{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JSAV5T4XQTM7QC4PMFUDO2MCCP","short_pith_number":"pith:JSAV5T4X","canonical_record":{"source":{"id":"2606.30367","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T14:33:03Z","cross_cats_sorted":[],"title_canon_sha256":"27dc02a9c68957610ca4fa390d5aed54ca81052c48c5b1a5e7b3ecf09d4bd739","abstract_canon_sha256":"4ebddd22ecc1d735b3ed37ca49d9266fea712348b1f75b4733bf931ade566c82"},"schema_version":"1.0"},"canonical_sha256":"4c815ecf9784d9f80b8f616837698213df6cab12dd4196199c0f2f6328902347","source":{"kind":"arxiv","id":"2606.30367","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30367","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30367v1","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30367","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"JSAV5T4XQTM7","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"JSAV5T4XQTM7QC4P","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"JSAV5T4X","created_at":"2026-06-30T02:18:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JSAV5T4XQTM7QC4PMFUDO2MCCP","target":"record","payload":{"canonical_record":{"source":{"id":"2606.30367","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T14:33:03Z","cross_cats_sorted":[],"title_canon_sha256":"27dc02a9c68957610ca4fa390d5aed54ca81052c48c5b1a5e7b3ecf09d4bd739","abstract_canon_sha256":"4ebddd22ecc1d735b3ed37ca49d9266fea712348b1f75b4733bf931ade566c82"},"schema_version":"1.0"},"canonical_sha256":"4c815ecf9784d9f80b8f616837698213df6cab12dd4196199c0f2f6328902347","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:12.202879Z","signature_b64":"VY3/FM/qiXwj9NgeX1jmBkmm4jzWxxapPGAzcMU3Leer2tBxt3hp/TARpO9RKPC6gAPmajjRz06XJKu4XnFcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c815ecf9784d9f80b8f616837698213df6cab12dd4196199c0f2f6328902347","last_reissued_at":"2026-06-30T02:18:12.202115Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:12.202115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.30367","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":"2026-06-30T02:18:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WD0TS47HAtIe3y5vY7Ya/nkcqYA6xVF2+pvpyq8E0Z7g9QZrTZn9CRB75Qpm+jGCWBWBq20IrwmYhGrWBL2hBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T19:07:24.091281Z"},"content_sha256":"3340929b4938f85df6faf33896d31ca138b80d557fe377dacaef1765f14b4d57","schema_version":"1.0","event_id":"sha256:3340929b4938f85df6faf33896d31ca138b80d557fe377dacaef1765f14b4d57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JSAV5T4XQTM7QC4PMFUDO2MCCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hangjun Ye, Haoxiang Fu, Junwei Liang, Lingfeng Zhang, Mingliang Zhou, Qiang Zhang, Wenbo Ding, Xiaojun Liang, Xiaoshuai Hao, Zeying Gong","submitted_at":"2026-06-29T14:33:03Z","abstract_excerpt":"Vision-and-language navigation (VLN) in continuous environments requires an agent to ground instructions in egocentric observations while maintaining spatial understanding across long action sequences. Recent navigation foundation models have shown strong progress by scaling vision-language models, but they often learn navigation primarily as direct action generation, without explicitly modeling world states or predicting their future evolution. We introduce FutureNav, a VLM-based unified world-action modeling framework for vision-and-language navigation. Specifically, FutureNav jointly encode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30367","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/2606.30367/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":"2026-06-30T02:18:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iF66eJycTv8OZR5HeXCvcQHFgj3o4qgPr/hy036RWrGaMEJT4EYRpoNsoaUlhHUY+sm8lSnCiv4ArDFaxqL0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T19:07:24.091678Z"},"content_sha256":"46fc398a59c2be889cc3622f540d7ff2fefc3979917fd170f97278af56d5257a","schema_version":"1.0","event_id":"sha256:46fc398a59c2be889cc3622f540d7ff2fefc3979917fd170f97278af56d5257a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JSAV5T4XQTM7QC4PMFUDO2MCCP/bundle.json","state_url":"https://pith.science/pith/JSAV5T4XQTM7QC4PMFUDO2MCCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JSAV5T4XQTM7QC4PMFUDO2MCCP/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":"2026-06-30T19:07:24Z","links":{"resolver":"https://pith.science/pith/JSAV5T4XQTM7QC4PMFUDO2MCCP","bundle":"https://pith.science/pith/JSAV5T4XQTM7QC4PMFUDO2MCCP/bundle.json","state":"https://pith.science/pith/JSAV5T4XQTM7QC4PMFUDO2MCCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JSAV5T4XQTM7QC4PMFUDO2MCCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JSAV5T4XQTM7QC4PMFUDO2MCCP","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":"4ebddd22ecc1d735b3ed37ca49d9266fea712348b1f75b4733bf931ade566c82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T14:33:03Z","title_canon_sha256":"27dc02a9c68957610ca4fa390d5aed54ca81052c48c5b1a5e7b3ecf09d4bd739"},"schema_version":"1.0","source":{"id":"2606.30367","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30367","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30367v1","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30367","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"JSAV5T4XQTM7","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"JSAV5T4XQTM7QC4P","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"JSAV5T4X","created_at":"2026-06-30T02:18:12Z"}],"graph_snapshots":[{"event_id":"sha256:46fc398a59c2be889cc3622f540d7ff2fefc3979917fd170f97278af56d5257a","target":"graph","created_at":"2026-06-30T02:18:12Z","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/2606.30367/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-language navigation (VLN) in continuous environments requires an agent to ground instructions in egocentric observations while maintaining spatial understanding across long action sequences. Recent navigation foundation models have shown strong progress by scaling vision-language models, but they often learn navigation primarily as direct action generation, without explicitly modeling world states or predicting their future evolution. We introduce FutureNav, a VLM-based unified world-action modeling framework for vision-and-language navigation. Specifically, FutureNav jointly encode","authors_text":"Hangjun Ye, Haoxiang Fu, Junwei Liang, Lingfeng Zhang, Mingliang Zhou, Qiang Zhang, Wenbo Ding, Xiaojun Liang, Xiaoshuai Hao, Zeying Gong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T14:33:03Z","title":"FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30367","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":"sha256:3340929b4938f85df6faf33896d31ca138b80d557fe377dacaef1765f14b4d57","target":"record","created_at":"2026-06-30T02:18:12Z","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":"4ebddd22ecc1d735b3ed37ca49d9266fea712348b1f75b4733bf931ade566c82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T14:33:03Z","title_canon_sha256":"27dc02a9c68957610ca4fa390d5aed54ca81052c48c5b1a5e7b3ecf09d4bd739"},"schema_version":"1.0","source":{"id":"2606.30367","kind":"arxiv","version":1}},"canonical_sha256":"4c815ecf9784d9f80b8f616837698213df6cab12dd4196199c0f2f6328902347","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c815ecf9784d9f80b8f616837698213df6cab12dd4196199c0f2f6328902347","first_computed_at":"2026-06-30T02:18:12.202115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:18:12.202115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VY3/FM/qiXwj9NgeX1jmBkmm4jzWxxapPGAzcMU3Leer2tBxt3hp/TARpO9RKPC6gAPmajjRz06XJKu4XnFcCw==","signature_status":"signed_v1","signed_at":"2026-06-30T02:18:12.202879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30367","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3340929b4938f85df6faf33896d31ca138b80d557fe377dacaef1765f14b4d57","sha256:46fc398a59c2be889cc3622f540d7ff2fefc3979917fd170f97278af56d5257a"],"state_sha256":"5eafb585c590b7cb13f39ed112b5882836115e7d79cd2823a4eed14a94adcbe5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k7n2oYic76g7pGs/ybE/U8AgdoWts46r35dTqg9kiMJEQyZd34y8/tpwKNDsUdFxzQRIaFKmWdXPrbpuf9G6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T19:07:24.093731Z","bundle_sha256":"13d55cc4ebb2f962bcbeb24142dbaf1aa90b9d270ddfa1391725145fe73b224a"}}