{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LHM7VL374JQOODY47IQAH2OLPB","short_pith_number":"pith:LHM7VL37","canonical_record":{"source":{"id":"2411.05755","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-08T18:16:58Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"5c6cfc868f5874a585e690c510f2eed6c30ecfda3ef31dd95e16b3a422ff327a","abstract_canon_sha256":"55b0bc8daf0f34dfc0f7d03bdfa2dd1285f68d9028cccc06287649ba28707e46"},"schema_version":"1.0"},"canonical_sha256":"59d9faaf7fe260e70f1cfa2003e9cb784b5e521f5d6b614bdb399b3fc8ace761","source":{"kind":"arxiv","id":"2411.05755","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05755","created_at":"2026-07-05T09:33:06Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05755v1","created_at":"2026-07-05T09:33:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05755","created_at":"2026-07-05T09:33:06Z"},{"alias_kind":"pith_short_12","alias_value":"LHM7VL374JQO","created_at":"2026-07-05T09:33:06Z"},{"alias_kind":"pith_short_16","alias_value":"LHM7VL374JQOODY4","created_at":"2026-07-05T09:33:06Z"},{"alias_kind":"pith_short_8","alias_value":"LHM7VL37","created_at":"2026-07-05T09:33:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LHM7VL374JQOODY47IQAH2OLPB","target":"record","payload":{"canonical_record":{"source":{"id":"2411.05755","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-08T18:16:58Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"5c6cfc868f5874a585e690c510f2eed6c30ecfda3ef31dd95e16b3a422ff327a","abstract_canon_sha256":"55b0bc8daf0f34dfc0f7d03bdfa2dd1285f68d9028cccc06287649ba28707e46"},"schema_version":"1.0"},"canonical_sha256":"59d9faaf7fe260e70f1cfa2003e9cb784b5e521f5d6b614bdb399b3fc8ace761","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:06.251374Z","signature_b64":"9e4VE7YwSjGclPEHgn8fKE6TpDSCYKcQTNOSSkcwoEP+CEs8lnxIbcy1ZFGh1YVWK3zd9pfseoUGADKz7gqFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59d9faaf7fe260e70f1cfa2003e9cb784b5e521f5d6b614bdb399b3fc8ace761","last_reissued_at":"2026-07-05T09:33:06.250792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:06.250792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.05755","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":"2026-07-05T09:33:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AiJErDQhnGneyvELFnsAu8fUEkVL4EatiEldmFbdtxD4AxLsNLnfGs5VWT92jAzQPiPxYVWOF4bMWwCuAw7mCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:05:08.356055Z"},"content_sha256":"72f03338eca3a75855af91bc85e63ec1fa9bb36e29cd2f11d64f3fd5234227fd","schema_version":"1.0","event_id":"sha256:72f03338eca3a75855af91bc85e63ec1fa9bb36e29cd2f11d64f3fd5234227fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LHM7VL374JQOODY47IQAH2OLPB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Antonio Loquercio, Dylan Goetting, Himanshu Gaurav Singh","submitted_at":"2024-11-08T18:16:58Z","abstract_excerpt":"We present VLMnav, an embodied framework to transform a Vision-Language Model (VLM) into an end-to-end navigation policy. In contrast to prior work, we do not rely on a separation between perception, planning, and control; instead, we use a VLM to directly select actions in one step. Surprisingly, we find that a VLM can be used as an end-to-end policy zero-shot, i.e., without any fine-tuning or exposure to navigation data. This makes our approach open-ended and generalizable to any downstream navigation task. We run an extensive study to evaluate the performance of our approach in comparison t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05755","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/2411.05755/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":"2026-07-05T09:33:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SSSfQT97/F2AEYxLH84unMs24ONkSrhn2lBd2j/MWQ3pnUojvYpbrCJGZnQjOO4DJQYsGGgRqusybLYBl9ESAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:05:08.356612Z"},"content_sha256":"c88cbb70bea3140344e89b6d5eb49ad406c7f389d1bfef7b8a30c6332645f98f","schema_version":"1.0","event_id":"sha256:c88cbb70bea3140344e89b6d5eb49ad406c7f389d1bfef7b8a30c6332645f98f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB/bundle.json","state_url":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LHM7VL374JQOODY47IQAH2OLPB/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":"2026-08-05T22:05:08Z","links":{"resolver":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB","bundle":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB/bundle.json","state":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LHM7VL374JQOODY47IQAH2OLPB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LHM7VL374JQOODY47IQAH2OLPB","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":"55b0bc8daf0f34dfc0f7d03bdfa2dd1285f68d9028cccc06287649ba28707e46","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-08T18:16:58Z","title_canon_sha256":"5c6cfc868f5874a585e690c510f2eed6c30ecfda3ef31dd95e16b3a422ff327a"},"schema_version":"1.0","source":{"id":"2411.05755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05755","created_at":"2026-07-05T09:33:06Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05755v1","created_at":"2026-07-05T09:33:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05755","created_at":"2026-07-05T09:33:06Z"},{"alias_kind":"pith_short_12","alias_value":"LHM7VL374JQO","created_at":"2026-07-05T09:33:06Z"},{"alias_kind":"pith_short_16","alias_value":"LHM7VL374JQOODY4","created_at":"2026-07-05T09:33:06Z"},{"alias_kind":"pith_short_8","alias_value":"LHM7VL37","created_at":"2026-07-05T09:33:06Z"}],"graph_snapshots":[{"event_id":"sha256:c88cbb70bea3140344e89b6d5eb49ad406c7f389d1bfef7b8a30c6332645f98f","target":"graph","created_at":"2026-07-05T09:33:06Z","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/2411.05755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present VLMnav, an embodied framework to transform a Vision-Language Model (VLM) into an end-to-end navigation policy. In contrast to prior work, we do not rely on a separation between perception, planning, and control; instead, we use a VLM to directly select actions in one step. Surprisingly, we find that a VLM can be used as an end-to-end policy zero-shot, i.e., without any fine-tuning or exposure to navigation data. This makes our approach open-ended and generalizable to any downstream navigation task. We run an extensive study to evaluate the performance of our approach in comparison t","authors_text":"Antonio Loquercio, Dylan Goetting, Himanshu Gaurav Singh","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-08T18:16:58Z","title":"End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05755","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":"sha256:72f03338eca3a75855af91bc85e63ec1fa9bb36e29cd2f11d64f3fd5234227fd","target":"record","created_at":"2026-07-05T09:33:06Z","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":"55b0bc8daf0f34dfc0f7d03bdfa2dd1285f68d9028cccc06287649ba28707e46","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-08T18:16:58Z","title_canon_sha256":"5c6cfc868f5874a585e690c510f2eed6c30ecfda3ef31dd95e16b3a422ff327a"},"schema_version":"1.0","source":{"id":"2411.05755","kind":"arxiv","version":1}},"canonical_sha256":"59d9faaf7fe260e70f1cfa2003e9cb784b5e521f5d6b614bdb399b3fc8ace761","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59d9faaf7fe260e70f1cfa2003e9cb784b5e521f5d6b614bdb399b3fc8ace761","first_computed_at":"2026-07-05T09:33:06.250792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:06.250792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9e4VE7YwSjGclPEHgn8fKE6TpDSCYKcQTNOSSkcwoEP+CEs8lnxIbcy1ZFGh1YVWK3zd9pfseoUGADKz7gqFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:06.251374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72f03338eca3a75855af91bc85e63ec1fa9bb36e29cd2f11d64f3fd5234227fd","sha256:c88cbb70bea3140344e89b6d5eb49ad406c7f389d1bfef7b8a30c6332645f98f"],"state_sha256":"92d0c13d4e2b4a0facf8c7f875247fe01d9ef5391a79455f7e969e93f74a96c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kMXA/CZqyKC0V0QGr1SYSB3DmdSPno2LT0px7rYCyWRwPtmFTF0DI0/cdHZbDuUTbpQ0xV9NPoyaiYzsBN8lCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:05:08.363027Z","bundle_sha256":"7b7004eecc8288de7c7b2ee042f3d8fb96fcc0ff68f4886b2f3a395859da307e"}}