{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BY4T3NKE54KBUWWJZ37UBIVWQ6","short_pith_number":"pith:BY4T3NKE","schema_version":"1.0","canonical_sha256":"0e393db544ef141a5ac9ceff40a2b687bc15389b9cc443881d57d2f279dd5b77","source":{"kind":"arxiv","id":"2501.01710","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Large Vision Model in Street Scene Semantic Understanding through Leveraging Posterior Optimization Trajectory","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Guangxu Zhu, Jingreng Lei, Ming Tang, Qingfeng Lin, Rongguang Ye, Shuai Wang, Wei-Bin Kou, Yik-Chung Wu","submitted_at":"2025-01-03T09:10:56Z","abstract_excerpt":"To improve the generalization of the autonomous driving (AD) perception model, vehicles need to update the model over time based on the continuously collected data. As time progresses, the amount of data fitted by the AD model expands, which helps to improve the AD model generalization substantially. However, such ever-expanding data is a double-edged sword for the AD model. Specifically, as the fitted data volume grows to exceed the the AD model's fitting capacities, the AD model is prone to under-fitting. To address this issue, we propose to use a pretrained Large Vision Models (LVMs) as bac"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.01710","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T09:10:56Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"28f56451e9b12d2ee5641b3291e3368045b9408836ad27e5448d30d3a7b64b75","abstract_canon_sha256":"0ec7eddc03fb59482db98d6e2ce4ca6c81ca5d1758152bd28ad0c014efd28124"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:18.003503Z","signature_b64":"8eazt3zz6nU/3FukbT11RI4h6eM9l6rV639C/qg36tXZHMi6ec0MvziqxC+adkKPB6EQHXkZ8GNznNLOHUEFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e393db544ef141a5ac9ceff40a2b687bc15389b9cc443881d57d2f279dd5b77","last_reissued_at":"2026-07-05T11:13:18.003041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:18.003041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Large Vision Model in Street Scene Semantic Understanding through Leveraging Posterior Optimization Trajectory","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Guangxu Zhu, Jingreng Lei, Ming Tang, Qingfeng Lin, Rongguang Ye, Shuai Wang, Wei-Bin Kou, Yik-Chung Wu","submitted_at":"2025-01-03T09:10:56Z","abstract_excerpt":"To improve the generalization of the autonomous driving (AD) perception model, vehicles need to update the model over time based on the continuously collected data. As time progresses, the amount of data fitted by the AD model expands, which helps to improve the AD model generalization substantially. However, such ever-expanding data is a double-edged sword for the AD model. Specifically, as the fitted data volume grows to exceed the the AD model's fitting capacities, the AD model is prone to under-fitting. To address this issue, we propose to use a pretrained Large Vision Models (LVMs) as bac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01710","kind":"arxiv","version":2},"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/2501.01710/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.01710","created_at":"2026-07-05T11:13:18.003091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01710v2","created_at":"2026-07-05T11:13:18.003091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01710","created_at":"2026-07-05T11:13:18.003091+00:00"},{"alias_kind":"pith_short_12","alias_value":"BY4T3NKE54KB","created_at":"2026-07-05T11:13:18.003091+00:00"},{"alias_kind":"pith_short_16","alias_value":"BY4T3NKE54KBUWWJ","created_at":"2026-07-05T11:13:18.003091+00:00"},{"alias_kind":"pith_short_8","alias_value":"BY4T3NKE","created_at":"2026-07-05T11:13:18.003091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.11041","citing_title":"Unveiling Uncertainty-Aware Autonomous Cooperative Learning Based Planning Strategy","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BY4T3NKE54KBUWWJZ37UBIVWQ6","json":"https://pith.science/pith/BY4T3NKE54KBUWWJZ37UBIVWQ6.json","graph_json":"https://pith.science/api/pith-number/BY4T3NKE54KBUWWJZ37UBIVWQ6/graph.json","events_json":"https://pith.science/api/pith-number/BY4T3NKE54KBUWWJZ37UBIVWQ6/events.json","paper":"https://pith.science/paper/BY4T3NKE"},"agent_actions":{"view_html":"https://pith.science/pith/BY4T3NKE54KBUWWJZ37UBIVWQ6","download_json":"https://pith.science/pith/BY4T3NKE54KBUWWJZ37UBIVWQ6.json","view_paper":"https://pith.science/paper/BY4T3NKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01710&json=true","fetch_graph":"https://pith.science/api/pith-number/BY4T3NKE54KBUWWJZ37UBIVWQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/BY4T3NKE54KBUWWJZ37UBIVWQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BY4T3NKE54KBUWWJZ37UBIVWQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BY4T3NKE54KBUWWJZ37UBIVWQ6/action/storage_attestation","attest_author":"https://pith.science/pith/BY4T3NKE54KBUWWJZ37UBIVWQ6/action/author_attestation","sign_citation":"https://pith.science/pith/BY4T3NKE54KBUWWJZ37UBIVWQ6/action/citation_signature","submit_replication":"https://pith.science/pith/BY4T3NKE54KBUWWJZ37UBIVWQ6/action/replication_record"}},"created_at":"2026-07-05T11:13:18.003091+00:00","updated_at":"2026-07-05T11:13:18.003091+00:00"}