{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VXOB4GETMIGUQX7E5PD2PFA5PJ","short_pith_number":"pith:VXOB4GET","schema_version":"1.0","canonical_sha256":"addc1e1893620d485fe4ebc7a7941d7a7f8ba7ed3df9380338fd027e3f7298e7","source":{"kind":"arxiv","id":"2511.20785","version":3},"attestation_state":"computed","paper":{"title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Li, Chengwei Qin, Kaichen Zhang, Keming Wu, Lidong Bing, Shijian Lu, Sicong Leng, Sudong Wang, Xingxuan Li, Yifan Zhang, Zuhao Yang","submitted_at":"2025-11-25T19:22:48Z","abstract_excerpt":"Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when processing long-form videos where evidence is sparse and temporally dispersed. Inspired by how humans comprehend long videos - by first skimming globally and then examining relevant clips for details - we introduce LongVT, an end-to-end agentic framework that enables \"Thinking with Long Videos\" via interleaved Multimodal Chain-of-Tool-Thought. Specifically, we exploit LMMs' inherent temporal grounding ability as a native"},"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":"2511.20785","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-25T19:22:48Z","cross_cats_sorted":[],"title_canon_sha256":"290fc79b0c0f06e7c05775738a5c14f0fef9737dd169c941dac1265ac3760094","abstract_canon_sha256":"ea7e29d39e42126bc9bd103c6b62b4e6d75328b003f909da01c428c1abc343d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:51.037207Z","signature_b64":"yiuSVYT3KHDmbzX5ylB/0HGxAUgVTV4TK41bRa/zzKhuysvWMPb1PGfm33OO+RqblZc+oej0R1AgzJvw4q/+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"addc1e1893620d485fe4ebc7a7941d7a7f8ba7ed3df9380338fd027e3f7298e7","last_reissued_at":"2026-05-22T01:03:51.036337Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:51.036337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Li, Chengwei Qin, Kaichen Zhang, Keming Wu, Lidong Bing, Shijian Lu, Sicong Leng, Sudong Wang, Xingxuan Li, Yifan Zhang, Zuhao Yang","submitted_at":"2025-11-25T19:22:48Z","abstract_excerpt":"Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when processing long-form videos where evidence is sparse and temporally dispersed. Inspired by how humans comprehend long videos - by first skimming globally and then examining relevant clips for details - we introduce LongVT, an end-to-end agentic framework that enables \"Thinking with Long Videos\" via interleaved Multimodal Chain-of-Tool-Thought. Specifically, we exploit LMMs' inherent temporal grounding ability as a native"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.20785","kind":"arxiv","version":3},"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/2511.20785/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":"2511.20785","created_at":"2026-05-22T01:03:51.036475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.20785v3","created_at":"2026-05-22T01:03:51.036475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.20785","created_at":"2026-05-22T01:03:51.036475+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXOB4GETMIGU","created_at":"2026-05-22T01:03:51.036475+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXOB4GETMIGUQX7E","created_at":"2026-05-22T01:03:51.036475+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXOB4GET","created_at":"2026-05-22T01:03:51.036475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"2605.20342","citing_title":"ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20342","citing_title":"ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16079","citing_title":"VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13831","citing_title":"Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06094","citing_title":"VISD: Enhancing Video Reasoning via Structured Self-Distillation","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22245","citing_title":"Listening with Time: Precise Temporal Awareness for Long-Form Audio Understanding","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06094","citing_title":"VISD: Enhancing Video Reasoning via Structured Self-Distillation","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06094","citing_title":"VISD: Enhancing Video Reasoning via Structured Self-Distillation","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05079","citing_title":"SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXOB4GETMIGUQX7E5PD2PFA5PJ","json":"https://pith.science/pith/VXOB4GETMIGUQX7E5PD2PFA5PJ.json","graph_json":"https://pith.science/api/pith-number/VXOB4GETMIGUQX7E5PD2PFA5PJ/graph.json","events_json":"https://pith.science/api/pith-number/VXOB4GETMIGUQX7E5PD2PFA5PJ/events.json","paper":"https://pith.science/paper/VXOB4GET"},"agent_actions":{"view_html":"https://pith.science/pith/VXOB4GETMIGUQX7E5PD2PFA5PJ","download_json":"https://pith.science/pith/VXOB4GETMIGUQX7E5PD2PFA5PJ.json","view_paper":"https://pith.science/paper/VXOB4GET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.20785&json=true","fetch_graph":"https://pith.science/api/pith-number/VXOB4GETMIGUQX7E5PD2PFA5PJ/graph.json","fetch_events":"https://pith.science/api/pith-number/VXOB4GETMIGUQX7E5PD2PFA5PJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXOB4GETMIGUQX7E5PD2PFA5PJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXOB4GETMIGUQX7E5PD2PFA5PJ/action/storage_attestation","attest_author":"https://pith.science/pith/VXOB4GETMIGUQX7E5PD2PFA5PJ/action/author_attestation","sign_citation":"https://pith.science/pith/VXOB4GETMIGUQX7E5PD2PFA5PJ/action/citation_signature","submit_replication":"https://pith.science/pith/VXOB4GETMIGUQX7E5PD2PFA5PJ/action/replication_record"}},"created_at":"2026-05-22T01:03:51.036475+00:00","updated_at":"2026-05-22T01:03:51.036475+00:00"}