{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EJRNPUO6NHU3QEWKNVTETOONQJ","short_pith_number":"pith:EJRNPUO6","schema_version":"1.0","canonical_sha256":"2262d7d1de69e9b812ca6d6649b9cd8269c95d8d4cdf6d28b2e7dc85272b7363","source":{"kind":"arxiv","id":"2605.07496","version":2},"attestation_state":"computed","paper":{"title":"PathPainter: Transferring the Generalization Ability of Image Generation Models to Embodied Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Image generation models interpret natural language to create traversability masks on bird's-eye-view images for guiding robot navigation.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Fei Gao, Mo Zhu, Weiqi Gai, Xijie Huang, Xin Zhou, Yijin Wang, Yuru Tian, Yuze Wu","submitted_at":"2026-05-08T09:33:19Z","abstract_excerpt":"Bird's-eye-view (BEV) images have been widely demonstrated to provide valuable prior information for navigation. Given the global information provided by such views, two key challenges remain: how to fully exploit this information and how to reliably use it during execution. In this paper, we propose a navigation system that uses BEV images as global priors and is designed for ground and near-ground robotic platforms. The system employs an image generation model to interpret human intent from natural language, identify the target destination, and generate traversability masks. During execution"},"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":true},"canonical_record":{"source":{"id":"2605.07496","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-08T09:33:19Z","cross_cats_sorted":[],"title_canon_sha256":"be1cba362c908c4d8deff7079a4cdc5a319aead17aa989748922316c2bf8ae72","abstract_canon_sha256":"9863f7d8e141fc8cae05719a1f0de8f8f38dcf314dad7d4e4bc9ae1bbf4a3316"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:06.896252Z","signature_b64":"ggSnA2j0ecYtzkPqLpwEBCaJ+NG7tzs0zg2/iuC+lSN+0PitJvqxHmaW97BR+U6OfFFR1cEz4eLZaIIY/0LaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2262d7d1de69e9b812ca6d6649b9cd8269c95d8d4cdf6d28b2e7dc85272b7363","last_reissued_at":"2026-06-08T01:04:06.895228Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:06.895228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PathPainter: Transferring the Generalization Ability of Image Generation Models to Embodied Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Image generation models interpret natural language to create traversability masks on bird's-eye-view images for guiding robot navigation.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Fei Gao, Mo Zhu, Weiqi Gai, Xijie Huang, Xin Zhou, Yijin Wang, Yuru Tian, Yuze Wu","submitted_at":"2026-05-08T09:33:19Z","abstract_excerpt":"Bird's-eye-view (BEV) images have been widely demonstrated to provide valuable prior information for navigation. Given the global information provided by such views, two key challenges remain: how to fully exploit this information and how to reliably use it during execution. In this paper, we propose a navigation system that uses BEV images as global priors and is designed for ground and near-ground robotic platforms. The system employs an image generation model to interpret human intent from natural language, identify the target destination, and generate traversability masks. During execution"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"This work demonstrates how the world-understanding capabilities of foundation models can be transferred to embodied navigation, enabling robots to benefit from the strong generalization ability of existing image generation models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The image generation model can reliably interpret natural language intent and produce accurate traversability masks from BEV images that a conventional local motion planner can use successfully for long-range tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PathPainter transfers image generation models to embodied navigation by generating traversability masks from BEV images and language instructions while using cross-view localization to reduce odometry drift.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Image generation models interpret natural language to create traversability masks on bird's-eye-view images for guiding robot navigation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b5ec935e2e8cf87c960f57cdd7063ec788e6324bb29acded58b06cd408ac5dfa"},"source":{"id":"2605.07496","kind":"arxiv","version":2},"verdict":{"id":"e7c28f6f-7909-4c7d-88cc-5bd55a3fc53d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T02:02:21.175119Z","strongest_claim":"This work demonstrates how the world-understanding capabilities of foundation models can be transferred to embodied navigation, enabling robots to benefit from the strong generalization ability of existing image generation models.","one_line_summary":"PathPainter transfers image generation models to embodied navigation by generating traversability masks from BEV images and language instructions while using cross-view localization to reduce odometry drift.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The image generation model can reliably interpret natural language intent and produce accurate traversability masks from BEV images that a conventional local motion planner can use successfully for long-range tasks.","pith_extraction_headline":"Image generation models interpret natural language to create traversability masks on bird's-eye-view images for guiding robot navigation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07496/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T10:42:02.905510Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T05:42:43.105033Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.816844Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:44:05.509795Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"efab0d344dce0fcdf46dbb46df2f95116612ed889ca375f08eda37c155943e42"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d9a98c4e1dec6648fd98f4bd3548d4af202fcaaf84cdfbae7d3d8b5da48356c1"},"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":"2605.07496","created_at":"2026-06-08T01:04:06.895383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.07496v2","created_at":"2026-06-08T01:04:06.895383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07496","created_at":"2026-06-08T01:04:06.895383+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJRNPUO6NHU3","created_at":"2026-06-08T01:04:06.895383+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJRNPUO6NHU3QEWK","created_at":"2026-06-08T01:04:06.895383+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJRNPUO6","created_at":"2026-06-08T01:04:06.895383+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EJRNPUO6NHU3QEWKNVTETOONQJ","json":"https://pith.science/pith/EJRNPUO6NHU3QEWKNVTETOONQJ.json","graph_json":"https://pith.science/api/pith-number/EJRNPUO6NHU3QEWKNVTETOONQJ/graph.json","events_json":"https://pith.science/api/pith-number/EJRNPUO6NHU3QEWKNVTETOONQJ/events.json","paper":"https://pith.science/paper/EJRNPUO6"},"agent_actions":{"view_html":"https://pith.science/pith/EJRNPUO6NHU3QEWKNVTETOONQJ","download_json":"https://pith.science/pith/EJRNPUO6NHU3QEWKNVTETOONQJ.json","view_paper":"https://pith.science/paper/EJRNPUO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.07496&json=true","fetch_graph":"https://pith.science/api/pith-number/EJRNPUO6NHU3QEWKNVTETOONQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/EJRNPUO6NHU3QEWKNVTETOONQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJRNPUO6NHU3QEWKNVTETOONQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJRNPUO6NHU3QEWKNVTETOONQJ/action/storage_attestation","attest_author":"https://pith.science/pith/EJRNPUO6NHU3QEWKNVTETOONQJ/action/author_attestation","sign_citation":"https://pith.science/pith/EJRNPUO6NHU3QEWKNVTETOONQJ/action/citation_signature","submit_replication":"https://pith.science/pith/EJRNPUO6NHU3QEWKNVTETOONQJ/action/replication_record"}},"created_at":"2026-06-08T01:04:06.895383+00:00","updated_at":"2026-06-08T01:04:06.895383+00:00"}