{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YWABPYUXX3DPBY5LORKSXAQDKM","short_pith_number":"pith:YWABPYUX","schema_version":"1.0","canonical_sha256":"c58017e297bec6f0e3ab74552b8203530820392060f6daaf8ad5dad5acb2c0b1","source":{"kind":"arxiv","id":"2307.12907","version":4},"attestation_state":"computed","paper":{"title":"GridMM: Grid Memory Map for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiahao Yang, Shuqiang Jiang, Xiangyang Li, Yeqi Liu, Zihan Wang","submitted_at":"2023-07-24T16:02:42Z","abstract_excerpt":"Vision-and-language navigation (VLN) enables the agent to navigate to a remote location following the natural language instruction in 3D environments. To represent the previously visited environment, most approaches for VLN implement memory using recurrent states, topological maps, or top-down semantic maps. In contrast to these approaches, we build the top-down egocentric and dynamically growing Grid Memory Map (i.e., GridMM) to structure the visited environment. From a global perspective, historical observations are projected into a unified grid map in a top-down view, which can better repre"},"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":"2307.12907","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T16:02:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64d50d6936501753a6164134bea369b9f19ae373d370fa14d845071953c6fcd2","abstract_canon_sha256":"0441e0c857dd79c7ac8a318142aafc45e73df167bcb544a739d92d3813991cbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:08.544583Z","signature_b64":"JcvfPI+lM4F/lHJB3aBgfZw6OAs3HOJ2Th7944VzYT9rrqc5eCmx8GKzXKERkdQcklmSq2sGeOfoPIHT/FxPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c58017e297bec6f0e3ab74552b8203530820392060f6daaf8ad5dad5acb2c0b1","last_reissued_at":"2026-07-05T06:44:08.544050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:08.544050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GridMM: Grid Memory Map for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiahao Yang, Shuqiang Jiang, Xiangyang Li, Yeqi Liu, Zihan Wang","submitted_at":"2023-07-24T16:02:42Z","abstract_excerpt":"Vision-and-language navigation (VLN) enables the agent to navigate to a remote location following the natural language instruction in 3D environments. To represent the previously visited environment, most approaches for VLN implement memory using recurrent states, topological maps, or top-down semantic maps. In contrast to these approaches, we build the top-down egocentric and dynamically growing Grid Memory Map (i.e., GridMM) to structure the visited environment. From a global perspective, historical observations are projected into a unified grid map in a top-down view, which can better repre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12907","kind":"arxiv","version":4},"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/2307.12907/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":"2307.12907","created_at":"2026-07-05T06:44:08.544115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12907v4","created_at":"2026-07-05T06:44:08.544115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12907","created_at":"2026-07-05T06:44:08.544115+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWABPYUXX3DP","created_at":"2026-07-05T06:44:08.544115+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWABPYUXX3DPBY5L","created_at":"2026-07-05T06:44:08.544115+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWABPYUX","created_at":"2026-07-05T06:44:08.544115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06165","citing_title":"EAGOR: Embodied Reasoning in Omni-direction","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YWABPYUXX3DPBY5LORKSXAQDKM","json":"https://pith.science/pith/YWABPYUXX3DPBY5LORKSXAQDKM.json","graph_json":"https://pith.science/api/pith-number/YWABPYUXX3DPBY5LORKSXAQDKM/graph.json","events_json":"https://pith.science/api/pith-number/YWABPYUXX3DPBY5LORKSXAQDKM/events.json","paper":"https://pith.science/paper/YWABPYUX"},"agent_actions":{"view_html":"https://pith.science/pith/YWABPYUXX3DPBY5LORKSXAQDKM","download_json":"https://pith.science/pith/YWABPYUXX3DPBY5LORKSXAQDKM.json","view_paper":"https://pith.science/paper/YWABPYUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12907&json=true","fetch_graph":"https://pith.science/api/pith-number/YWABPYUXX3DPBY5LORKSXAQDKM/graph.json","fetch_events":"https://pith.science/api/pith-number/YWABPYUXX3DPBY5LORKSXAQDKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWABPYUXX3DPBY5LORKSXAQDKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWABPYUXX3DPBY5LORKSXAQDKM/action/storage_attestation","attest_author":"https://pith.science/pith/YWABPYUXX3DPBY5LORKSXAQDKM/action/author_attestation","sign_citation":"https://pith.science/pith/YWABPYUXX3DPBY5LORKSXAQDKM/action/citation_signature","submit_replication":"https://pith.science/pith/YWABPYUXX3DPBY5LORKSXAQDKM/action/replication_record"}},"created_at":"2026-07-05T06:44:08.544115+00:00","updated_at":"2026-07-05T06:44:08.544115+00:00"}