{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QTV44Q44I75I3WIFWNPP42ZJKP","short_pith_number":"pith:QTV44Q44","schema_version":"1.0","canonical_sha256":"84ebce439c47fa8dd905b35efe6b2953c09860d5fa1eec3cf2d4a83e27ed48ca","source":{"kind":"arxiv","id":"2512.05277","version":3},"attestation_state":"computed","paper":{"title":"From Segments to Scenes: Temporal Understanding in Autonomous Driving via Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmad Rezaei, Alireza Heidarikhazaei, Kevin Cannons, Mohammad Akbari, Mohammad Asiful Hossain, Mohsen Gholami, Saeed Ranjbar Alvar, Yong Zhang, Zhou Weimin","submitted_at":"2025-12-04T21:57:10Z","abstract_excerpt":"Vision-Language Models (VLMs) are increasingly deployed as the perception and reasoning backbone of autonomous agents acting in the wild, with autonomous driving (AD) being one of the most safety-critical instances. Reliable temporal understanding is essential for such agents to anticipate events, attribute causes, and act safely in dynamic environments, yet this remains a significant challenge even for state-of-the-art (SoTA) VLMs. Prior video benchmarks have emphasized other content (sports, cooking, etc.), yet no existing benchmark focuses exclusively on temporal understanding for both shor"},"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":"2512.05277","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-04T21:57:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c269b6d49f2183ebc9f4df51f71fcac7fe9a8b1e360b56c868d6b2e1fdfa5fa2","abstract_canon_sha256":"404e839deb1067c9d13531b0fa837ec89da16ef5f14f0159bc71353a0a2954c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:39.100359Z","signature_b64":"QGwoVpUNsIQa6Z/eOlffwQrebyPzT4Rn2QY+HhNuUHn6htZWludCA7odr1da62PnRnkQW7mQ20CGZ+DBk6drBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84ebce439c47fa8dd905b35efe6b2953c09860d5fa1eec3cf2d4a83e27ed48ca","last_reissued_at":"2026-06-02T01:03:39.099819Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:39.099819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Segments to Scenes: Temporal Understanding in Autonomous Driving via Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmad Rezaei, Alireza Heidarikhazaei, Kevin Cannons, Mohammad Akbari, Mohammad Asiful Hossain, Mohsen Gholami, Saeed Ranjbar Alvar, Yong Zhang, Zhou Weimin","submitted_at":"2025-12-04T21:57:10Z","abstract_excerpt":"Vision-Language Models (VLMs) are increasingly deployed as the perception and reasoning backbone of autonomous agents acting in the wild, with autonomous driving (AD) being one of the most safety-critical instances. Reliable temporal understanding is essential for such agents to anticipate events, attribute causes, and act safely in dynamic environments, yet this remains a significant challenge even for state-of-the-art (SoTA) VLMs. Prior video benchmarks have emphasized other content (sports, cooking, etc.), yet no existing benchmark focuses exclusively on temporal understanding for both shor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.05277","kind":"arxiv","version":3},"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/2512.05277/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":"2512.05277","created_at":"2026-06-02T01:03:39.099886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.05277v3","created_at":"2026-06-02T01:03:39.099886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.05277","created_at":"2026-06-02T01:03:39.099886+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTV44Q44I75I","created_at":"2026-06-02T01:03:39.099886+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTV44Q44I75I3WIF","created_at":"2026-06-02T01:03:39.099886+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTV44Q44","created_at":"2026-06-02T01:03:39.099886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTV44Q44I75I3WIFWNPP42ZJKP","json":"https://pith.science/pith/QTV44Q44I75I3WIFWNPP42ZJKP.json","graph_json":"https://pith.science/api/pith-number/QTV44Q44I75I3WIFWNPP42ZJKP/graph.json","events_json":"https://pith.science/api/pith-number/QTV44Q44I75I3WIFWNPP42ZJKP/events.json","paper":"https://pith.science/paper/QTV44Q44"},"agent_actions":{"view_html":"https://pith.science/pith/QTV44Q44I75I3WIFWNPP42ZJKP","download_json":"https://pith.science/pith/QTV44Q44I75I3WIFWNPP42ZJKP.json","view_paper":"https://pith.science/paper/QTV44Q44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.05277&json=true","fetch_graph":"https://pith.science/api/pith-number/QTV44Q44I75I3WIFWNPP42ZJKP/graph.json","fetch_events":"https://pith.science/api/pith-number/QTV44Q44I75I3WIFWNPP42ZJKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTV44Q44I75I3WIFWNPP42ZJKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTV44Q44I75I3WIFWNPP42ZJKP/action/storage_attestation","attest_author":"https://pith.science/pith/QTV44Q44I75I3WIFWNPP42ZJKP/action/author_attestation","sign_citation":"https://pith.science/pith/QTV44Q44I75I3WIFWNPP42ZJKP/action/citation_signature","submit_replication":"https://pith.science/pith/QTV44Q44I75I3WIFWNPP42ZJKP/action/replication_record"}},"created_at":"2026-06-02T01:03:39.099886+00:00","updated_at":"2026-06-02T01:03:39.099886+00:00"}