{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OLCX4ZUOUXF5UZALP7NTX54A3J","short_pith_number":"pith:OLCX4ZUO","schema_version":"1.0","canonical_sha256":"72c57e668ea5cbda640b7fdb3bf780da58509e2de34bfbc0afd2ca3de4eb6c2b","source":{"kind":"arxiv","id":"2601.13836","version":2},"attestation_state":"computed","paper":{"title":"FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.CL","authors_text":"Changsong Li, Jinlan Fu, Min Zhang, Qian Chen, See-kiong Ng, Xipeng Qiu","submitted_at":"2026-01-20T10:47:20Z","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"},"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":"2601.13836","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-20T10:47:20Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"1e35bbf3da8e41cf6cfe1a8540da5825d742abf3b359fead8e513cad5271a9d2","abstract_canon_sha256":"563df2a59738068db602871f1d1cdf006744657ed7d507aefe1134f9277770b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:19.380135Z","signature_b64":"2kx34Iz2Y5kaQh44uFTAhd83ThmAKCbhyTnyoNjdWU0qbQmlqUpVwAd4Cn775PwmneEZW5gYXh3OiNlr5vd8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72c57e668ea5cbda640b7fdb3bf780da58509e2de34bfbc0afd2ca3de4eb6c2b","last_reissued_at":"2026-06-19T16:11:19.379710Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:19.379710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.CL","authors_text":"Changsong Li, Jinlan Fu, Min Zhang, Qian Chen, See-kiong Ng, Xipeng Qiu","submitted_at":"2026-01-20T10:47:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.13836","kind":"arxiv","version":2},"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/2601.13836/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":"2601.13836","created_at":"2026-06-19T16:11:19.379768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.13836v2","created_at":"2026-06-19T16:11:19.379768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.13836","created_at":"2026-06-19T16:11:19.379768+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLCX4ZUOUXF5","created_at":"2026-06-19T16:11:19.379768+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLCX4ZUOUXF5UZAL","created_at":"2026-06-19T16:11:19.379768+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLCX4ZUO","created_at":"2026-06-19T16:11:19.379768+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2604.27393","citing_title":"MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07593","citing_title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLCX4ZUOUXF5UZALP7NTX54A3J","json":"https://pith.science/pith/OLCX4ZUOUXF5UZALP7NTX54A3J.json","graph_json":"https://pith.science/api/pith-number/OLCX4ZUOUXF5UZALP7NTX54A3J/graph.json","events_json":"https://pith.science/api/pith-number/OLCX4ZUOUXF5UZALP7NTX54A3J/events.json","paper":"https://pith.science/paper/OLCX4ZUO"},"agent_actions":{"view_html":"https://pith.science/pith/OLCX4ZUOUXF5UZALP7NTX54A3J","download_json":"https://pith.science/pith/OLCX4ZUOUXF5UZALP7NTX54A3J.json","view_paper":"https://pith.science/paper/OLCX4ZUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.13836&json=true","fetch_graph":"https://pith.science/api/pith-number/OLCX4ZUOUXF5UZALP7NTX54A3J/graph.json","fetch_events":"https://pith.science/api/pith-number/OLCX4ZUOUXF5UZALP7NTX54A3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLCX4ZUOUXF5UZALP7NTX54A3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLCX4ZUOUXF5UZALP7NTX54A3J/action/storage_attestation","attest_author":"https://pith.science/pith/OLCX4ZUOUXF5UZALP7NTX54A3J/action/author_attestation","sign_citation":"https://pith.science/pith/OLCX4ZUOUXF5UZALP7NTX54A3J/action/citation_signature","submit_replication":"https://pith.science/pith/OLCX4ZUOUXF5UZALP7NTX54A3J/action/replication_record"}},"created_at":"2026-06-19T16:11:19.379768+00:00","updated_at":"2026-06-19T16:11:19.379768+00:00"}