{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CXAUIZ3OD7NUTXMHMPUYNSF37H","short_pith_number":"pith:CXAUIZ3O","schema_version":"1.0","canonical_sha256":"15c144676e1fdb49dd8763e986c8bbf9eac07ecae10f21fd8e9041ede5dd325f","source":{"kind":"arxiv","id":"2606.05769","version":1},"attestation_state":"computed","paper":{"title":"Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Yang, Linquan Wu, Sheng Xia, Songze Li, Tianxiang Jiang, Yi Wang, Yu Qiao, Ziang Yan","submitted_at":"2026-06-04T06:53:19Z","abstract_excerpt":"Video event prediction (VEP) requires models to infer unobserved future states from partial video evidence. Existing video MLLMs usually verbalize intermediate future reasoning in text space: once visual evidence is verbalized, fine-grained motion, geometry, and interaction cues can be lost, leading to plausible but visually ungrounded hallucinations. We introduce Future-L1, an interleaved latent visual reasoning framework that lets an MLLM alternate between language tokens and continuous latent visual spans during autoregressive decoding. To train this capability, we construct Future-L1-50K b"},"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":"2606.05769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T06:53:19Z","cross_cats_sorted":[],"title_canon_sha256":"4165b7e12cead5c81bdcdae1eb8020e1690805e884536e30a8403ff622a76c9f","abstract_canon_sha256":"50cd0eba1129abbbcca2cc72433cf9e8b64969cc4d63fa9511044f0528b56729"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:02.541248Z","signature_b64":"f/wjUk7Y/JwBgRa6VHCUMqVcm0/6WEaVv3N0UbrhyvP05QLKotuQLHyUrm0MceBOXMuUZFH2iyftnyyBaDaDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15c144676e1fdb49dd8763e986c8bbf9eac07ecae10f21fd8e9041ede5dd325f","last_reissued_at":"2026-06-05T01:15:02.540655Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:02.540655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Yang, Linquan Wu, Sheng Xia, Songze Li, Tianxiang Jiang, Yi Wang, Yu Qiao, Ziang Yan","submitted_at":"2026-06-04T06:53:19Z","abstract_excerpt":"Video event prediction (VEP) requires models to infer unobserved future states from partial video evidence. Existing video MLLMs usually verbalize intermediate future reasoning in text space: once visual evidence is verbalized, fine-grained motion, geometry, and interaction cues can be lost, leading to plausible but visually ungrounded hallucinations. We introduce Future-L1, an interleaved latent visual reasoning framework that lets an MLLM alternate between language tokens and continuous latent visual spans during autoregressive decoding. To train this capability, we construct Future-L1-50K b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05769","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/2606.05769/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":"2606.05769","created_at":"2026-06-05T01:15:02.540743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05769v1","created_at":"2026-06-05T01:15:02.540743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05769","created_at":"2026-06-05T01:15:02.540743+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXAUIZ3OD7NU","created_at":"2026-06-05T01:15:02.540743+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXAUIZ3OD7NUTXMH","created_at":"2026-06-05T01:15:02.540743+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXAUIZ3O","created_at":"2026-06-05T01:15:02.540743+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/CXAUIZ3OD7NUTXMHMPUYNSF37H","json":"https://pith.science/pith/CXAUIZ3OD7NUTXMHMPUYNSF37H.json","graph_json":"https://pith.science/api/pith-number/CXAUIZ3OD7NUTXMHMPUYNSF37H/graph.json","events_json":"https://pith.science/api/pith-number/CXAUIZ3OD7NUTXMHMPUYNSF37H/events.json","paper":"https://pith.science/paper/CXAUIZ3O"},"agent_actions":{"view_html":"https://pith.science/pith/CXAUIZ3OD7NUTXMHMPUYNSF37H","download_json":"https://pith.science/pith/CXAUIZ3OD7NUTXMHMPUYNSF37H.json","view_paper":"https://pith.science/paper/CXAUIZ3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05769&json=true","fetch_graph":"https://pith.science/api/pith-number/CXAUIZ3OD7NUTXMHMPUYNSF37H/graph.json","fetch_events":"https://pith.science/api/pith-number/CXAUIZ3OD7NUTXMHMPUYNSF37H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXAUIZ3OD7NUTXMHMPUYNSF37H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXAUIZ3OD7NUTXMHMPUYNSF37H/action/storage_attestation","attest_author":"https://pith.science/pith/CXAUIZ3OD7NUTXMHMPUYNSF37H/action/author_attestation","sign_citation":"https://pith.science/pith/CXAUIZ3OD7NUTXMHMPUYNSF37H/action/citation_signature","submit_replication":"https://pith.science/pith/CXAUIZ3OD7NUTXMHMPUYNSF37H/action/replication_record"}},"created_at":"2026-06-05T01:15:02.540743+00:00","updated_at":"2026-06-05T01:15:02.540743+00:00"}