{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZSGOEO5L5ZIY5GALJI5Q3KTZB7","short_pith_number":"pith:ZSGOEO5L","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"},"canonical_sha256":"cc8ce23babee518e980b4a3b0daa790fc58cb121af6e755612a0dc69a728234a","source":{"kind":"arxiv","id":"2503.15807","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15807","created_at":"2026-07-05T10:35:59Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15807v1","created_at":"2026-07-05T10:35:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15807","created_at":"2026-07-05T10:35:59Z"},{"alias_kind":"pith_short_12","alias_value":"ZSGOEO5L5ZIY","created_at":"2026-07-05T10:35:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZSGOEO5L5ZIY5GAL","created_at":"2026-07-05T10:35:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZSGOEO5L","created_at":"2026-07-05T10:35:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZSGOEO5L5ZIY5GALJI5Q3KTZB7","target":"record","payload":{"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"},"canonical_sha256":"cc8ce23babee518e980b4a3b0daa790fc58cb121af6e755612a0dc69a728234a","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"},"source_kind":"arxiv","source_id":"2503.15807","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":"2026-07-05T10:35:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2rt4vxDR5mAOVyHyNApDwa1O8qqVJBnsFDw4oc8qi1yltFvR5TpqhzUOPNEKVKJQwLlsRaUAnGFEy7oYx8yDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:15:11.117463Z"},"content_sha256":"6cc0c9e180c1184375a32bd865d29faff0fffeaf632e9538b4bbaa64e98dc9ab","schema_version":"1.0","event_id":"sha256:6cc0c9e180c1184375a32bd865d29faff0fffeaf632e9538b4bbaa64e98dc9ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZSGOEO5L5ZIY5GALJI5Q3KTZB7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:35:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0g5nNrJeq3375LdGwSLwMclyWWyWDxLFmFRgHLU2PEGAi17ZRezqxEyntJSTQknVfVi8AcVNmWrbds53eq72DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:15:11.118009Z"},"content_sha256":"fa29c3628ae1af34b06b56e3cf7d2b2b1b299b6140b5e86121269a7141a966bb","schema_version":"1.0","event_id":"sha256:fa29c3628ae1af34b06b56e3cf7d2b2b1b299b6140b5e86121269a7141a966bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/bundle.json","state_url":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/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":"2026-08-09T04:15:11Z","links":{"resolver":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7","bundle":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/bundle.json","state":"https://pith.science/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZSGOEO5L5ZIY5GALJI5Q3KTZB7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZSGOEO5L5ZIY5GALJI5Q3KTZB7","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":"e8146bfc41655e11ee85d3c5ca4cb081b7ff685552ae11f9bf6c0ce48f49ef3a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-20T02:50:57Z","title_canon_sha256":"95b66706b658e93570099690ec50fa2e4cb3138af7ed2705a192b3eacc6c5963"},"schema_version":"1.0","source":{"id":"2503.15807","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15807","created_at":"2026-07-05T10:35:59Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15807v1","created_at":"2026-07-05T10:35:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15807","created_at":"2026-07-05T10:35:59Z"},{"alias_kind":"pith_short_12","alias_value":"ZSGOEO5L5ZIY","created_at":"2026-07-05T10:35:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZSGOEO5L5ZIY5GAL","created_at":"2026-07-05T10:35:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZSGOEO5L","created_at":"2026-07-05T10:35:59Z"}],"graph_snapshots":[{"event_id":"sha256:fa29c3628ae1af34b06b56e3cf7d2b2b1b299b6140b5e86121269a7141a966bb","target":"graph","created_at":"2026-07-05T10:35:59Z","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/2503.15807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cheng Li, Jiexiong Liu, Yanqin Jia, Yixuan Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-20T02:50:57Z","title":"Video-VoT-R1: An efficient video inference model integrating image packing and AoE architecture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15807","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":"sha256:6cc0c9e180c1184375a32bd865d29faff0fffeaf632e9538b4bbaa64e98dc9ab","target":"record","created_at":"2026-07-05T10:35:59Z","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":"e8146bfc41655e11ee85d3c5ca4cb081b7ff685552ae11f9bf6c0ce48f49ef3a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-20T02:50:57Z","title_canon_sha256":"95b66706b658e93570099690ec50fa2e4cb3138af7ed2705a192b3eacc6c5963"},"schema_version":"1.0","source":{"id":"2503.15807","kind":"arxiv","version":1}},"canonical_sha256":"cc8ce23babee518e980b4a3b0daa790fc58cb121af6e755612a0dc69a728234a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc8ce23babee518e980b4a3b0daa790fc58cb121af6e755612a0dc69a728234a","first_computed_at":"2026-07-05T10:35:59.206887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:59.206887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OpCCK2dHXEc5oofqT14HBZgyRpKLeNYblgHo/uJqbcGdduoAm4+p3lvRj4B9q5mKPI6WNTGBDRb0A9KELTW6DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:59.207431Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15807","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cc0c9e180c1184375a32bd865d29faff0fffeaf632e9538b4bbaa64e98dc9ab","sha256:fa29c3628ae1af34b06b56e3cf7d2b2b1b299b6140b5e86121269a7141a966bb"],"state_sha256":"b55204f02e7086ccda471b7bbe01e71ab4fc277b23de156ec51d3e92bc1dcb9a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"duIvJQ2ClZK/OAl2ZdUrZ4a41hNQ1lcZ1nWNrJS5m/UuVrL+kuTgtbjOuKhNugm19apki1+Mgo9SnenEpyE/Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:15:11.122677Z","bundle_sha256":"7d064fdb9da8d5de4f7501707394687dd16aebe237f6c122aa23bfa85d64559e"}}