a challenging task especially when the audio is sporadic or the environment is noisy. In this paper, we present CAVEN, a Conversation-based Audio-Visual Embodied Navigation framework in which the agent may interact with a human/oracle for solving the task of navigating to an audio goal. Specifically, CAVEN is modeled as a budget-aware partially observable semi-Markov decision process that implicitly learns the uncertainty in the audio-based navigation policy to decide when and how the agent may interact with the oracle. Our ","authors_text":"Anoop Cherian, Moitreya Chatterjee, Sudipta Paul, Xiulong Liu","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T22:32:49Z","title":"CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04047","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":"sha256:9528a8acc92f596594af27a60aef25e9c86bf1e1367e14de2acb16144f5d7ccb","target":"record","created_at":"2026-07-05T07:28:09Z","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":"64e4d86882399f53c62fc5bc5e4339ad34f91d73a8776f31f24f57d53faf55e6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T22:32:49Z","title_canon_sha256":"9d817dc4af6db78fbefa4aee798200cf1fb63808b1dbfbb61692984afceab91b"},"schema_version":"1.0","source":{"id":"2306.04047","kind":"arxiv","version":2}},"canonical_sha256":"d394317b91a09b21a647e1297a9599bb2752b90e8ddfcd21edfc5f98749d1384","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d394317b91a09b21a647e1297a9599bb2752b90e8ddfcd21edfc5f98749d1384","first_computed_at":"2026-07-05T07:28:09.876699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:09.876699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qO71SCkDCJsisLkI8klQAwEzWTUWFaRE6ldYqg14BWqmGyw3+mqQFxRfpl9E2CF4mcjx9gGxfuNFIWzDw0/kDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:09.877187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04047","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9528a8acc92f596594af27a60aef25e9c86bf1e1367e14de2acb16144f5d7ccb","sha256:de70cba5dc1da30c0f170fc1d48da3d53146b69e31535fc54d11a1b3adbb9d6d"],"state_sha256":"d10a9a21a540f8208954c8072520b393498301f2a22a6e57e542ec4957cf46be"}