{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HPN22PYWAEFEQW523GILSI35VY","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":"fe80b453baaa266424857d35f69713dd364e19f50f0125a73d750e7f48720cc4","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T03:48:48Z","title_canon_sha256":"aaadeec1170ec0fbfa7feb943e8e530e7276ce451a90cb0e5ded24732070b54c"},"schema_version":"1.0","source":{"id":"2506.19288","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19288","created_at":"2026-07-05T11:30:02Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19288v2","created_at":"2026-07-05T11:30:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19288","created_at":"2026-07-05T11:30:02Z"},{"alias_kind":"pith_short_12","alias_value":"HPN22PYWAEFE","created_at":"2026-07-05T11:30:02Z"},{"alias_kind":"pith_short_16","alias_value":"HPN22PYWAEFEQW52","created_at":"2026-07-05T11:30:02Z"},{"alias_kind":"pith_short_8","alias_value":"HPN22PYW","created_at":"2026-07-05T11:30:02Z"}],"graph_snapshots":[{"event_id":"sha256:17802cd99895afe21ffb72112f543837021bad6e89898bba65cc7d40b311d15a","target":"graph","created_at":"2026-07-05T11:30:02Z","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/2506.19288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated waterway environment perception is crucial for enabling unmanned surface vessels (USVs) to understand their surroundings and make informed decisions. Most existing waterway perception models primarily focus on instance-level object perception paradigms (e.g., detection, segmentation). However, due to the complexity of waterway environments, current perception datasets and models fail to achieve global semantic understanding of waterways, limiting large-scale monitoring and structured log generation. With the advancement of vision-language models (VLMs), we leverage image captioning t","authors_text":"Hui Xiong, Ningwei Ouyang, Runwei Guan, Ryan Wen Liu, Shang Gao, Shanliang Yao, Shaofeng Liang, Songning Lai, Tianhao Xu, Wei Dai, Xuming Hu, Yafeng Sun, Yutao Yue","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T03:48:48Z","title":"Da Yu: Towards USV-Based Image Captioning for Waterway Surveillance and Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19288","kind":"arxiv","version":2},"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":"sha256:824213a761e42d3f9414c2cf4f0eec4d46d3fca6d2a204985f723e1534b1a513","target":"record","created_at":"2026-07-05T11:30:02Z","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":"fe80b453baaa266424857d35f69713dd364e19f50f0125a73d750e7f48720cc4","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T03:48:48Z","title_canon_sha256":"aaadeec1170ec0fbfa7feb943e8e530e7276ce451a90cb0e5ded24732070b54c"},"schema_version":"1.0","source":{"id":"2506.19288","kind":"arxiv","version":2}},"canonical_sha256":"3bdbad3f16010a485bbad990b9237dae185cd92989d8f7b41486b459e04c263d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bdbad3f16010a485bbad990b9237dae185cd92989d8f7b41486b459e04c263d","first_computed_at":"2026-07-05T11:30:02.471058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:02.471058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O2USlZ/4I8VPAeEaO2xTYCsRdTKiVaDuGFX1FFsNJjV/rHAFm/R9Mm17MYjKwqLmBGuE1/7Fo4DlmY9J49R9AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:02.471543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.19288","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:824213a761e42d3f9414c2cf4f0eec4d46d3fca6d2a204985f723e1534b1a513","sha256:17802cd99895afe21ffb72112f543837021bad6e89898bba65cc7d40b311d15a"],"state_sha256":"7e9d67136037072782deeab3c2a5a135c3cfb60cb2593280ac14547b233115bf"}