{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OLCX4ZUOUXF5UZALP7NTX54A3J","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":"563df2a59738068db602871f1d1cdf006744657ed7d507aefe1134f9277770b6","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-20T10:47:20Z","title_canon_sha256":"1e35bbf3da8e41cf6cfe1a8540da5825d742abf3b359fead8e513cad5271a9d2"},"schema_version":"1.0","source":{"id":"2601.13836","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.13836","created_at":"2026-06-19T16:11:19Z"},{"alias_kind":"arxiv_version","alias_value":"2601.13836v2","created_at":"2026-06-19T16:11:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.13836","created_at":"2026-06-19T16:11:19Z"},{"alias_kind":"pith_short_12","alias_value":"OLCX4ZUOUXF5","created_at":"2026-06-19T16:11:19Z"},{"alias_kind":"pith_short_16","alias_value":"OLCX4ZUOUXF5UZAL","created_at":"2026-06-19T16:11:19Z"},{"alias_kind":"pith_short_8","alias_value":"OLCX4ZUO","created_at":"2026-06-19T16:11:19Z"}],"graph_snapshots":[{"event_id":"sha256:532f8d94645d515ee525aeec3b8abb123317c1e788b1a2f2af8120761388180b","target":"graph","created_at":"2026-06-19T16:11:19Z","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/2601.13836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although Multimodal Large Language Models (MLLMs) demonstrate strong omni-modal perception, their ability to forecast future events from audio-visual cues remains largely unexplored, as existing benchmarks focus mainly on retrospective understanding. To bridge this gap, we introduce FutureOmni, the first benchmark designed to evaluate omni-modal future forecasting from audio-visual environments. The evaluated models are required to perform cross-modal causal and temporal reasoning, as well as effectively leverage internal knowledge to predict future events. FutureOmni is constructed via a scal","authors_text":"Changsong Li, Jinlan Fu, Min Zhang, Qian Chen, See-kiong Ng, Xipeng Qiu","cross_cats":["cs.CV","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-20T10:47:20Z","title":"FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.13836","kind":"arxiv","version":2},"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:bc5e206c757ac69d84f2cf10dd3e1eb3b961dffcf1cfd3b953c1fe7747353494","target":"record","created_at":"2026-06-19T16:11:19Z","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":"563df2a59738068db602871f1d1cdf006744657ed7d507aefe1134f9277770b6","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-20T10:47:20Z","title_canon_sha256":"1e35bbf3da8e41cf6cfe1a8540da5825d742abf3b359fead8e513cad5271a9d2"},"schema_version":"1.0","source":{"id":"2601.13836","kind":"arxiv","version":2}},"canonical_sha256":"72c57e668ea5cbda640b7fdb3bf780da58509e2de34bfbc0afd2ca3de4eb6c2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72c57e668ea5cbda640b7fdb3bf780da58509e2de34bfbc0afd2ca3de4eb6c2b","first_computed_at":"2026-06-19T16:11:19.379710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:19.379710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2kx34Iz2Y5kaQh44uFTAhd83ThmAKCbhyTnyoNjdWU0qbQmlqUpVwAd4Cn775PwmneEZW5gYXh3OiNlr5vd8Bg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:19.380135Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.13836","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc5e206c757ac69d84f2cf10dd3e1eb3b961dffcf1cfd3b953c1fe7747353494","sha256:532f8d94645d515ee525aeec3b8abb123317c1e788b1a2f2af8120761388180b"],"state_sha256":"7c1b1357d7db62c3b136dfea9fbcff75ce434e5677c6b26248b6cb8a2af5b766"}