{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OG6CWJQA6RQKOO4QV3HVELJKNV","short_pith_number":"pith:OG6CWJQA","schema_version":"1.0","canonical_sha256":"71bc2b2600f460a73b90aecf522d2a6d5042350f1c951ebde95d667eb9dc0ce9","source":{"kind":"arxiv","id":"2009.07783","version":3},"attestation_state":"computed","paper":{"title":"Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kyunghyun Cho, Shuhei Kurita","submitted_at":"2020-09-16T16:23:17Z","abstract_excerpt":"Vision-and-language navigation (VLN) is a task in which an agent is embodied in a realistic 3D environment and follows an instruction to reach the goal node. While most of the previous studies have built and investigated a discriminative approach, we notice that there are in fact two possible approaches to building such a VLN agent: discriminative \\textit{and} generative. In this paper, we design and investigate a generative language-grounded policy which uses a language model to compute the distribution over all possible instructions i.e. all possible sequences of vocabulary tokens given acti"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2009.07783","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-16T16:23:17Z","cross_cats_sorted":[],"title_canon_sha256":"ea3c6c562902b8fc1b1c0c8e05772fafcf314d28d828b185a461fcbfd5d2809d","abstract_canon_sha256":"639f2719becbd60057b90733a38fb94a32a51240e3377dd634f61c4fc0edb3a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:20.201953Z","signature_b64":"Ss7ikBpf7P8L2F1G1pqVflXEgaQ+1QnuR4v488Rc5MogaEhCHi/Pipp7y8qrljQsxaN/kYyTY6I6HlY89IF7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71bc2b2600f460a73b90aecf522d2a6d5042350f1c951ebde95d667eb9dc0ce9","last_reissued_at":"2026-07-05T01:41:20.201575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:20.201575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kyunghyun Cho, Shuhei Kurita","submitted_at":"2020-09-16T16:23:17Z","abstract_excerpt":"Vision-and-language navigation (VLN) is a task in which an agent is embodied in a realistic 3D environment and follows an instruction to reach the goal node. While most of the previous studies have built and investigated a discriminative approach, we notice that there are in fact two possible approaches to building such a VLN agent: discriminative \\textit{and} generative. In this paper, we design and investigate a generative language-grounded policy which uses a language model to compute the distribution over all possible instructions i.e. all possible sequences of vocabulary tokens given acti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.07783","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.07783/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2009.07783","created_at":"2026-07-05T01:41:20.201631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.07783v3","created_at":"2026-07-05T01:41:20.201631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.07783","created_at":"2026-07-05T01:41:20.201631+00:00"},{"alias_kind":"pith_short_12","alias_value":"OG6CWJQA6RQK","created_at":"2026-07-05T01:41:20.201631+00:00"},{"alias_kind":"pith_short_16","alias_value":"OG6CWJQA6RQKOO4Q","created_at":"2026-07-05T01:41:20.201631+00:00"},{"alias_kind":"pith_short_8","alias_value":"OG6CWJQA","created_at":"2026-07-05T01:41:20.201631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22087","citing_title":"Cognitively-Inspired Emergent Communication via Knowledge Graphs for Assisting the Visually Impaired","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OG6CWJQA6RQKOO4QV3HVELJKNV","json":"https://pith.science/pith/OG6CWJQA6RQKOO4QV3HVELJKNV.json","graph_json":"https://pith.science/api/pith-number/OG6CWJQA6RQKOO4QV3HVELJKNV/graph.json","events_json":"https://pith.science/api/pith-number/OG6CWJQA6RQKOO4QV3HVELJKNV/events.json","paper":"https://pith.science/paper/OG6CWJQA"},"agent_actions":{"view_html":"https://pith.science/pith/OG6CWJQA6RQKOO4QV3HVELJKNV","download_json":"https://pith.science/pith/OG6CWJQA6RQKOO4QV3HVELJKNV.json","view_paper":"https://pith.science/paper/OG6CWJQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.07783&json=true","fetch_graph":"https://pith.science/api/pith-number/OG6CWJQA6RQKOO4QV3HVELJKNV/graph.json","fetch_events":"https://pith.science/api/pith-number/OG6CWJQA6RQKOO4QV3HVELJKNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OG6CWJQA6RQKOO4QV3HVELJKNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OG6CWJQA6RQKOO4QV3HVELJKNV/action/storage_attestation","attest_author":"https://pith.science/pith/OG6CWJQA6RQKOO4QV3HVELJKNV/action/author_attestation","sign_citation":"https://pith.science/pith/OG6CWJQA6RQKOO4QV3HVELJKNV/action/citation_signature","submit_replication":"https://pith.science/pith/OG6CWJQA6RQKOO4QV3HVELJKNV/action/replication_record"}},"created_at":"2026-07-05T01:41:20.201631+00:00","updated_at":"2026-07-05T01:41:20.201631+00:00"}