{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WFB2TFVXECKXDKXVQMMSRZ4BEZ","short_pith_number":"pith:WFB2TFVX","schema_version":"1.0","canonical_sha256":"b143a996b7209571aaf5831928e78126551dd8cd88c6fd3404848f74ec06cb83","source":{"kind":"arxiv","id":"2410.12075","version":2},"attestation_state":"computed","paper":{"title":"WeatherDG: LLM-assisted Diffusion Model for Procedural Weather Generation in Domain-Generalized Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenghao Qian, Wenjing Li, Yuhong Mo, Yuhu Guo","submitted_at":"2024-10-15T21:29:26Z","abstract_excerpt":"In this work, we propose a novel approach, namely WeatherDG, that can generate realistic, weather-diverse, and driving-screen images based on the cooperation of two foundation models, i.e, Stable Diffusion (SD) and Large Language Model (LLM). Specifically, we first fine-tune the SD with source data, aligning the content and layout of generated samples with real-world driving scenarios. Then, we propose a procedural prompt generation method based on LLM, which can enrich scenario descriptions and help SD automatically generate more diverse, detailed images. In addition, we introduce a balanced "},"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":"2410.12075","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T21:29:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4504bb0c2a08482b8406754ecf649d6947f37adfca92f7af49ecf3443939e10","abstract_canon_sha256":"1c2f280246da179b9ec6e13a49755559811804ba3d54e5f80b7394c295a18b53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:13.362196Z","signature_b64":"FkAJbnOqAcdgCrWNXc1vzYwERIH7jA9PZ841uMxr0MBcpIhWo1VOTSB4gqVGkcbIQvxINa1NVtSrILIfO6BmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b143a996b7209571aaf5831928e78126551dd8cd88c6fd3404848f74ec06cb83","last_reissued_at":"2026-07-05T09:55:13.361764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:13.361764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WeatherDG: LLM-assisted Diffusion Model for Procedural Weather Generation in Domain-Generalized Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenghao Qian, Wenjing Li, Yuhong Mo, Yuhu Guo","submitted_at":"2024-10-15T21:29:26Z","abstract_excerpt":"In this work, we propose a novel approach, namely WeatherDG, that can generate realistic, weather-diverse, and driving-screen images based on the cooperation of two foundation models, i.e, Stable Diffusion (SD) and Large Language Model (LLM). Specifically, we first fine-tune the SD with source data, aligning the content and layout of generated samples with real-world driving scenarios. Then, we propose a procedural prompt generation method based on LLM, which can enrich scenario descriptions and help SD automatically generate more diverse, detailed images. In addition, we introduce a balanced "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12075","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/2410.12075/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":"2410.12075","created_at":"2026-07-05T09:55:13.361821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12075v2","created_at":"2026-07-05T09:55:13.361821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12075","created_at":"2026-07-05T09:55:13.361821+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFB2TFVXECKX","created_at":"2026-07-05T09:55:13.361821+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFB2TFVXECKXDKXV","created_at":"2026-07-05T09:55:13.361821+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFB2TFVX","created_at":"2026-07-05T09:55:13.361821+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06513","citing_title":"What Demands Attention in Urban Street Scenes? From Scene Understanding towards Road Safety: A Survey of Vision-driven Datasets and Studies","ref_index":205,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WFB2TFVXECKXDKXVQMMSRZ4BEZ","json":"https://pith.science/pith/WFB2TFVXECKXDKXVQMMSRZ4BEZ.json","graph_json":"https://pith.science/api/pith-number/WFB2TFVXECKXDKXVQMMSRZ4BEZ/graph.json","events_json":"https://pith.science/api/pith-number/WFB2TFVXECKXDKXVQMMSRZ4BEZ/events.json","paper":"https://pith.science/paper/WFB2TFVX"},"agent_actions":{"view_html":"https://pith.science/pith/WFB2TFVXECKXDKXVQMMSRZ4BEZ","download_json":"https://pith.science/pith/WFB2TFVXECKXDKXVQMMSRZ4BEZ.json","view_paper":"https://pith.science/paper/WFB2TFVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12075&json=true","fetch_graph":"https://pith.science/api/pith-number/WFB2TFVXECKXDKXVQMMSRZ4BEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WFB2TFVXECKXDKXVQMMSRZ4BEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFB2TFVXECKXDKXVQMMSRZ4BEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFB2TFVXECKXDKXVQMMSRZ4BEZ/action/storage_attestation","attest_author":"https://pith.science/pith/WFB2TFVXECKXDKXVQMMSRZ4BEZ/action/author_attestation","sign_citation":"https://pith.science/pith/WFB2TFVXECKXDKXVQMMSRZ4BEZ/action/citation_signature","submit_replication":"https://pith.science/pith/WFB2TFVXECKXDKXVQMMSRZ4BEZ/action/replication_record"}},"created_at":"2026-07-05T09:55:13.361821+00:00","updated_at":"2026-07-05T09:55:13.361821+00:00"}