{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H5NVLYCFCCBX4C64IDFZB4NGWO","short_pith_number":"pith:H5NVLYCF","schema_version":"1.0","canonical_sha256":"3f5b55e04510837e0bdc40cb90f1a6b3af26451129b12d535bdaf8ac493c56da","source":{"kind":"arxiv","id":"2606.29023","version":1},"attestation_state":"computed","paper":{"title":"Efficient Spatio-Temporal Grounding with Multimodal Large Models via Second-Level Tracking and RL Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ji Qi, Lijie Wen, Tianshu Zhang, Yan Wang","submitted_at":"2026-06-27T17:42:32Z","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"},"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":"2606.29023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-27T17:42:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"efcdb4546b3afb1f9aef834e56baa5bd893abbcd4fceed38377cd960772b2e4f","abstract_canon_sha256":"79430a4179e9bd5ba7d85a154a8f4ec9f4f8ceeb4adbeadfd6420685a54ab76f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:49.794584Z","signature_b64":"6bbbTyXW9XoXE+YDoac4va2aC3ySp8N52KHigm6HDNnrgeSeI71jiSC7dTVd+CSEDIZMNoggaFfDSxZa24IrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f5b55e04510837e0bdc40cb90f1a6b3af26451129b12d535bdaf8ac493c56da","last_reissued_at":"2026-06-30T01:17:49.793883Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:49.793883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Spatio-Temporal Grounding with Multimodal Large Models via Second-Level Tracking and RL Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ji Qi, Lijie Wen, Tianshu Zhang, Yan Wang","submitted_at":"2026-06-27T17:42:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29023","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/2606.29023/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":"2606.29023","created_at":"2026-06-30T01:17:49.794045+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29023v1","created_at":"2026-06-30T01:17:49.794045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29023","created_at":"2026-06-30T01:17:49.794045+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5NVLYCFCCBX","created_at":"2026-06-30T01:17:49.794045+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5NVLYCFCCBX4C64","created_at":"2026-06-30T01:17:49.794045+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5NVLYCF","created_at":"2026-06-30T01:17:49.794045+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/H5NVLYCFCCBX4C64IDFZB4NGWO","json":"https://pith.science/pith/H5NVLYCFCCBX4C64IDFZB4NGWO.json","graph_json":"https://pith.science/api/pith-number/H5NVLYCFCCBX4C64IDFZB4NGWO/graph.json","events_json":"https://pith.science/api/pith-number/H5NVLYCFCCBX4C64IDFZB4NGWO/events.json","paper":"https://pith.science/paper/H5NVLYCF"},"agent_actions":{"view_html":"https://pith.science/pith/H5NVLYCFCCBX4C64IDFZB4NGWO","download_json":"https://pith.science/pith/H5NVLYCFCCBX4C64IDFZB4NGWO.json","view_paper":"https://pith.science/paper/H5NVLYCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29023&json=true","fetch_graph":"https://pith.science/api/pith-number/H5NVLYCFCCBX4C64IDFZB4NGWO/graph.json","fetch_events":"https://pith.science/api/pith-number/H5NVLYCFCCBX4C64IDFZB4NGWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5NVLYCFCCBX4C64IDFZB4NGWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5NVLYCFCCBX4C64IDFZB4NGWO/action/storage_attestation","attest_author":"https://pith.science/pith/H5NVLYCFCCBX4C64IDFZB4NGWO/action/author_attestation","sign_citation":"https://pith.science/pith/H5NVLYCFCCBX4C64IDFZB4NGWO/action/citation_signature","submit_replication":"https://pith.science/pith/H5NVLYCFCCBX4C64IDFZB4NGWO/action/replication_record"}},"created_at":"2026-06-30T01:17:49.794045+00:00","updated_at":"2026-06-30T01:17:49.794045+00:00"}