{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QTV44Q44I75I3WIFWNPP42ZJKP","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":"404e839deb1067c9d13531b0fa837ec89da16ef5f14f0159bc71353a0a2954c9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-04T21:57:10Z","title_canon_sha256":"c269b6d49f2183ebc9f4df51f71fcac7fe9a8b1e360b56c868d6b2e1fdfa5fa2"},"schema_version":"1.0","source":{"id":"2512.05277","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.05277","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2512.05277v3","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.05277","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"QTV44Q44I75I","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"QTV44Q44I75I3WIF","created_at":"2026-06-02T01:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"QTV44Q44","created_at":"2026-06-02T01:03:39Z"}],"graph_snapshots":[{"event_id":"sha256:0800c63411c164f7a45c917e37788cf07f96908a4cd30dc022519bee6ca93ffd","target":"graph","created_at":"2026-06-02T01:03:39Z","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/2512.05277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ahmad Rezaei, Alireza Heidarikhazaei, Kevin Cannons, Mohammad Akbari, Mohammad Asiful Hossain, Mohsen Gholami, Saeed Ranjbar Alvar, Yong Zhang, Zhou Weimin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-04T21:57:10Z","title":"From Segments to Scenes: Temporal Understanding in Autonomous Driving via Vision-Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.05277","kind":"arxiv","version":3},"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:a3b916dded740485e2b7d52d2cc2f6a9578a83519547d389e693687920a3bf0c","target":"record","created_at":"2026-06-02T01:03:39Z","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":"404e839deb1067c9d13531b0fa837ec89da16ef5f14f0159bc71353a0a2954c9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-04T21:57:10Z","title_canon_sha256":"c269b6d49f2183ebc9f4df51f71fcac7fe9a8b1e360b56c868d6b2e1fdfa5fa2"},"schema_version":"1.0","source":{"id":"2512.05277","kind":"arxiv","version":3}},"canonical_sha256":"84ebce439c47fa8dd905b35efe6b2953c09860d5fa1eec3cf2d4a83e27ed48ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84ebce439c47fa8dd905b35efe6b2953c09860d5fa1eec3cf2d4a83e27ed48ca","first_computed_at":"2026-06-02T01:03:39.099819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:39.099819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QGwoVpUNsIQa6Z/eOlffwQrebyPzT4Rn2QY+HhNuUHn6htZWludCA7odr1da62PnRnkQW7mQ20CGZ+DBk6drBg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:39.100359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.05277","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3b916dded740485e2b7d52d2cc2f6a9578a83519547d389e693687920a3bf0c","sha256:0800c63411c164f7a45c917e37788cf07f96908a4cd30dc022519bee6ca93ffd"],"state_sha256":"c0c4dade14d7bcb0b4cb56600a0f44d74d7ac654dbab801097577ab323de68db"}