{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3NAZPWY3HAULNWZXJ4YDCH73T3","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":"82420b304d2ee15b7579b04c5c4e5a4edbef8b50a81b940ec78e72f924aa7bdc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-19T03:03:29Z","title_canon_sha256":"d6139166c942fee6fd618bf78f420810d8ad6b5e6b62d33f40b58b38f4049f21"},"schema_version":"1.0","source":{"id":"2508.13470","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.13470","created_at":"2026-07-05T11:55:48Z"},{"alias_kind":"arxiv_version","alias_value":"2508.13470v1","created_at":"2026-07-05T11:55:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13470","created_at":"2026-07-05T11:55:48Z"},{"alias_kind":"pith_short_12","alias_value":"3NAZPWY3HAUL","created_at":"2026-07-05T11:55:48Z"},{"alias_kind":"pith_short_16","alias_value":"3NAZPWY3HAULNWZX","created_at":"2026-07-05T11:55:48Z"},{"alias_kind":"pith_short_8","alias_value":"3NAZPWY3","created_at":"2026-07-05T11:55:48Z"}],"graph_snapshots":[{"event_id":"sha256:ad695ad56df449b54fce339732d92955a55fcbd62a6eb124c0e663b2bc880a84","target":"graph","created_at":"2026-07-05T11:55:48Z","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/2508.13470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have emerged as powerful tools for enabling automated traffic analysis; however, current approaches often demand substantial computational resources and struggle with fine-grained spatio-temporal understanding. This paper introduces STER-VLM, a computationally efficient framework that enhances VLM performance through (1) caption decomposition to tackle spatial and temporal information separately, (2) temporal frame selection with best-view filtering for sufficient temporal information, and (3) reference-driven understanding for capturing fine-grained motion and dy","authors_text":"Dat To-Thanh, Phuc Le-Gia, Tien-Huy Nguyen, Tinh-Anh Nguyen-Nhu, Triet Dao Hoang Minh, Tuan Vo-Lan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-19T03:03:29Z","title":"STER-VLM: Spatio-Temporal With Enhanced Reference Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13470","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":"sha256:12f422b26a311086f4b4e97a3b032d018c889f24943b5b7d45270932f3fee2c6","target":"record","created_at":"2026-07-05T11:55:48Z","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":"82420b304d2ee15b7579b04c5c4e5a4edbef8b50a81b940ec78e72f924aa7bdc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-19T03:03:29Z","title_canon_sha256":"d6139166c942fee6fd618bf78f420810d8ad6b5e6b62d33f40b58b38f4049f21"},"schema_version":"1.0","source":{"id":"2508.13470","kind":"arxiv","version":1}},"canonical_sha256":"db4197db1b3828b6db374f30311ffb9ef03de59c65d5d21cb063ddfb8d2b5258","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db4197db1b3828b6db374f30311ffb9ef03de59c65d5d21cb063ddfb8d2b5258","first_computed_at":"2026-07-05T11:55:48.566455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:48.566455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7K/E5BO99Ia1d/9gCEnmKtXjJ48XR/lN1a5INoy2crVHXpIzhEzRjPTdYaveOtY053Ju2PJgTwrU5tr8XQRuAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:48.566922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.13470","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12f422b26a311086f4b4e97a3b032d018c889f24943b5b7d45270932f3fee2c6","sha256:ad695ad56df449b54fce339732d92955a55fcbd62a6eb124c0e663b2bc880a84"],"state_sha256":"0db63640322cc1e32d145f82bcb22c858123c3aaf9858a471aef011ddd0c7c8d"}