{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TJU3DQBJPPIMQBPSBQZ2T5C7SG","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":"521c3aba7e475fce78c108a53dd750101227b81fbcc2e44736ed2fd1352be748","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T05:08:06Z","title_canon_sha256":"f98063d6a8bfeb4b55f21e68a65b1ac2f3bde2e8fed851f36ee5b7c4a4f61cd6"},"schema_version":"1.0","source":{"id":"2503.19355","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19355","created_at":"2026-07-05T10:39:28Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19355v2","created_at":"2026-07-05T10:39:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19355","created_at":"2026-07-05T10:39:28Z"},{"alias_kind":"pith_short_12","alias_value":"TJU3DQBJPPIM","created_at":"2026-07-05T10:39:28Z"},{"alias_kind":"pith_short_16","alias_value":"TJU3DQBJPPIMQBPS","created_at":"2026-07-05T10:39:28Z"},{"alias_kind":"pith_short_8","alias_value":"TJU3DQBJ","created_at":"2026-07-05T10:39:28Z"}],"graph_snapshots":[{"event_id":"sha256:28011eee42b2f60f4935fc4cc0e9b67042ff2cec31a51c8b5a20a38a38a7891c","target":"graph","created_at":"2026-07-05T10:39:28Z","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/2503.19355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatio-temporal reasoning is essential in understanding real-world environments in various fields, eg, autonomous driving and sports analytics. Recent advances have improved the spatial reasoning ability of Vision-Language Models (VLMs) by introducing large-scale data, but these models still struggle to analyze kinematic elements like traveled distance and speed of moving objects. To bridge this gap, we construct a spatio-temporal reasoning dataset and benchmark involving kinematic instruction tuning, referred to as STKit and STKit-Bench. They consist of real-world videos with 3D annotations, ","authors_text":"Dohwan Ko, Hyunwoo J. Kim, Manmohan Chandraker, Minseo Yoon, Sihyeon Kim, Vijay Kumar B.G, Yumin Suh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T05:08:06Z","title":"ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19355","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:fb760ff452a20954e1324565f112113287f0463262fba97116b29918bdfbb0b1","target":"record","created_at":"2026-07-05T10:39:28Z","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":"521c3aba7e475fce78c108a53dd750101227b81fbcc2e44736ed2fd1352be748","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T05:08:06Z","title_canon_sha256":"f98063d6a8bfeb4b55f21e68a65b1ac2f3bde2e8fed851f36ee5b7c4a4f61cd6"},"schema_version":"1.0","source":{"id":"2503.19355","kind":"arxiv","version":2}},"canonical_sha256":"9a69b1c0297bd0c805f20c33a9f45f91ae742b1664adabe2edc1d8390fe9f46a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a69b1c0297bd0c805f20c33a9f45f91ae742b1664adabe2edc1d8390fe9f46a","first_computed_at":"2026-07-05T10:39:28.477569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:28.477569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kBOg9LpnIVjrlJW91dmT/WJgFtt6R+3jQSNfT1xlZ+83jHq7VjHgh2VGruZXtnv3jxXPdD5WsOhzUL0HFpvsAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:28.478031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19355","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb760ff452a20954e1324565f112113287f0463262fba97116b29918bdfbb0b1","sha256:28011eee42b2f60f4935fc4cc0e9b67042ff2cec31a51c8b5a20a38a38a7891c"],"state_sha256":"2d459391418514f16f95d5c644dac715c33bcdb3b1e43351f59dfbe21c2bfa03"}