{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZRT7EDYYA7BYSVZFWCR66SP4HD","short_pith_number":"pith:ZRT7EDYY","canonical_record":{"source":{"id":"2505.22457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T15:13:34Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"81922a94d428806e6c3ac6f57652edfb0f6897e4178729ebe8bfc7fe68d0656f","abstract_canon_sha256":"92c23620c8bfec962c3fdaf42e0a734deb4141d9151f4afb1df0bf2e97695cb9"},"schema_version":"1.0"},"canonical_sha256":"cc67f20f1807c3895725b0a3ef49fc38de20e1b3d195fd43ea0c75c9674daa59","source":{"kind":"arxiv","id":"2505.22457","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22457","created_at":"2026-07-05T11:11:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22457v1","created_at":"2026-07-05T11:11:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22457","created_at":"2026-07-05T11:11:24Z"},{"alias_kind":"pith_short_12","alias_value":"ZRT7EDYYA7BY","created_at":"2026-07-05T11:11:24Z"},{"alias_kind":"pith_short_16","alias_value":"ZRT7EDYYA7BYSVZF","created_at":"2026-07-05T11:11:24Z"},{"alias_kind":"pith_short_8","alias_value":"ZRT7EDYY","created_at":"2026-07-05T11:11:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZRT7EDYYA7BYSVZFWCR66SP4HD","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T15:13:34Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"81922a94d428806e6c3ac6f57652edfb0f6897e4178729ebe8bfc7fe68d0656f","abstract_canon_sha256":"92c23620c8bfec962c3fdaf42e0a734deb4141d9151f4afb1df0bf2e97695cb9"},"schema_version":"1.0"},"canonical_sha256":"cc67f20f1807c3895725b0a3ef49fc38de20e1b3d195fd43ea0c75c9674daa59","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:24.422733Z","signature_b64":"2mQZIxPoljbA3tSY7jgAndDtxvFaa42zbwFQ66+nXrK7EdSk2mYLny4hvH0W2Pcmr3kVPwMmK2gn04fGiO15DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc67f20f1807c3895725b0a3ef49fc38de20e1b3d195fd43ea0c75c9674daa59","last_reissued_at":"2026-07-05T11:11:24.422217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:24.422217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22457","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fma7AGlbVlqR+E83I/weRW9iswNbhLY+OqOn9qa0ZzN2Xs8H1QT/zKY1a0Um64F0Bbjn8eUvtUtlL0bNvvHfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:31:08.657462Z"},"content_sha256":"384158c6faff6685f8df91f11e8e47e756f5b9d96f2c37bce571d1da8540ab94","schema_version":"1.0","event_id":"sha256:384158c6faff6685f8df91f11e8e47e756f5b9d96f2c37bce571d1da8540ab94"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZRT7EDYYA7BYSVZFWCR66SP4HD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fostering Video Reasoning via Next-Event Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chao Du, Haonan Wang, Hongfu Liu, Kenji Kawaguchi, Tianyu Pang, Xiangyan Liu, Ye Wang","submitted_at":"2025-05-28T15:13:34Z","abstract_excerpt":"Next-token prediction serves as the foundational learning task enabling reasoning in LLMs. But what should the learning task be when aiming to equip MLLMs with temporal reasoning capabilities over video inputs? Existing tasks such as video question answering often rely on annotations from humans or much stronger MLLMs, while video captioning tends to entangle temporal reasoning with spatial information. To address this gap, we propose next-event prediction (NEP), a learning task that harnesses future video segments as a rich, self-supervised signal to foster temporal reasoning. We segment each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22457","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/2505.22457/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"US0POvls7WYg8Zn67mfwIQB2iGVkLRbjiJXHzhofIoXESiSU1hf1z3Kbr2/VZjALhx32QZDX13qUFUn6MdN7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:31:08.661016Z"},"content_sha256":"075f3af45f27ad9c41ed50036689491aad1bc27223c5796d456456e93d137bb8","schema_version":"1.0","event_id":"sha256:075f3af45f27ad9c41ed50036689491aad1bc27223c5796d456456e93d137bb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZRT7EDYYA7BYSVZFWCR66SP4HD/bundle.json","state_url":"https://pith.science/pith/ZRT7EDYYA7BYSVZFWCR66SP4HD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZRT7EDYYA7BYSVZFWCR66SP4HD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T19:31:08Z","links":{"resolver":"https://pith.science/pith/ZRT7EDYYA7BYSVZFWCR66SP4HD","bundle":"https://pith.science/pith/ZRT7EDYYA7BYSVZFWCR66SP4HD/bundle.json","state":"https://pith.science/pith/ZRT7EDYYA7BYSVZFWCR66SP4HD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZRT7EDYYA7BYSVZFWCR66SP4HD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZRT7EDYYA7BYSVZFWCR66SP4HD","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":"92c23620c8bfec962c3fdaf42e0a734deb4141d9151f4afb1df0bf2e97695cb9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T15:13:34Z","title_canon_sha256":"81922a94d428806e6c3ac6f57652edfb0f6897e4178729ebe8bfc7fe68d0656f"},"schema_version":"1.0","source":{"id":"2505.22457","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22457","created_at":"2026-07-05T11:11:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22457v1","created_at":"2026-07-05T11:11:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22457","created_at":"2026-07-05T11:11:24Z"},{"alias_kind":"pith_short_12","alias_value":"ZRT7EDYYA7BY","created_at":"2026-07-05T11:11:24Z"},{"alias_kind":"pith_short_16","alias_value":"ZRT7EDYYA7BYSVZF","created_at":"2026-07-05T11:11:24Z"},{"alias_kind":"pith_short_8","alias_value":"ZRT7EDYY","created_at":"2026-07-05T11:11:24Z"}],"graph_snapshots":[{"event_id":"sha256:075f3af45f27ad9c41ed50036689491aad1bc27223c5796d456456e93d137bb8","target":"graph","created_at":"2026-07-05T11:11:24Z","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/2505.22457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Next-token prediction serves as the foundational learning task enabling reasoning in LLMs. But what should the learning task be when aiming to equip MLLMs with temporal reasoning capabilities over video inputs? Existing tasks such as video question answering often rely on annotations from humans or much stronger MLLMs, while video captioning tends to entangle temporal reasoning with spatial information. To address this gap, we propose next-event prediction (NEP), a learning task that harnesses future video segments as a rich, self-supervised signal to foster temporal reasoning. We segment each","authors_text":"Chao Du, Haonan Wang, Hongfu Liu, Kenji Kawaguchi, Tianyu Pang, Xiangyan Liu, Ye Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T15:13:34Z","title":"Fostering Video Reasoning via Next-Event Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22457","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":"sha256:384158c6faff6685f8df91f11e8e47e756f5b9d96f2c37bce571d1da8540ab94","target":"record","created_at":"2026-07-05T11:11:24Z","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":"92c23620c8bfec962c3fdaf42e0a734deb4141d9151f4afb1df0bf2e97695cb9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T15:13:34Z","title_canon_sha256":"81922a94d428806e6c3ac6f57652edfb0f6897e4178729ebe8bfc7fe68d0656f"},"schema_version":"1.0","source":{"id":"2505.22457","kind":"arxiv","version":1}},"canonical_sha256":"cc67f20f1807c3895725b0a3ef49fc38de20e1b3d195fd43ea0c75c9674daa59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc67f20f1807c3895725b0a3ef49fc38de20e1b3d195fd43ea0c75c9674daa59","first_computed_at":"2026-07-05T11:11:24.422217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:24.422217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2mQZIxPoljbA3tSY7jgAndDtxvFaa42zbwFQ66+nXrK7EdSk2mYLny4hvH0W2Pcmr3kVPwMmK2gn04fGiO15DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:24.422733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22457","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:384158c6faff6685f8df91f11e8e47e756f5b9d96f2c37bce571d1da8540ab94","sha256:075f3af45f27ad9c41ed50036689491aad1bc27223c5796d456456e93d137bb8"],"state_sha256":"7fb567efd7c772fd63b506c71634712c3a47ebf82cd0e4a10776ade10dec1ecb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TEAAoA/tOEIBkxAZZNbXz1KqE0iKzPbznLShpbv4XFKCbthKmaU/u1P1SuYFD8iAKrVVvNNpiCMq/4fq6drNCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:31:08.669719Z","bundle_sha256":"20af58226d7693b2367576e36ebef10c49d104418a88c6900e63d2262d857c7a"}}