{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HN3CMNVFXQGCY7EHUP7BYKEX4T","short_pith_number":"pith:HN3CMNVF","canonical_record":{"source":{"id":"2407.15087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T08:05:29Z","cross_cats_sorted":[],"title_canon_sha256":"7b658b4f70c085d9a8220eb0e75181a19cd33fbfd039736bf129d1d82f466cc0","abstract_canon_sha256":"c3a98cad835c6c549fef7ae0435fb939d2b332bfa008ace507ba8533b7751983"},"schema_version":"1.0"},"canonical_sha256":"3b762636a5bc0c2c7c87a3fe1c2897e4f9b4f43d3e636be88eff1f6547cc29dd","source":{"kind":"arxiv","id":"2407.15087","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15087","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15087v1","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15087","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"pith_short_12","alias_value":"HN3CMNVFXQGC","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"pith_short_16","alias_value":"HN3CMNVFXQGCY7EH","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"pith_short_8","alias_value":"HN3CMNVF","created_at":"2026-07-05T08:46:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HN3CMNVFXQGCY7EHUP7BYKEX4T","target":"record","payload":{"canonical_record":{"source":{"id":"2407.15087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T08:05:29Z","cross_cats_sorted":[],"title_canon_sha256":"7b658b4f70c085d9a8220eb0e75181a19cd33fbfd039736bf129d1d82f466cc0","abstract_canon_sha256":"c3a98cad835c6c549fef7ae0435fb939d2b332bfa008ace507ba8533b7751983"},"schema_version":"1.0"},"canonical_sha256":"3b762636a5bc0c2c7c87a3fe1c2897e4f9b4f43d3e636be88eff1f6547cc29dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:38.633887Z","signature_b64":"gsmXH+MYLKkL/HUr4DXIy9EFSs3liV0K/KPS9SidtH6NMEDFgb1KQTKD8AczVusa1c+I14+fuhM8PHV9UW66Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b762636a5bc0c2c7c87a3fe1c2897e4f9b4f43d3e636be88eff1f6547cc29dd","last_reissued_at":"2026-07-05T08:46:38.633483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:38.633483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.15087","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":"2026-07-05T08:46:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o0fuybq3NqEeBms12HulB3gXPuWEfHYRBIDFNm0jsb1ZlNBTtwZaP03cyrVblV3q4LgLNmuZG4h1zhkf+LOzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:22:46.732993Z"},"content_sha256":"83d87cc57a1aa08ad3932b693d65cfbd66ad7242962a2078a0c5f25529e41b61","schema_version":"1.0","event_id":"sha256:83d87cc57a1aa08ad3932b693d65cfbd66ad7242962a2078a0c5f25529e41b61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HN3CMNVFXQGCY7EHUP7BYKEX4T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Navigation Instruction Generation with BEV Perception and Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Rui Liu, Sheng Fan, Wenguan Wang, Yi Yang","submitted_at":"2024-07-21T08:05:29Z","abstract_excerpt":"Navigation instruction generation, which requires embodied agents to describe the navigation routes, has been of great interest in robotics and human-computer interaction. Existing studies directly map the sequence of 2D perspective observations to route descriptions. Though straightforward, they overlook the geometric information and object semantics of the 3D environment. To address these challenges, we propose BEVInstructor, which incorporates Bird's Eye View (BEV) features into Multi-Modal Large Language Models (MLLMs) for instruction generation. Specifically, BEVInstructor constructs a Pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15087","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/2407.15087/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":"2026-07-05T08:46:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YFIydCZ5jDv98EuZiSAqxezR9gT2RuzbNMMkhcOZVYvDcuOLvaS92+twqi9+JZ7gokV0j2wOszhTBFjXGnLPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:22:46.733416Z"},"content_sha256":"885569cdde9e51fb135e1e00e7a1f7cae506033c56497873dc376e153fd2d5f0","schema_version":"1.0","event_id":"sha256:885569cdde9e51fb135e1e00e7a1f7cae506033c56497873dc376e153fd2d5f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HN3CMNVFXQGCY7EHUP7BYKEX4T/bundle.json","state_url":"https://pith.science/pith/HN3CMNVFXQGCY7EHUP7BYKEX4T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HN3CMNVFXQGCY7EHUP7BYKEX4T/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":"2026-07-07T03:22:46Z","links":{"resolver":"https://pith.science/pith/HN3CMNVFXQGCY7EHUP7BYKEX4T","bundle":"https://pith.science/pith/HN3CMNVFXQGCY7EHUP7BYKEX4T/bundle.json","state":"https://pith.science/pith/HN3CMNVFXQGCY7EHUP7BYKEX4T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HN3CMNVFXQGCY7EHUP7BYKEX4T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HN3CMNVFXQGCY7EHUP7BYKEX4T","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":"c3a98cad835c6c549fef7ae0435fb939d2b332bfa008ace507ba8533b7751983","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T08:05:29Z","title_canon_sha256":"7b658b4f70c085d9a8220eb0e75181a19cd33fbfd039736bf129d1d82f466cc0"},"schema_version":"1.0","source":{"id":"2407.15087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15087","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15087v1","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15087","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"pith_short_12","alias_value":"HN3CMNVFXQGC","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"pith_short_16","alias_value":"HN3CMNVFXQGCY7EH","created_at":"2026-07-05T08:46:38Z"},{"alias_kind":"pith_short_8","alias_value":"HN3CMNVF","created_at":"2026-07-05T08:46:38Z"}],"graph_snapshots":[{"event_id":"sha256:885569cdde9e51fb135e1e00e7a1f7cae506033c56497873dc376e153fd2d5f0","target":"graph","created_at":"2026-07-05T08:46:38Z","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/2407.15087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Navigation instruction generation, which requires embodied agents to describe the navigation routes, has been of great interest in robotics and human-computer interaction. Existing studies directly map the sequence of 2D perspective observations to route descriptions. Though straightforward, they overlook the geometric information and object semantics of the 3D environment. To address these challenges, we propose BEVInstructor, which incorporates Bird's Eye View (BEV) features into Multi-Modal Large Language Models (MLLMs) for instruction generation. Specifically, BEVInstructor constructs a Pe","authors_text":"Rui Liu, Sheng Fan, Wenguan Wang, Yi Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T08:05:29Z","title":"Navigation Instruction Generation with BEV Perception and Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15087","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":"sha256:83d87cc57a1aa08ad3932b693d65cfbd66ad7242962a2078a0c5f25529e41b61","target":"record","created_at":"2026-07-05T08:46:38Z","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":"c3a98cad835c6c549fef7ae0435fb939d2b332bfa008ace507ba8533b7751983","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T08:05:29Z","title_canon_sha256":"7b658b4f70c085d9a8220eb0e75181a19cd33fbfd039736bf129d1d82f466cc0"},"schema_version":"1.0","source":{"id":"2407.15087","kind":"arxiv","version":1}},"canonical_sha256":"3b762636a5bc0c2c7c87a3fe1c2897e4f9b4f43d3e636be88eff1f6547cc29dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b762636a5bc0c2c7c87a3fe1c2897e4f9b4f43d3e636be88eff1f6547cc29dd","first_computed_at":"2026-07-05T08:46:38.633483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:38.633483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gsmXH+MYLKkL/HUr4DXIy9EFSs3liV0K/KPS9SidtH6NMEDFgb1KQTKD8AczVusa1c+I14+fuhM8PHV9UW66Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:38.633887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15087","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83d87cc57a1aa08ad3932b693d65cfbd66ad7242962a2078a0c5f25529e41b61","sha256:885569cdde9e51fb135e1e00e7a1f7cae506033c56497873dc376e153fd2d5f0"],"state_sha256":"c646bc65ec6a4765ec3addc8ce8604743c37d327ddb5585233b843acb292c24f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZVwCnnSBAqaf6KsOj5ObFFIPuSVCvV66PYJLU+IMjR9hi7ub/fnjJWDwjAW/rfHtkiSPfMPDICpwmIlHBUk7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:22:46.735747Z","bundle_sha256":"d1bb61d01d78ccb58ebbfeac0ceb2e7a71dbc95f3d4bf425645853f2752a1e43"}}