{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3NAZPWY3HAULNWZXJ4YDCH73T3","short_pith_number":"pith:3NAZPWY3","schema_version":"1.0","canonical_sha256":"db4197db1b3828b6db374f30311ffb9ef03de59c65d5d21cb063ddfb8d2b5258","source":{"kind":"arxiv","id":"2508.13470","version":1},"attestation_state":"computed","paper":{"title":"STER-VLM: Spatio-Temporal With Enhanced Reference Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dat To-Thanh, Phuc Le-Gia, Tien-Huy Nguyen, Tinh-Anh Nguyen-Nhu, Triet Dao Hoang Minh, Tuan Vo-Lan","submitted_at":"2025-08-19T03:03:29Z","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"},"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":"2508.13470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-19T03:03:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6139166c942fee6fd618bf78f420810d8ad6b5e6b62d33f40b58b38f4049f21","abstract_canon_sha256":"82420b304d2ee15b7579b04c5c4e5a4edbef8b50a81b940ec78e72f924aa7bdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:48.566922Z","signature_b64":"7K/E5BO99Ia1d/9gCEnmKtXjJ48XR/lN1a5INoy2crVHXpIzhEzRjPTdYaveOtY053Ju2PJgTwrU5tr8XQRuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db4197db1b3828b6db374f30311ffb9ef03de59c65d5d21cb063ddfb8d2b5258","last_reissued_at":"2026-07-05T11:55:48.566455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:48.566455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STER-VLM: Spatio-Temporal With Enhanced Reference Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dat To-Thanh, Phuc Le-Gia, Tien-Huy Nguyen, Tinh-Anh Nguyen-Nhu, Triet Dao Hoang Minh, Tuan Vo-Lan","submitted_at":"2025-08-19T03:03:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13470","kind":"arxiv","version":1},"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/2508.13470/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":"2508.13470","created_at":"2026-07-05T11:55:48.566520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13470v1","created_at":"2026-07-05T11:55:48.566520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13470","created_at":"2026-07-05T11:55:48.566520+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NAZPWY3HAUL","created_at":"2026-07-05T11:55:48.566520+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NAZPWY3HAULNWZX","created_at":"2026-07-05T11:55:48.566520+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NAZPWY3","created_at":"2026-07-05T11:55:48.566520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02089","citing_title":"ESC: Emotional Self-Correction for Reliable Vision-Language Models","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NAZPWY3HAULNWZXJ4YDCH73T3","json":"https://pith.science/pith/3NAZPWY3HAULNWZXJ4YDCH73T3.json","graph_json":"https://pith.science/api/pith-number/3NAZPWY3HAULNWZXJ4YDCH73T3/graph.json","events_json":"https://pith.science/api/pith-number/3NAZPWY3HAULNWZXJ4YDCH73T3/events.json","paper":"https://pith.science/paper/3NAZPWY3"},"agent_actions":{"view_html":"https://pith.science/pith/3NAZPWY3HAULNWZXJ4YDCH73T3","download_json":"https://pith.science/pith/3NAZPWY3HAULNWZXJ4YDCH73T3.json","view_paper":"https://pith.science/paper/3NAZPWY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13470&json=true","fetch_graph":"https://pith.science/api/pith-number/3NAZPWY3HAULNWZXJ4YDCH73T3/graph.json","fetch_events":"https://pith.science/api/pith-number/3NAZPWY3HAULNWZXJ4YDCH73T3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NAZPWY3HAULNWZXJ4YDCH73T3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NAZPWY3HAULNWZXJ4YDCH73T3/action/storage_attestation","attest_author":"https://pith.science/pith/3NAZPWY3HAULNWZXJ4YDCH73T3/action/author_attestation","sign_citation":"https://pith.science/pith/3NAZPWY3HAULNWZXJ4YDCH73T3/action/citation_signature","submit_replication":"https://pith.science/pith/3NAZPWY3HAULNWZXJ4YDCH73T3/action/replication_record"}},"created_at":"2026-07-05T11:55:48.566520+00:00","updated_at":"2026-07-05T11:55:48.566520+00:00"}