{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H5NVLYCFCCBX4C64IDFZB4NGWO","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":"79430a4179e9bd5ba7d85a154a8f4ec9f4f8ceeb4adbeadfd6420685a54ab76f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-27T17:42:32Z","title_canon_sha256":"efcdb4546b3afb1f9aef834e56baa5bd893abbcd4fceed38377cd960772b2e4f"},"schema_version":"1.0","source":{"id":"2606.29023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29023","created_at":"2026-06-30T01:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29023v1","created_at":"2026-06-30T01:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29023","created_at":"2026-06-30T01:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"H5NVLYCFCCBX","created_at":"2026-06-30T01:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"H5NVLYCFCCBX4C64","created_at":"2026-06-30T01:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"H5NVLYCF","created_at":"2026-06-30T01:17:49Z"}],"graph_snapshots":[{"event_id":"sha256:ceec8648fa9393fee125dd6820027be751f65b126bf1e99a077d54f3db510974","target":"graph","created_at":"2026-06-30T01:17:49Z","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/2606.29023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatio-temporal grounding in long videos requires precise temporal localization and robust object tracking conditioned on natural-language queries. While recent vision-language models (VLMs) show strong reasoning ability, directly applying frame-by-frame inference to long sequences is computationally expensive and unstable. We propose a practical pipeline that shifts from frame-level to second-level tracking and performs cross-second smoothing to preserve continuity while reducing sequence length. To improve reasoning supervision, we synthesize chain-of-thought style trajectories using advance","authors_text":"Ji Qi, Lijie Wen, Tianshu Zhang, Yan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-27T17:42:32Z","title":"Efficient Spatio-Temporal Grounding with Multimodal Large Models via Second-Level Tracking and RL Verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29023","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:cc5fabc56292db7164bdb85256271f57eadcdd709406da9287e468b69184ef1f","target":"record","created_at":"2026-06-30T01:17:49Z","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":"79430a4179e9bd5ba7d85a154a8f4ec9f4f8ceeb4adbeadfd6420685a54ab76f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-27T17:42:32Z","title_canon_sha256":"efcdb4546b3afb1f9aef834e56baa5bd893abbcd4fceed38377cd960772b2e4f"},"schema_version":"1.0","source":{"id":"2606.29023","kind":"arxiv","version":1}},"canonical_sha256":"3f5b55e04510837e0bdc40cb90f1a6b3af26451129b12d535bdaf8ac493c56da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f5b55e04510837e0bdc40cb90f1a6b3af26451129b12d535bdaf8ac493c56da","first_computed_at":"2026-06-30T01:17:49.793883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:49.793883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6bbbTyXW9XoXE+YDoac4va2aC3ySp8N52KHigm6HDNnrgeSeI71jiSC7dTVd+CSEDIZMNoggaFfDSxZa24IrAw==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:49.794584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc5fabc56292db7164bdb85256271f57eadcdd709406da9287e468b69184ef1f","sha256:ceec8648fa9393fee125dd6820027be751f65b126bf1e99a077d54f3db510974"],"state_sha256":"944a628d5d4e1b81f070bac459ae5a264ee836e1818d1e5e01667563a747da72"}