{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PWGIOR4JKKFXDTWWPAH5JZM6OE","short_pith_number":"pith:PWGIOR4J","schema_version":"1.0","canonical_sha256":"7d8c874789528b71ced6780fd4e59e711ac654505a3de4b0d4bad4e004cde13f","source":{"kind":"arxiv","id":"2210.07506","version":1},"attestation_state":"computed","paper":{"title":"Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Dongyu Ji, Kunyang Lin, Mingkui Tan, Peihao Chen, Runhao Zeng, Thomas H. Li","submitted_at":"2022-10-14T04:23:27Z","abstract_excerpt":"We address a practical yet challenging problem of training robot agents to navigate in an environment following a path described by some language instructions. The instructions often contain descriptions of objects in the environment. To achieve accurate and efficient navigation, it is critical to build a map that accurately represents both spatial location and the semantic information of the environment objects. However, enabling a robot to build a map that well represents the environment is extremely challenging as the environment often involves diverse objects with various attributes. In th"},"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":"2210.07506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-14T04:23:27Z","cross_cats_sorted":[],"title_canon_sha256":"19d10de7c772612aaf86f85ba08b94a5cb07d692c04c39c56cf696258cfa8082","abstract_canon_sha256":"efc44ecb85033311b366ac2ed51cd1732c014749cab2acc53a80ac69ae4fac91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:38.050417Z","signature_b64":"rCtk3n8bFllY/IsukJxhX2DnTqq8ZnEz1zE1269GpzKocDE1hRteUWptaisbUJaK8DqXYOkW4XKv/lZo2SrJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d8c874789528b71ced6780fd4e59e711ac654505a3de4b0d4bad4e004cde13f","last_reissued_at":"2026-07-05T05:06:38.049997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:38.049997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Dongyu Ji, Kunyang Lin, Mingkui Tan, Peihao Chen, Runhao Zeng, Thomas H. Li","submitted_at":"2022-10-14T04:23:27Z","abstract_excerpt":"We address a practical yet challenging problem of training robot agents to navigate in an environment following a path described by some language instructions. The instructions often contain descriptions of objects in the environment. To achieve accurate and efficient navigation, it is critical to build a map that accurately represents both spatial location and the semantic information of the environment objects. However, enabling a robot to build a map that well represents the environment is extremely challenging as the environment often involves diverse objects with various attributes. In th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07506","kind":"arxiv","version":1},"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/2210.07506/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":"2210.07506","created_at":"2026-07-05T05:06:38.050053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07506v1","created_at":"2026-07-05T05:06:38.050053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07506","created_at":"2026-07-05T05:06:38.050053+00:00"},{"alias_kind":"pith_short_12","alias_value":"PWGIOR4JKKFX","created_at":"2026-07-05T05:06:38.050053+00:00"},{"alias_kind":"pith_short_16","alias_value":"PWGIOR4JKKFXDTWW","created_at":"2026-07-05T05:06:38.050053+00:00"},{"alias_kind":"pith_short_8","alias_value":"PWGIOR4J","created_at":"2026-07-05T05:06:38.050053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22816","citing_title":"AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2402.15852","citing_title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06224","citing_title":"Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PWGIOR4JKKFXDTWWPAH5JZM6OE","json":"https://pith.science/pith/PWGIOR4JKKFXDTWWPAH5JZM6OE.json","graph_json":"https://pith.science/api/pith-number/PWGIOR4JKKFXDTWWPAH5JZM6OE/graph.json","events_json":"https://pith.science/api/pith-number/PWGIOR4JKKFXDTWWPAH5JZM6OE/events.json","paper":"https://pith.science/paper/PWGIOR4J"},"agent_actions":{"view_html":"https://pith.science/pith/PWGIOR4JKKFXDTWWPAH5JZM6OE","download_json":"https://pith.science/pith/PWGIOR4JKKFXDTWWPAH5JZM6OE.json","view_paper":"https://pith.science/paper/PWGIOR4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07506&json=true","fetch_graph":"https://pith.science/api/pith-number/PWGIOR4JKKFXDTWWPAH5JZM6OE/graph.json","fetch_events":"https://pith.science/api/pith-number/PWGIOR4JKKFXDTWWPAH5JZM6OE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PWGIOR4JKKFXDTWWPAH5JZM6OE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PWGIOR4JKKFXDTWWPAH5JZM6OE/action/storage_attestation","attest_author":"https://pith.science/pith/PWGIOR4JKKFXDTWWPAH5JZM6OE/action/author_attestation","sign_citation":"https://pith.science/pith/PWGIOR4JKKFXDTWWPAH5JZM6OE/action/citation_signature","submit_replication":"https://pith.science/pith/PWGIOR4JKKFXDTWWPAH5JZM6OE/action/replication_record"}},"created_at":"2026-07-05T05:06:38.050053+00:00","updated_at":"2026-07-05T05:06:38.050053+00:00"}