{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V6CFBYHBGFGOQ4PX7QBCUR4XBK","short_pith_number":"pith:V6CFBYHB","schema_version":"1.0","canonical_sha256":"af8450e0e1314ce871f7fc022a47970a9efb643ae4cef252e46de79109d03faf","source":{"kind":"arxiv","id":"2409.01534","version":2},"attestation_state":"computed","paper":{"title":"Cross-domain Multi-step Thinking: Zero-shot Fine-grained Traffic Sign Recognition in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Guang Li, Keisuke Maeda, Miki Haseyama, Ren Togo, Takahiro Ogawa, Yaozong Gan","submitted_at":"2024-09-03T02:08:47Z","abstract_excerpt":"In this study, we propose Cross-domain Multi-step Thinking (CdMT) to improve zero-shot fine-grained traffic sign recognition (TSR) performance in the wild. Zero-shot fine-grained TSR in the wild is challenging due to the cross-domain problem between clean template traffic signs and real-world counterparts, and existing approaches particularly struggle with cross-country TSR scenarios, where traffic signs typically differ between countries. The proposed CdMT framework tackles these challenges by leveraging the multi-step reasoning capabilities of large multimodal models (LMMs). We introduce con"},"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":"2409.01534","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T02:08:47Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"981d5fba04ef7bab0ec9ea24ad7d45e6f4b49f8f1866c61eb53424a0f2b4c53f","abstract_canon_sha256":"13383754ca8a9ce72e8fb550d2504223ed34746160c5174d9becde7768789689"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:35.172624Z","signature_b64":"QQinmn6c0Z3rwIY3txJp3oE3dt3asb9TArsvsEpjfxXKI2Beg0V1FnaJAplH8q7CgvlEZCSzaBgOj3bwKU/YCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af8450e0e1314ce871f7fc022a47970a9efb643ae4cef252e46de79109d03faf","last_reissued_at":"2026-07-05T11:41:35.172094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:35.172094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-domain Multi-step Thinking: Zero-shot Fine-grained Traffic Sign Recognition in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Guang Li, Keisuke Maeda, Miki Haseyama, Ren Togo, Takahiro Ogawa, Yaozong Gan","submitted_at":"2024-09-03T02:08:47Z","abstract_excerpt":"In this study, we propose Cross-domain Multi-step Thinking (CdMT) to improve zero-shot fine-grained traffic sign recognition (TSR) performance in the wild. Zero-shot fine-grained TSR in the wild is challenging due to the cross-domain problem between clean template traffic signs and real-world counterparts, and existing approaches particularly struggle with cross-country TSR scenarios, where traffic signs typically differ between countries. The proposed CdMT framework tackles these challenges by leveraging the multi-step reasoning capabilities of large multimodal models (LMMs). We introduce con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01534","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/2409.01534/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":"2409.01534","created_at":"2026-07-05T11:41:35.172155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01534v2","created_at":"2026-07-05T11:41:35.172155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01534","created_at":"2026-07-05T11:41:35.172155+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6CFBYHBGFGO","created_at":"2026-07-05T11:41:35.172155+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6CFBYHBGFGOQ4PX","created_at":"2026-07-05T11:41:35.172155+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6CFBYHB","created_at":"2026-07-05T11:41:35.172155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.12045","citing_title":"FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V6CFBYHBGFGOQ4PX7QBCUR4XBK","json":"https://pith.science/pith/V6CFBYHBGFGOQ4PX7QBCUR4XBK.json","graph_json":"https://pith.science/api/pith-number/V6CFBYHBGFGOQ4PX7QBCUR4XBK/graph.json","events_json":"https://pith.science/api/pith-number/V6CFBYHBGFGOQ4PX7QBCUR4XBK/events.json","paper":"https://pith.science/paper/V6CFBYHB"},"agent_actions":{"view_html":"https://pith.science/pith/V6CFBYHBGFGOQ4PX7QBCUR4XBK","download_json":"https://pith.science/pith/V6CFBYHBGFGOQ4PX7QBCUR4XBK.json","view_paper":"https://pith.science/paper/V6CFBYHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01534&json=true","fetch_graph":"https://pith.science/api/pith-number/V6CFBYHBGFGOQ4PX7QBCUR4XBK/graph.json","fetch_events":"https://pith.science/api/pith-number/V6CFBYHBGFGOQ4PX7QBCUR4XBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6CFBYHBGFGOQ4PX7QBCUR4XBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6CFBYHBGFGOQ4PX7QBCUR4XBK/action/storage_attestation","attest_author":"https://pith.science/pith/V6CFBYHBGFGOQ4PX7QBCUR4XBK/action/author_attestation","sign_citation":"https://pith.science/pith/V6CFBYHBGFGOQ4PX7QBCUR4XBK/action/citation_signature","submit_replication":"https://pith.science/pith/V6CFBYHBGFGOQ4PX7QBCUR4XBK/action/replication_record"}},"created_at":"2026-07-05T11:41:35.172155+00:00","updated_at":"2026-07-05T11:41:35.172155+00:00"}