{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZSGOEO5L5ZIY5GALJI5Q3KTZB7","short_pith_number":"pith:ZSGOEO5L","schema_version":"1.0","canonical_sha256":"cc8ce23babee518e980b4a3b0daa790fc58cb121af6e755612a0dc69a728234a","source":{"kind":"arxiv","id":"2503.15807","version":1},"attestation_state":"computed","paper":{"title":"Video-VoT-R1: An efficient video inference model integrating image packing and AoE architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng Li, Jiexiong Liu, Yanqin Jia, Yixuan Chen","submitted_at":"2025-03-20T02:50:57Z","abstract_excerpt":"In the field of video-language pretraining, existing models face numerous challenges in terms of inference efficiency and multimodal data processing. This paper proposes a KunLunBaize-VoT-R1 video inference model based on a long-sequence image encoder, along with its training and application methods. By integrating image packing technology, the Autonomy-of-Experts (AoE) architecture, and combining the video of Thought (VoT), a large language model (LLM) trained with large-scale reinforcement learning, and multiple training techniques, the efficiency and accuracy of the model in video inference"},"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":"2503.15807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-20T02:50:57Z","cross_cats_sorted":[],"title_canon_sha256":"95b66706b658e93570099690ec50fa2e4cb3138af7ed2705a192b3eacc6c5963","abstract_canon_sha256":"e8146bfc41655e11ee85d3c5ca4cb081b7ff685552ae11f9bf6c0ce48f49ef3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:59.207431Z","signature_b64":"OpCCK2dHXEc5oofqT14HBZgyRpKLeNYblgHo/uJqbcGdduoAm4+p3lvRj4B9q5mKPI6WNTGBDRb0A9KELTW6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc8ce23babee518e980b4a3b0daa790fc58cb121af6e755612a0dc69a728234a","last_reissued_at":"2026-07-05T10:35:59.206887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:59.206887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-VoT-R1: An efficient video inference model integrating image packing and AoE architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng Li, Jiexiong Liu, Yanqin Jia, Yixuan Chen","submitted_at":"2025-03-20T02:50:57Z","abstract_excerpt":"In the field of video-language pretraining, existing models face numerous challenges in terms of inference efficiency and multimodal data processing. This paper proposes a KunLunBaize-VoT-R1 video inference model based on a long-sequence image encoder, along with its training and application methods. By integrating image packing technology, the Autonomy-of-Experts (AoE) architecture, and combining the video of Thought (VoT), a large language model (LLM) trained with large-scale reinforcement learning, and multiple training techniques, the efficiency and accuracy of the model in video inference"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15807","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/2503.15807/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":"2503.15807","created_at":"2026-07-05T10:35:59.206953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15807v1","created_at":"2026-07-05T10:35:59.206953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15807","created_at":"2026-07-05T10:35:59.206953+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSGOEO5L5ZIY","created_at":"2026-07-05T10:35:59.206953+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSGOEO5L5ZIY5GAL","created_at":"2026-07-05T10:35:59.206953+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSGOEO5L","created_at":"2026-07-05T10:35:59.206953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01300","citing_title":"ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7","json":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7.json","graph_json":"https://pith.science/api/pith-number/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/graph.json","events_json":"https://pith.science/api/pith-number/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/events.json","paper":"https://pith.science/paper/ZSGOEO5L"},"agent_actions":{"view_html":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7","download_json":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7.json","view_paper":"https://pith.science/paper/ZSGOEO5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15807&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/action/storage_attestation","attest_author":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/action/author_attestation","sign_citation":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/action/citation_signature","submit_replication":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/action/replication_record"}},"created_at":"2026-07-05T10:35:59.206953+00:00","updated_at":"2026-07-05T10:35:59.206953+00:00"}