{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VYO2PWDFZUYRBIPVJSQPVK2CSS","short_pith_number":"pith:VYO2PWDF","schema_version":"1.0","canonical_sha256":"ae1da7d865cd3110a1f54ca0faab42949fce26fc51f9016362ed5756669306a0","source":{"kind":"arxiv","id":"2607.03792","version":1},"attestation_state":"computed","paper":{"title":"From Region Arrival to Instance-Level Grounding in Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jiwen Zhang, Qi Wu, Ruoxi Yang, Wei Tao, Xiangyu Shi, Yanyuan Qiao","submitted_at":"2026-07-04T09:44:57Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) agents may satisfy conventional success criteria while still failing to establish reliable object-level grounding, because current evaluation protocols mainly reward stopping within a 3-meter radius and largely ignore the agent's final orientation and target visibility. We formalize this limitation as the Last-3-Meter Grounding Gap and introduce three instance-centric metrics to quantify proximity precision, target visibility, and final-view grounding. To mitigate this gap, we propose REALM (Region-to-Entity Alignment for Last-3-Meter Navigation), a plug-an"},"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":"2607.03792","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-04T09:44:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7499a0fb927861c74d1bee9a73a9dbd48946027575e21f6e2978d506f585e54d","abstract_canon_sha256":"7368e3449ea2bb219ded0af85d5e9431634d3816b9b4b79cb0f38f58a0331390"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:08.010181Z","signature_b64":"dJCv93eBqTiuG9XNonPlLDbuUc0vIyzzM5uKMuGL3QUskY3vfW3pSLTRPSWCv9K9bMp0H/w9TMCkxVyK5aP1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae1da7d865cd3110a1f54ca0faab42949fce26fc51f9016362ed5756669306a0","last_reissued_at":"2026-07-07T02:18:08.009389Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:08.009389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Region Arrival to Instance-Level Grounding in Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jiwen Zhang, Qi Wu, Ruoxi Yang, Wei Tao, Xiangyu Shi, Yanyuan Qiao","submitted_at":"2026-07-04T09:44:57Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) agents may satisfy conventional success criteria while still failing to establish reliable object-level grounding, because current evaluation protocols mainly reward stopping within a 3-meter radius and largely ignore the agent's final orientation and target visibility. We formalize this limitation as the Last-3-Meter Grounding Gap and introduce three instance-centric metrics to quantify proximity precision, target visibility, and final-view grounding. To mitigate this gap, we propose REALM (Region-to-Entity Alignment for Last-3-Meter Navigation), a plug-an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03792","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/2607.03792/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":"2607.03792","created_at":"2026-07-07T02:18:08.009503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03792v1","created_at":"2026-07-07T02:18:08.009503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03792","created_at":"2026-07-07T02:18:08.009503+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYO2PWDFZUYR","created_at":"2026-07-07T02:18:08.009503+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYO2PWDFZUYRBIPV","created_at":"2026-07-07T02:18:08.009503+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYO2PWDF","created_at":"2026-07-07T02:18:08.009503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VYO2PWDFZUYRBIPVJSQPVK2CSS","json":"https://pith.science/pith/VYO2PWDFZUYRBIPVJSQPVK2CSS.json","graph_json":"https://pith.science/api/pith-number/VYO2PWDFZUYRBIPVJSQPVK2CSS/graph.json","events_json":"https://pith.science/api/pith-number/VYO2PWDFZUYRBIPVJSQPVK2CSS/events.json","paper":"https://pith.science/paper/VYO2PWDF"},"agent_actions":{"view_html":"https://pith.science/pith/VYO2PWDFZUYRBIPVJSQPVK2CSS","download_json":"https://pith.science/pith/VYO2PWDFZUYRBIPVJSQPVK2CSS.json","view_paper":"https://pith.science/paper/VYO2PWDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03792&json=true","fetch_graph":"https://pith.science/api/pith-number/VYO2PWDFZUYRBIPVJSQPVK2CSS/graph.json","fetch_events":"https://pith.science/api/pith-number/VYO2PWDFZUYRBIPVJSQPVK2CSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYO2PWDFZUYRBIPVJSQPVK2CSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYO2PWDFZUYRBIPVJSQPVK2CSS/action/storage_attestation","attest_author":"https://pith.science/pith/VYO2PWDFZUYRBIPVJSQPVK2CSS/action/author_attestation","sign_citation":"https://pith.science/pith/VYO2PWDFZUYRBIPVJSQPVK2CSS/action/citation_signature","submit_replication":"https://pith.science/pith/VYO2PWDFZUYRBIPVJSQPVK2CSS/action/replication_record"}},"created_at":"2026-07-07T02:18:08.009503+00:00","updated_at":"2026-07-07T02:18:08.009503+00:00"}