{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DG5H4TJQVFXASQKJG5TGQHIRL2","short_pith_number":"pith:DG5H4TJQ","schema_version":"1.0","canonical_sha256":"19ba7e4d30a96e0941493766681d115ebd01d8b1622df24e55034de5415920e5","source":{"kind":"arxiv","id":"2512.10359","version":1},"attestation_state":"computed","paper":{"title":"Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiashuo Cui, Meng-Hao Guo, Shuojin Yang, Sunqi Fan","submitted_at":"2025-12-11T07:17:57Z","abstract_excerpt":"Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios. However, existing Multimodal Large Language Models (MLLMs) struggle with simultaneously modeling spatial relationships within video frames and understanding the causal dynamics of temporal evolution on complex and reasoning-intensive VideoQA task. In this work, we equip MLLM with a comprehensive and extensible Video Toolkit, to enhance MLLM's spatiotemporal reasoning capabilities and ensure the harm"},"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":"2512.10359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T07:17:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"839d17d4c082a48b7d261a65337818febc8c3ffe1e4ab3cd37a119eefe3874ab","abstract_canon_sha256":"342358233017ecc188bfe106166a5f9ec32ad9cab26c6cfb623dc21412cca0f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:30.666965Z","signature_b64":"+Q/8fAwF6CYxdRuRxaB7iBu4lt25GEv3JbI0xfU4uLcw9LdPw2vpA5fywSKgpdNwqEBnmc95+jZayKf8G3jWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19ba7e4d30a96e0941493766681d115ebd01d8b1622df24e55034de5415920e5","last_reissued_at":"2026-06-30T01:17:30.666221Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:30.666221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiashuo Cui, Meng-Hao Guo, Shuojin Yang, Sunqi Fan","submitted_at":"2025-12-11T07:17:57Z","abstract_excerpt":"Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios. However, existing Multimodal Large Language Models (MLLMs) struggle with simultaneously modeling spatial relationships within video frames and understanding the causal dynamics of temporal evolution on complex and reasoning-intensive VideoQA task. In this work, we equip MLLM with a comprehensive and extensible Video Toolkit, to enhance MLLM's spatiotemporal reasoning capabilities and ensure the harm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10359","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/2512.10359/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":"2512.10359","created_at":"2026-06-30T01:17:30.666322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.10359v1","created_at":"2026-06-30T01:17:30.666322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10359","created_at":"2026-06-30T01:17:30.666322+00:00"},{"alias_kind":"pith_short_12","alias_value":"DG5H4TJQVFXA","created_at":"2026-06-30T01:17:30.666322+00:00"},{"alias_kind":"pith_short_16","alias_value":"DG5H4TJQVFXASQKJ","created_at":"2026-06-30T01:17:30.666322+00:00"},{"alias_kind":"pith_short_8","alias_value":"DG5H4TJQ","created_at":"2026-06-30T01:17:30.666322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2603.13091","citing_title":"Reasoning over Video: Evaluating How MLLMs Extract, Integrate, and Reconstruct Spatiotemporal Evidence","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13228","citing_title":"ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09167","citing_title":"MAG-3D: Multi-Agent Grounded Reasoning for 3D Understanding","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2","json":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2.json","graph_json":"https://pith.science/api/pith-number/DG5H4TJQVFXASQKJG5TGQHIRL2/graph.json","events_json":"https://pith.science/api/pith-number/DG5H4TJQVFXASQKJG5TGQHIRL2/events.json","paper":"https://pith.science/paper/DG5H4TJQ"},"agent_actions":{"view_html":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2","download_json":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2.json","view_paper":"https://pith.science/paper/DG5H4TJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.10359&json=true","fetch_graph":"https://pith.science/api/pith-number/DG5H4TJQVFXASQKJG5TGQHIRL2/graph.json","fetch_events":"https://pith.science/api/pith-number/DG5H4TJQVFXASQKJG5TGQHIRL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2/action/storage_attestation","attest_author":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2/action/author_attestation","sign_citation":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2/action/citation_signature","submit_replication":"https://pith.science/pith/DG5H4TJQVFXASQKJG5TGQHIRL2/action/replication_record"}},"created_at":"2026-06-30T01:17:30.666322+00:00","updated_at":"2026-06-30T01:17:30.666322+00:00"}