{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3VMJCFMG6KV6VWT326DFECU624","short_pith_number":"pith:3VMJCFMG","schema_version":"1.0","canonical_sha256":"dd58911586f2abeada7bd786520a9ed7091f0230fbb85bef175b74321193f97b","source":{"kind":"arxiv","id":"2105.08756","version":2},"attestation_state":"computed","paper":{"title":"Pathdreamer: A World Model for Indoor Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Honglak Lee, Jason Baldridge, Jing Yu Koh, Peter Anderson, Yinfei Yang","submitted_at":"2021-05-18T18:13:53Z","abstract_excerpt":"People navigating in unfamiliar buildings take advantage of myriad visual, spatial and semantic cues to efficiently achieve their navigation goals. Towards equipping computational agents with similar capabilities, we introduce Pathdreamer, a visual world model for agents navigating in novel indoor environments. Given one or more previous visual observations, Pathdreamer generates plausible high-resolution 360 visual observations (RGB, semantic segmentation and depth) for viewpoints that have not been visited, in buildings not seen during training. In regions of high uncertainty (e.g. predictin"},"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":"2105.08756","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-18T18:13:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5c94adececf8156c073f43f43ffe93a2e4624bb3c5a18ccae255bf114604b72b","abstract_canon_sha256":"969ff01203034086c1bd998a328b8e41a3bf7b16f9a53c7a8c81d455aee6976f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:03.248517Z","signature_b64":"YHeOUOx+1IJN4riVR37K91DftEkchiUms7PKi1d6s/gBZBQgKxlFGdz9EFDzf9zLgpPGgh/KLKhp7s3nsPtSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd58911586f2abeada7bd786520a9ed7091f0230fbb85bef175b74321193f97b","last_reissued_at":"2026-07-05T03:06:03.248099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:03.248099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pathdreamer: A World Model for Indoor Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Honglak Lee, Jason Baldridge, Jing Yu Koh, Peter Anderson, Yinfei Yang","submitted_at":"2021-05-18T18:13:53Z","abstract_excerpt":"People navigating in unfamiliar buildings take advantage of myriad visual, spatial and semantic cues to efficiently achieve their navigation goals. Towards equipping computational agents with similar capabilities, we introduce Pathdreamer, a visual world model for agents navigating in novel indoor environments. Given one or more previous visual observations, Pathdreamer generates plausible high-resolution 360 visual observations (RGB, semantic segmentation and depth) for viewpoints that have not been visited, in buildings not seen during training. In regions of high uncertainty (e.g. predictin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08756","kind":"arxiv","version":2},"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/2105.08756/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":"2105.08756","created_at":"2026-07-05T03:06:03.248156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.08756v2","created_at":"2026-07-05T03:06:03.248156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08756","created_at":"2026-07-05T03:06:03.248156+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VMJCFMG6KV6","created_at":"2026-07-05T03:06:03.248156+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VMJCFMG6KV6VWT3","created_at":"2026-07-05T03:06:03.248156+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VMJCFMG","created_at":"2026-07-05T03:06:03.248156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30367","citing_title":"FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VMJCFMG6KV6VWT326DFECU624","json":"https://pith.science/pith/3VMJCFMG6KV6VWT326DFECU624.json","graph_json":"https://pith.science/api/pith-number/3VMJCFMG6KV6VWT326DFECU624/graph.json","events_json":"https://pith.science/api/pith-number/3VMJCFMG6KV6VWT326DFECU624/events.json","paper":"https://pith.science/paper/3VMJCFMG"},"agent_actions":{"view_html":"https://pith.science/pith/3VMJCFMG6KV6VWT326DFECU624","download_json":"https://pith.science/pith/3VMJCFMG6KV6VWT326DFECU624.json","view_paper":"https://pith.science/paper/3VMJCFMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.08756&json=true","fetch_graph":"https://pith.science/api/pith-number/3VMJCFMG6KV6VWT326DFECU624/graph.json","fetch_events":"https://pith.science/api/pith-number/3VMJCFMG6KV6VWT326DFECU624/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VMJCFMG6KV6VWT326DFECU624/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VMJCFMG6KV6VWT326DFECU624/action/storage_attestation","attest_author":"https://pith.science/pith/3VMJCFMG6KV6VWT326DFECU624/action/author_attestation","sign_citation":"https://pith.science/pith/3VMJCFMG6KV6VWT326DFECU624/action/citation_signature","submit_replication":"https://pith.science/pith/3VMJCFMG6KV6VWT326DFECU624/action/replication_record"}},"created_at":"2026-07-05T03:06:03.248156+00:00","updated_at":"2026-07-05T03:06:03.248156+00:00"}