{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ISWKVKJOCGIY7FXKVA7UG7IRSY","short_pith_number":"pith:ISWKVKJO","canonical_record":{"source":{"id":"2505.18855","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T20:09:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"56daebbddbe7270990873bb3b1fc8b5ddb8b88debdd1843711962ee0d01c7365","abstract_canon_sha256":"f5d6d13f85bee82c8cc46889268a28cd06ab348228cedb14ae8e50282e971860"},"schema_version":"1.0"},"canonical_sha256":"44acaaa92e11918f96eaa83f437d1196228c6fb87ca691f27408ba5d7537c900","source":{"kind":"arxiv","id":"2505.18855","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18855","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18855v1","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18855","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"pith_short_12","alias_value":"ISWKVKJOCGIY","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"pith_short_16","alias_value":"ISWKVKJOCGIY7FXK","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"pith_short_8","alias_value":"ISWKVKJO","created_at":"2026-07-05T11:09:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ISWKVKJOCGIY7FXKVA7UG7IRSY","target":"record","payload":{"canonical_record":{"source":{"id":"2505.18855","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T20:09:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"56daebbddbe7270990873bb3b1fc8b5ddb8b88debdd1843711962ee0d01c7365","abstract_canon_sha256":"f5d6d13f85bee82c8cc46889268a28cd06ab348228cedb14ae8e50282e971860"},"schema_version":"1.0"},"canonical_sha256":"44acaaa92e11918f96eaa83f437d1196228c6fb87ca691f27408ba5d7537c900","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:20.651594Z","signature_b64":"37275OLNxgf2IdTqHp9SIZGi/JUB8w5mLQMGl6G5S1IRB3PN1VhZqoKSWWak6YcXehjKwyGqPmIft3uUawhjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44acaaa92e11918f96eaa83f437d1196228c6fb87ca691f27408ba5d7537c900","last_reissued_at":"2026-07-05T11:09:20.651060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:20.651060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.18855","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":"2026-07-05T11:09:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1yunaEyK3F1/HmKIAsDPrZE6bre/lDqXWi/kxKe+oePpumOgmxtkMm5+sRo/heYGoXPG2XeOoWtS0Yfu4gagDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:42:24.078144Z"},"content_sha256":"7d72067dc4de9869ad804d91045fe762478e8ba26150550596090c8fe443427d","schema_version":"1.0","event_id":"sha256:7d72067dc4de9869ad804d91045fe762478e8ba26150550596090c8fe443427d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ISWKVKJOCGIY7FXKVA7UG7IRSY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inference Compute-Optimal Video Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fujun Liu, Hanchao Yu, Lifu Huang, Peiqi Wang, Qifan Wang, ShengYun Peng, Xuewen Zhang, Yibo Yang","submitted_at":"2025-05-24T20:09:04Z","abstract_excerpt":"This work investigates the optimal allocation of inference compute across three key scaling factors in video vision language models: language model size, frame count, and the number of visual tokens per frame. While prior works typically focuses on optimizing model efficiency or improving performance without considering resource constraints, we instead identify optimal model configuration under fixed inference compute budgets. We conduct large-scale training sweeps and careful parametric modeling of task performance to identify the inference compute-optimal frontier. Our experiments reveal how"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18855","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/2505.18855/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":"2026-07-05T11:09:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jMeoP8USSHUyqVB8ZOIVTRCXrfyq8Uho/uMxJjTKgZ480FgISvFSCoyOKYySxzGd9FM4dnLaZQWP3oIHjtSZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:42:24.079020Z"},"content_sha256":"b1f63e15f8f1cc6e3bf9f8ae48f1d500adc92aa9fef06422d920b7c22b465e5e","schema_version":"1.0","event_id":"sha256:b1f63e15f8f1cc6e3bf9f8ae48f1d500adc92aa9fef06422d920b7c22b465e5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ISWKVKJOCGIY7FXKVA7UG7IRSY/bundle.json","state_url":"https://pith.science/pith/ISWKVKJOCGIY7FXKVA7UG7IRSY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ISWKVKJOCGIY7FXKVA7UG7IRSY/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":"2026-08-08T20:42:24Z","links":{"resolver":"https://pith.science/pith/ISWKVKJOCGIY7FXKVA7UG7IRSY","bundle":"https://pith.science/pith/ISWKVKJOCGIY7FXKVA7UG7IRSY/bundle.json","state":"https://pith.science/pith/ISWKVKJOCGIY7FXKVA7UG7IRSY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ISWKVKJOCGIY7FXKVA7UG7IRSY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ISWKVKJOCGIY7FXKVA7UG7IRSY","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":"f5d6d13f85bee82c8cc46889268a28cd06ab348228cedb14ae8e50282e971860","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T20:09:04Z","title_canon_sha256":"56daebbddbe7270990873bb3b1fc8b5ddb8b88debdd1843711962ee0d01c7365"},"schema_version":"1.0","source":{"id":"2505.18855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18855","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18855v1","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18855","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"pith_short_12","alias_value":"ISWKVKJOCGIY","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"pith_short_16","alias_value":"ISWKVKJOCGIY7FXK","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"pith_short_8","alias_value":"ISWKVKJO","created_at":"2026-07-05T11:09:20Z"}],"graph_snapshots":[{"event_id":"sha256:b1f63e15f8f1cc6e3bf9f8ae48f1d500adc92aa9fef06422d920b7c22b465e5e","target":"graph","created_at":"2026-07-05T11:09:20Z","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/2505.18855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work investigates the optimal allocation of inference compute across three key scaling factors in video vision language models: language model size, frame count, and the number of visual tokens per frame. While prior works typically focuses on optimizing model efficiency or improving performance without considering resource constraints, we instead identify optimal model configuration under fixed inference compute budgets. We conduct large-scale training sweeps and careful parametric modeling of task performance to identify the inference compute-optimal frontier. Our experiments reveal how","authors_text":"Fujun Liu, Hanchao Yu, Lifu Huang, Peiqi Wang, Qifan Wang, ShengYun Peng, Xuewen Zhang, Yibo Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T20:09:04Z","title":"Inference Compute-Optimal Video Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18855","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":"sha256:7d72067dc4de9869ad804d91045fe762478e8ba26150550596090c8fe443427d","target":"record","created_at":"2026-07-05T11:09:20Z","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":"f5d6d13f85bee82c8cc46889268a28cd06ab348228cedb14ae8e50282e971860","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T20:09:04Z","title_canon_sha256":"56daebbddbe7270990873bb3b1fc8b5ddb8b88debdd1843711962ee0d01c7365"},"schema_version":"1.0","source":{"id":"2505.18855","kind":"arxiv","version":1}},"canonical_sha256":"44acaaa92e11918f96eaa83f437d1196228c6fb87ca691f27408ba5d7537c900","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44acaaa92e11918f96eaa83f437d1196228c6fb87ca691f27408ba5d7537c900","first_computed_at":"2026-07-05T11:09:20.651060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:20.651060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"37275OLNxgf2IdTqHp9SIZGi/JUB8w5mLQMGl6G5S1IRB3PN1VhZqoKSWWak6YcXehjKwyGqPmIft3uUawhjDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:20.651594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d72067dc4de9869ad804d91045fe762478e8ba26150550596090c8fe443427d","sha256:b1f63e15f8f1cc6e3bf9f8ae48f1d500adc92aa9fef06422d920b7c22b465e5e"],"state_sha256":"c3a34456d72e4b7d6aa9e9b541e92fc7045c07d8c98669943c62726ef85ae480"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EPI2/mHe9XmatPTpApZ8jVkj+AnAT4VDrv+v8hKu98hKWr3ieIkcgtqRjYUIm1DlRTr4BQQKBQfmedUie4kADw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:42:24.083190Z","bundle_sha256":"76977fa6cc73642d3ec5e1139f2a0d995f5220f6d8012ddf61d9ff5d012e648e"}}