{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YPOOHLKM5UOBHDPLUV7ONCO3QQ","short_pith_number":"pith:YPOOHLKM","schema_version":"1.0","canonical_sha256":"c3dce3ad4ced1c138deba57ee689db8431d64e0656ac0ddb522ea044039efeca","source":{"kind":"arxiv","id":"2606.12195","version":1},"attestation_state":"computed","paper":{"title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiashuo Yu, Kai Chen, Kanghui Tian, Limin Wang, Sheng Xia, Songze Li, Tianxiang Jiang, Yicheng Xu, Yinan He, Yi Wang, Yue Wu, Yu Qiao, Ziang Yan","submitted_at":"2026-06-10T15:17:08Z","abstract_excerpt":"Recent progress in foundation models has shifted toward agentic behavior involving multi-step reasoning and tool use. However, open-source efforts largely focus on text-dominant settings, leaving long-horizon multimodal tasks underexplored. This gap is evident in video tasks requiring sustained temporal understanding and iterative interaction. We present InternVideo3, a framework enhancing these capabilities via Multimodal Contextual Reasoning (MCR). MCR treats understanding as a closed-loop process over a shared, evolving context containing observations, instructions, reasoning, tool actions,"},"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":"2606.12195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T15:17:08Z","cross_cats_sorted":[],"title_canon_sha256":"6b391a27ad640ab67c586ab3c145f3722b9fad180d7e458b40a91701109b53e9","abstract_canon_sha256":"4db938d3af646c73f049a521d549c748f93fdda6c52ac0080935482c19cb943a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:53.566020Z","signature_b64":"Zn+Fs/Sm03DL1/hjNe+cZ1B+b+s3VVnI0VtkkfYZqPM3cFZ+QU1xXT4vsv8Zx5XzLCt80VUDA/o1jOSoRLBnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3dce3ad4ced1c138deba57ee689db8431d64e0656ac0ddb522ea044039efeca","last_reissued_at":"2026-06-11T01:10:53.565178Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:53.565178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiashuo Yu, Kai Chen, Kanghui Tian, Limin Wang, Sheng Xia, Songze Li, Tianxiang Jiang, Yicheng Xu, Yinan He, Yi Wang, Yue Wu, Yu Qiao, Ziang Yan","submitted_at":"2026-06-10T15:17:08Z","abstract_excerpt":"Recent progress in foundation models has shifted toward agentic behavior involving multi-step reasoning and tool use. However, open-source efforts largely focus on text-dominant settings, leaving long-horizon multimodal tasks underexplored. This gap is evident in video tasks requiring sustained temporal understanding and iterative interaction. We present InternVideo3, a framework enhancing these capabilities via Multimodal Contextual Reasoning (MCR). MCR treats understanding as a closed-loop process over a shared, evolving context containing observations, instructions, reasoning, tool actions,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12195","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/2606.12195/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":"2606.12195","created_at":"2026-06-11T01:10:53.565331+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12195v1","created_at":"2026-06-11T01:10:53.565331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12195","created_at":"2026-06-11T01:10:53.565331+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPOOHLKM5UOB","created_at":"2026-06-11T01:10:53.565331+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPOOHLKM5UOBHDPL","created_at":"2026-06-11T01:10:53.565331+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPOOHLKM","created_at":"2026-06-11T01:10:53.565331+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/YPOOHLKM5UOBHDPLUV7ONCO3QQ","json":"https://pith.science/pith/YPOOHLKM5UOBHDPLUV7ONCO3QQ.json","graph_json":"https://pith.science/api/pith-number/YPOOHLKM5UOBHDPLUV7ONCO3QQ/graph.json","events_json":"https://pith.science/api/pith-number/YPOOHLKM5UOBHDPLUV7ONCO3QQ/events.json","paper":"https://pith.science/paper/YPOOHLKM"},"agent_actions":{"view_html":"https://pith.science/pith/YPOOHLKM5UOBHDPLUV7ONCO3QQ","download_json":"https://pith.science/pith/YPOOHLKM5UOBHDPLUV7ONCO3QQ.json","view_paper":"https://pith.science/paper/YPOOHLKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12195&json=true","fetch_graph":"https://pith.science/api/pith-number/YPOOHLKM5UOBHDPLUV7ONCO3QQ/graph.json","fetch_events":"https://pith.science/api/pith-number/YPOOHLKM5UOBHDPLUV7ONCO3QQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPOOHLKM5UOBHDPLUV7ONCO3QQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPOOHLKM5UOBHDPLUV7ONCO3QQ/action/storage_attestation","attest_author":"https://pith.science/pith/YPOOHLKM5UOBHDPLUV7ONCO3QQ/action/author_attestation","sign_citation":"https://pith.science/pith/YPOOHLKM5UOBHDPLUV7ONCO3QQ/action/citation_signature","submit_replication":"https://pith.science/pith/YPOOHLKM5UOBHDPLUV7ONCO3QQ/action/replication_record"}},"created_at":"2026-06-11T01:10:53.565331+00:00","updated_at":"2026-06-11T01:10:53.565331+00:00"}