{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YPOOHLKM5UOBHDPLUV7ONCO3QQ","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":"4db938d3af646c73f049a521d549c748f93fdda6c52ac0080935482c19cb943a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T15:17:08Z","title_canon_sha256":"6b391a27ad640ab67c586ab3c145f3722b9fad180d7e458b40a91701109b53e9"},"schema_version":"1.0","source":{"id":"2606.12195","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12195","created_at":"2026-06-11T01:10:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12195v1","created_at":"2026-06-11T01:10:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12195","created_at":"2026-06-11T01:10:53Z"},{"alias_kind":"pith_short_12","alias_value":"YPOOHLKM5UOB","created_at":"2026-06-11T01:10:53Z"},{"alias_kind":"pith_short_16","alias_value":"YPOOHLKM5UOBHDPL","created_at":"2026-06-11T01:10:53Z"},{"alias_kind":"pith_short_8","alias_value":"YPOOHLKM","created_at":"2026-06-11T01:10:53Z"}],"graph_snapshots":[{"event_id":"sha256:a164839f1ceb458929e75590fa98aba4fe2c701c54b8741d47a717854d8bc45a","target":"graph","created_at":"2026-06-11T01:10:53Z","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/2606.12195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T15:17:08Z","title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12195","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:d6f10e1f0dae7df55bf21401f809fe0b60088a631c09cdddce7011daf4310641","target":"record","created_at":"2026-06-11T01:10:53Z","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":"4db938d3af646c73f049a521d549c748f93fdda6c52ac0080935482c19cb943a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T15:17:08Z","title_canon_sha256":"6b391a27ad640ab67c586ab3c145f3722b9fad180d7e458b40a91701109b53e9"},"schema_version":"1.0","source":{"id":"2606.12195","kind":"arxiv","version":1}},"canonical_sha256":"c3dce3ad4ced1c138deba57ee689db8431d64e0656ac0ddb522ea044039efeca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3dce3ad4ced1c138deba57ee689db8431d64e0656ac0ddb522ea044039efeca","first_computed_at":"2026-06-11T01:10:53.565178Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:53.565178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zn+Fs/Sm03DL1/hjNe+cZ1B+b+s3VVnI0VtkkfYZqPM3cFZ+QU1xXT4vsv8Zx5XzLCt80VUDA/o1jOSoRLBnAw==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:53.566020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12195","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6f10e1f0dae7df55bf21401f809fe0b60088a631c09cdddce7011daf4310641","sha256:a164839f1ceb458929e75590fa98aba4fe2c701c54b8741d47a717854d8bc45a"],"state_sha256":"4eab1d6fc404d303e240b0d7403b3791552cbb31ad30bc7433a42fa9a80952a8"}