{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WXH75JINRBVOJUXFIOQSDGHP4X","short_pith_number":"pith:WXH75JIN","canonical_record":{"source":{"id":"2506.06862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-07T17:02:13Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"c3e1fe51bacb514b2c41a7ccb5661e0579511bd2ad6357339c4e1e2f475edb98","abstract_canon_sha256":"7e6a40bd1060fddd94c360014a26bdf4cbcccec2169b4fe1a391df7706b19963"},"schema_version":"1.0"},"canonical_sha256":"b5cffea50d886ae4d2e543a12198efe5c26cf357a09e34ce2458c4ee84477c07","source":{"kind":"arxiv","id":"2506.06862","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06862","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06862v1","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06862","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"WXH75JINRBVO","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"WXH75JINRBVOJUXF","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"WXH75JIN","created_at":"2026-07-05T11:17:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WXH75JINRBVOJUXFIOQSDGHP4X","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-07T17:02:13Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"c3e1fe51bacb514b2c41a7ccb5661e0579511bd2ad6357339c4e1e2f475edb98","abstract_canon_sha256":"7e6a40bd1060fddd94c360014a26bdf4cbcccec2169b4fe1a391df7706b19963"},"schema_version":"1.0"},"canonical_sha256":"b5cffea50d886ae4d2e543a12198efe5c26cf357a09e34ce2458c4ee84477c07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:57.019914Z","signature_b64":"idVgaE6uwJpptQcvE6ehMv1pJ5jqE0R3bBykwNE+ss63pFvfXruJ1zeV1R4i2xVbnL8so27J638KYioLvDlLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5cffea50d886ae4d2e543a12198efe5c26cf357a09e34ce2458c4ee84477c07","last_reissued_at":"2026-07-05T11:17:57.019451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:57.019451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06862","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VCrsSpSEsqRQ0PsaCv/jLFHrm+JkgWqyCjMHz9O52BBD61pI2lBaTb8i3csQEXf9V/3hrKTF06Ees6MzyFuJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:20:08.622968Z"},"content_sha256":"926aa5f44c26cf7e1f5dab3fbab46380517539d54952f3b5fc6af195943311cc","schema_version":"1.0","event_id":"sha256:926aa5f44c26cf7e1f5dab3fbab46380517539d54952f3b5fc6af195943311cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WXH75JINRBVOJUXFIOQSDGHP4X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Spatial Language Maps for Robot Navigation and Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.RO","authors_text":"Andy Zeng, Chenguang Huang, Oier Mees, Wolfram Burgard","submitted_at":"2025-06-07T17:02:13Z","abstract_excerpt":"Grounding language to a navigating agent's observations can leverage pretrained multimodal foundation models to match perceptions to object or event descriptions. However, previous approaches remain disconnected from environment mapping, lack the spatial precision of geometric maps, or neglect additional modality information beyond vision. To address this, we propose multimodal spatial language maps as a spatial map representation that fuses pretrained multimodal features with a 3D reconstruction of the environment. We build these maps autonomously using standard exploration. We present two in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06862","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/2506.06862/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PEt7R/jQUzz/NG8IrPatm0ivwvjIFRiI2MDdf2AEFEufWNdCc0P6/Bfm5CQK5nZr/XX3c4nnZJeC7+vjDZhuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:20:08.623476Z"},"content_sha256":"56dde6c43ca4592830bef9fee61fb88a2384b07bae6b3590530a13bb0e2ccf55","schema_version":"1.0","event_id":"sha256:56dde6c43ca4592830bef9fee61fb88a2384b07bae6b3590530a13bb0e2ccf55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXH75JINRBVOJUXFIOQSDGHP4X/bundle.json","state_url":"https://pith.science/pith/WXH75JINRBVOJUXFIOQSDGHP4X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXH75JINRBVOJUXFIOQSDGHP4X/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T17:20:08Z","links":{"resolver":"https://pith.science/pith/WXH75JINRBVOJUXFIOQSDGHP4X","bundle":"https://pith.science/pith/WXH75JINRBVOJUXFIOQSDGHP4X/bundle.json","state":"https://pith.science/pith/WXH75JINRBVOJUXFIOQSDGHP4X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXH75JINRBVOJUXFIOQSDGHP4X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WXH75JINRBVOJUXFIOQSDGHP4X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7e6a40bd1060fddd94c360014a26bdf4cbcccec2169b4fe1a391df7706b19963","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-07T17:02:13Z","title_canon_sha256":"c3e1fe51bacb514b2c41a7ccb5661e0579511bd2ad6357339c4e1e2f475edb98"},"schema_version":"1.0","source":{"id":"2506.06862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06862","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06862v1","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06862","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"WXH75JINRBVO","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"WXH75JINRBVOJUXF","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"WXH75JIN","created_at":"2026-07-05T11:17:57Z"}],"graph_snapshots":[{"event_id":"sha256:56dde6c43ca4592830bef9fee61fb88a2384b07bae6b3590530a13bb0e2ccf55","target":"graph","created_at":"2026-07-05T11:17:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.06862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grounding language to a navigating agent's observations can leverage pretrained multimodal foundation models to match perceptions to object or event descriptions. However, previous approaches remain disconnected from environment mapping, lack the spatial precision of geometric maps, or neglect additional modality information beyond vision. To address this, we propose multimodal spatial language maps as a spatial map representation that fuses pretrained multimodal features with a 3D reconstruction of the environment. We build these maps autonomously using standard exploration. We present two in","authors_text":"Andy Zeng, Chenguang Huang, Oier Mees, Wolfram Burgard","cross_cats":["cs.AI","cs.CV","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-07T17:02:13Z","title":"Multimodal Spatial Language Maps for Robot Navigation and Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06862","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:926aa5f44c26cf7e1f5dab3fbab46380517539d54952f3b5fc6af195943311cc","target":"record","created_at":"2026-07-05T11:17:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7e6a40bd1060fddd94c360014a26bdf4cbcccec2169b4fe1a391df7706b19963","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-07T17:02:13Z","title_canon_sha256":"c3e1fe51bacb514b2c41a7ccb5661e0579511bd2ad6357339c4e1e2f475edb98"},"schema_version":"1.0","source":{"id":"2506.06862","kind":"arxiv","version":1}},"canonical_sha256":"b5cffea50d886ae4d2e543a12198efe5c26cf357a09e34ce2458c4ee84477c07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5cffea50d886ae4d2e543a12198efe5c26cf357a09e34ce2458c4ee84477c07","first_computed_at":"2026-07-05T11:17:57.019451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:57.019451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"idVgaE6uwJpptQcvE6ehMv1pJ5jqE0R3bBykwNE+ss63pFvfXruJ1zeV1R4i2xVbnL8so27J638KYioLvDlLCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:57.019914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:926aa5f44c26cf7e1f5dab3fbab46380517539d54952f3b5fc6af195943311cc","sha256:56dde6c43ca4592830bef9fee61fb88a2384b07bae6b3590530a13bb0e2ccf55"],"state_sha256":"861c92ed1ea06aa4c053a7fe46700df90c6ea5101aa13eb7b853ee5deab8a1bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GCQTKJibrmiQ21LQV4EkxpB/G+km4oHEhnjY6AFan4V428Su9BLGLxzy3lGWNd0ASfQUN1vBRu3PKftgFh3aBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:20:08.627693Z","bundle_sha256":"781fe5a26385f73062218ee7f3650d167aceb8e8186bcd23f2d4b3dda2057c9f"}}