{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PGLRDNR5V5FI6FQVFCCLT7W23M","short_pith_number":"pith:PGLRDNR5","canonical_record":{"source":{"id":"2412.19406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T02:05:38Z","cross_cats_sorted":[],"title_canon_sha256":"bd2f29245528ba9a2d667bc4f600074e2d32a090e0ebe36d9a95f3e21e2a4fd3","abstract_canon_sha256":"1a5eae227916d0acaaed1534d73ceb5853afbdfa1d2adf40ad2d4b708dd4c54c"},"schema_version":"1.0"},"canonical_sha256":"799711b63daf4a8f16152884b9fedadb3965965273bf90569cd5535c9f33d4b0","source":{"kind":"arxiv","id":"2412.19406","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19406","created_at":"2026-07-05T09:54:35Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19406v1","created_at":"2026-07-05T09:54:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19406","created_at":"2026-07-05T09:54:35Z"},{"alias_kind":"pith_short_12","alias_value":"PGLRDNR5V5FI","created_at":"2026-07-05T09:54:35Z"},{"alias_kind":"pith_short_16","alias_value":"PGLRDNR5V5FI6FQV","created_at":"2026-07-05T09:54:35Z"},{"alias_kind":"pith_short_8","alias_value":"PGLRDNR5","created_at":"2026-07-05T09:54:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PGLRDNR5V5FI6FQVFCCLT7W23M","target":"record","payload":{"canonical_record":{"source":{"id":"2412.19406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T02:05:38Z","cross_cats_sorted":[],"title_canon_sha256":"bd2f29245528ba9a2d667bc4f600074e2d32a090e0ebe36d9a95f3e21e2a4fd3","abstract_canon_sha256":"1a5eae227916d0acaaed1534d73ceb5853afbdfa1d2adf40ad2d4b708dd4c54c"},"schema_version":"1.0"},"canonical_sha256":"799711b63daf4a8f16152884b9fedadb3965965273bf90569cd5535c9f33d4b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:35.079762Z","signature_b64":"XswnWzVkR+kIdpIfr7e+QQ55AT3+NML+cC50S2TQERgwnAJ2/TFXrfl5isZsCtV5oIiMewVdZDGZG8CQrXu0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"799711b63daf4a8f16152884b9fedadb3965965273bf90569cd5535c9f33d4b0","last_reissued_at":"2026-07-05T09:54:35.079300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:35.079300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.19406","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":"2026-07-05T09:54:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bDbk1xriRtcpRIs3MaDxs/BdUIJ3/OMthisqEB9PSYFarR/6as4tyE7ipjLVLoK0hYmBYBAHQeDCkYO6I7z8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T04:39:32.212942Z"},"content_sha256":"07c43689860ee0fe479d79249bb1440cfe12b164e14449b4b0922db4db27d8c7","schema_version":"1.0","event_id":"sha256:07c43689860ee0fe479d79249bb1440cfe12b164e14449b4b0922db4db27d8c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PGLRDNR5V5FI6FQVFCCLT7W23M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingzhao Gao, Hongqing Chu, Jianhao Yu, Jianhua Wu, Jiaqi Fan, Jincheng Gao, Yafei Wang","submitted_at":"2024-12-27T02:05:38Z","abstract_excerpt":"Multimodal large language models (MLLMs) have shown satisfactory effects in many autonomous driving tasks. In this paper, MLLMs are utilized to solve joint semantic scene understanding and risk localization tasks, while only relying on front-view images. In the proposed MLLM-SUL framework, a dual-branch visual encoder is first designed to extract features from two resolutions, and rich visual information is conducive to the language model describing risk objects of different sizes accurately. Then for the language generation, LLaMA model is fine-tuned to predict scene descriptions, containing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19406","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/2412.19406/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":"2026-07-05T09:54:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FR+0LCzkZhls9I7QUyecckd8+Wg+WJ4oEK8gi8Sla2P+vov19CbkzfKjAtSbmeZKCQowizZfSPv2Tyx3uUskDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T04:39:32.213455Z"},"content_sha256":"8b6e5eb06730ed3de4712b2e8961bfabdb3c961d772130a677c93735c6d789d8","schema_version":"1.0","event_id":"sha256:8b6e5eb06730ed3de4712b2e8961bfabdb3c961d772130a677c93735c6d789d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PGLRDNR5V5FI6FQVFCCLT7W23M/bundle.json","state_url":"https://pith.science/pith/PGLRDNR5V5FI6FQVFCCLT7W23M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PGLRDNR5V5FI6FQVFCCLT7W23M/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":"2026-08-23T04:39:32Z","links":{"resolver":"https://pith.science/pith/PGLRDNR5V5FI6FQVFCCLT7W23M","bundle":"https://pith.science/pith/PGLRDNR5V5FI6FQVFCCLT7W23M/bundle.json","state":"https://pith.science/pith/PGLRDNR5V5FI6FQVFCCLT7W23M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PGLRDNR5V5FI6FQVFCCLT7W23M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PGLRDNR5V5FI6FQVFCCLT7W23M","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":"1a5eae227916d0acaaed1534d73ceb5853afbdfa1d2adf40ad2d4b708dd4c54c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T02:05:38Z","title_canon_sha256":"bd2f29245528ba9a2d667bc4f600074e2d32a090e0ebe36d9a95f3e21e2a4fd3"},"schema_version":"1.0","source":{"id":"2412.19406","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19406","created_at":"2026-07-05T09:54:35Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19406v1","created_at":"2026-07-05T09:54:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19406","created_at":"2026-07-05T09:54:35Z"},{"alias_kind":"pith_short_12","alias_value":"PGLRDNR5V5FI","created_at":"2026-07-05T09:54:35Z"},{"alias_kind":"pith_short_16","alias_value":"PGLRDNR5V5FI6FQV","created_at":"2026-07-05T09:54:35Z"},{"alias_kind":"pith_short_8","alias_value":"PGLRDNR5","created_at":"2026-07-05T09:54:35Z"}],"graph_snapshots":[{"event_id":"sha256:8b6e5eb06730ed3de4712b2e8961bfabdb3c961d772130a677c93735c6d789d8","target":"graph","created_at":"2026-07-05T09:54:35Z","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/2412.19406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have shown satisfactory effects in many autonomous driving tasks. In this paper, MLLMs are utilized to solve joint semantic scene understanding and risk localization tasks, while only relying on front-view images. In the proposed MLLM-SUL framework, a dual-branch visual encoder is first designed to extract features from two resolutions, and rich visual information is conducive to the language model describing risk objects of different sizes accurately. Then for the language generation, LLaMA model is fine-tuned to predict scene descriptions, containing ","authors_text":"Bingzhao Gao, Hongqing Chu, Jianhao Yu, Jianhua Wu, Jiaqi Fan, Jincheng Gao, Yafei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T02:05:38Z","title":"MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19406","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":"sha256:07c43689860ee0fe479d79249bb1440cfe12b164e14449b4b0922db4db27d8c7","target":"record","created_at":"2026-07-05T09:54:35Z","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":"1a5eae227916d0acaaed1534d73ceb5853afbdfa1d2adf40ad2d4b708dd4c54c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T02:05:38Z","title_canon_sha256":"bd2f29245528ba9a2d667bc4f600074e2d32a090e0ebe36d9a95f3e21e2a4fd3"},"schema_version":"1.0","source":{"id":"2412.19406","kind":"arxiv","version":1}},"canonical_sha256":"799711b63daf4a8f16152884b9fedadb3965965273bf90569cd5535c9f33d4b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"799711b63daf4a8f16152884b9fedadb3965965273bf90569cd5535c9f33d4b0","first_computed_at":"2026-07-05T09:54:35.079300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:35.079300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XswnWzVkR+kIdpIfr7e+QQ55AT3+NML+cC50S2TQERgwnAJ2/TFXrfl5isZsCtV5oIiMewVdZDGZG8CQrXu0BA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:35.079762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19406","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07c43689860ee0fe479d79249bb1440cfe12b164e14449b4b0922db4db27d8c7","sha256:8b6e5eb06730ed3de4712b2e8961bfabdb3c961d772130a677c93735c6d789d8"],"state_sha256":"e534d8deb64dd9a8a8cb584386bb6568f51117f5f1a6be7f64e53b9c47149350"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b5+NesRhWm90JglmV0GYWKUf8tTbSOC1qjignwj3xefv1lX/EDsEzQzOHe3tw/loIacp2vWPVW3hOtSuJ4WRAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T04:39:32.219093Z","bundle_sha256":"fbf3f0bcf6efb71d7f3a1b042319befb403127520de833cddd4ba4de8e9eb020"}}