{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZM2JPHV7IMIPLFKOUJMUDHDLJD","short_pith_number":"pith:ZM2JPHV7","canonical_record":{"source":{"id":"2504.15415","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T19:53:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"89b1a0137d0a92c2d8d2da6d0d4bca0777a578e461167d849efd32996a579d2c","abstract_canon_sha256":"97e7c9feab25e092297b6804500ce71cb32743568924532715153297649f8fea"},"schema_version":"1.0"},"canonical_sha256":"cb34979ebf4310f5954ea259419c6b48c624a9fafdc235d5dd5636d10e828076","source":{"kind":"arxiv","id":"2504.15415","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15415","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15415v1","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15415","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"ZM2JPHV7IMIP","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"pith_short_16","alias_value":"ZM2JPHV7IMIPLFKO","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"pith_short_8","alias_value":"ZM2JPHV7","created_at":"2026-07-05T10:52:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZM2JPHV7IMIPLFKOUJMUDHDLJD","target":"record","payload":{"canonical_record":{"source":{"id":"2504.15415","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T19:53:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"89b1a0137d0a92c2d8d2da6d0d4bca0777a578e461167d849efd32996a579d2c","abstract_canon_sha256":"97e7c9feab25e092297b6804500ce71cb32743568924532715153297649f8fea"},"schema_version":"1.0"},"canonical_sha256":"cb34979ebf4310f5954ea259419c6b48c624a9fafdc235d5dd5636d10e828076","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:24.143726Z","signature_b64":"tHTPvP8b97auTbZB84FeN7V34TYzSzkfAAGCdCbtlQrue2NU4+SbVytrzhIBJFatiLmia5q+l6O2L+aIYB1eBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb34979ebf4310f5954ea259419c6b48c624a9fafdc235d5dd5636d10e828076","last_reissued_at":"2026-07-05T10:52:24.143217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:24.143217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.15415","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":"2026-07-05T10:52:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CUvW+N2p2phg94EsUdDGpJM7RG+PPiQLYbw+aEftYhmJLCY11EuwgxJjs8iE5ooG/Uwne0344GzbtRM9NenxCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:14:16.400807Z"},"content_sha256":"66e44bfcb5595300502a58c8af5c769c1a35abf457246977e1656b28c07e7617","schema_version":"1.0","event_id":"sha256:66e44bfcb5595300502a58c8af5c769c1a35abf457246977e1656b28c07e7617"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZM2JPHV7IMIPLFKOUJMUDHDLJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Boyu Feng, David Ma, Ge Zhang, Jarvis Guo, Jiaheng Liu, Jincheng Ren, Jun Ma, King Zhu, Meng Cao, Shiwen Ni, Wenhao Huang, Xiao Gu, Xiaojie Jin, Yancheng He, Yifan Yao, Yuanxing Zhang, Zhenlin Wei, Zhenzhu Yang, Zhongyuan Peng, Zhoufutu Wen","submitted_at":"2025-04-21T19:53:44Z","abstract_excerpt":"Existing evaluation frameworks for Multimodal Large Language Models (MLLMs) primarily focus on image reasoning or general video understanding tasks, largely overlooking the significant role of image context in video comprehension. To bridge this gap, we propose IV-Bench, the first comprehensive benchmark for evaluating Image-Grounded Video Perception and Reasoning. IV-Bench consists of 967 videos paired with 2,585 meticulously annotated image-text queries across 13 tasks (7 perception and 6 reasoning tasks) and 5 representative categories. Extensive evaluations of state-of-the-art open-source "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15415","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/2504.15415/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":"2026-07-05T10:52:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8naYz9G/QGwHAGgj+/P1c6Vu7pAKF/lnq0qhtPvzytD2o3tncRZSIRTCxIPC3HhWZ03gEm9k6Yr2aAUuwUq8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:14:16.401390Z"},"content_sha256":"54193af4c7cac41c623330bb75517708e354ad5751f69558bbe145a47d6ebfbe","schema_version":"1.0","event_id":"sha256:54193af4c7cac41c623330bb75517708e354ad5751f69558bbe145a47d6ebfbe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZM2JPHV7IMIPLFKOUJMUDHDLJD/bundle.json","state_url":"https://pith.science/pith/ZM2JPHV7IMIPLFKOUJMUDHDLJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZM2JPHV7IMIPLFKOUJMUDHDLJD/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":"2026-08-05T20:14:16Z","links":{"resolver":"https://pith.science/pith/ZM2JPHV7IMIPLFKOUJMUDHDLJD","bundle":"https://pith.science/pith/ZM2JPHV7IMIPLFKOUJMUDHDLJD/bundle.json","state":"https://pith.science/pith/ZM2JPHV7IMIPLFKOUJMUDHDLJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZM2JPHV7IMIPLFKOUJMUDHDLJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZM2JPHV7IMIPLFKOUJMUDHDLJD","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":"97e7c9feab25e092297b6804500ce71cb32743568924532715153297649f8fea","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T19:53:44Z","title_canon_sha256":"89b1a0137d0a92c2d8d2da6d0d4bca0777a578e461167d849efd32996a579d2c"},"schema_version":"1.0","source":{"id":"2504.15415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15415","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15415v1","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15415","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"ZM2JPHV7IMIP","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"pith_short_16","alias_value":"ZM2JPHV7IMIPLFKO","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"pith_short_8","alias_value":"ZM2JPHV7","created_at":"2026-07-05T10:52:24Z"}],"graph_snapshots":[{"event_id":"sha256:54193af4c7cac41c623330bb75517708e354ad5751f69558bbe145a47d6ebfbe","target":"graph","created_at":"2026-07-05T10:52:24Z","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/2504.15415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing evaluation frameworks for Multimodal Large Language Models (MLLMs) primarily focus on image reasoning or general video understanding tasks, largely overlooking the significant role of image context in video comprehension. To bridge this gap, we propose IV-Bench, the first comprehensive benchmark for evaluating Image-Grounded Video Perception and Reasoning. IV-Bench consists of 967 videos paired with 2,585 meticulously annotated image-text queries across 13 tasks (7 perception and 6 reasoning tasks) and 5 representative categories. Extensive evaluations of state-of-the-art open-source ","authors_text":"Boyu Feng, David Ma, Ge Zhang, Jarvis Guo, Jiaheng Liu, Jincheng Ren, Jun Ma, King Zhu, Meng Cao, Shiwen Ni, Wenhao Huang, Xiao Gu, Xiaojie Jin, Yancheng He, Yifan Yao, Yuanxing Zhang, Zhenlin Wei, Zhenzhu Yang, Zhongyuan Peng, Zhoufutu Wen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T19:53:44Z","title":"IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15415","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":"sha256:66e44bfcb5595300502a58c8af5c769c1a35abf457246977e1656b28c07e7617","target":"record","created_at":"2026-07-05T10:52:24Z","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":"97e7c9feab25e092297b6804500ce71cb32743568924532715153297649f8fea","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T19:53:44Z","title_canon_sha256":"89b1a0137d0a92c2d8d2da6d0d4bca0777a578e461167d849efd32996a579d2c"},"schema_version":"1.0","source":{"id":"2504.15415","kind":"arxiv","version":1}},"canonical_sha256":"cb34979ebf4310f5954ea259419c6b48c624a9fafdc235d5dd5636d10e828076","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb34979ebf4310f5954ea259419c6b48c624a9fafdc235d5dd5636d10e828076","first_computed_at":"2026-07-05T10:52:24.143217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:24.143217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tHTPvP8b97auTbZB84FeN7V34TYzSzkfAAGCdCbtlQrue2NU4+SbVytrzhIBJFatiLmia5q+l6O2L+aIYB1eBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:24.143726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66e44bfcb5595300502a58c8af5c769c1a35abf457246977e1656b28c07e7617","sha256:54193af4c7cac41c623330bb75517708e354ad5751f69558bbe145a47d6ebfbe"],"state_sha256":"a353303e5ab6bb6a89d4befd5ee085775e080406c028108a65cc60ce5bb4b1f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u4RuF5q8UdbyjhUAcHHSdbmX9f/46VYRFEjXbGMvfkweVUmbIAZ+i+IBdgvCH/6N/5UQ3A8q5yrRadW8jvsOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:14:16.406486Z","bundle_sha256":"9b0ae28d308cbebd782e396a3e7573db557cb2bbb7a22c6e53d27824601826a0"}}