{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6JRFLHHMNVSMMRAW4WJLIUSFCZ","short_pith_number":"pith:6JRFLHHM","canonical_record":{"source":{"id":"2606.08572","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T11:03:33Z","cross_cats_sorted":[],"title_canon_sha256":"817ccf7b320574580c4f4c125c4341a923a59caa97b65e49fa58c1b4fdc4a772","abstract_canon_sha256":"d4ad41222027fd9dbd2df435b43f8d420d9a7df380c602fd40cea571ea121086"},"schema_version":"1.0"},"canonical_sha256":"f262559cec6d64c64416e592b4524516765320bb700e62faf99a8b088a9d5cb7","source":{"kind":"arxiv","id":"2606.08572","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08572","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08572v1","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08572","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"6JRFLHHMNVSM","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"6JRFLHHMNVSMMRAW","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"6JRFLHHM","created_at":"2026-06-09T01:05:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6JRFLHHMNVSMMRAW4WJLIUSFCZ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.08572","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T11:03:33Z","cross_cats_sorted":[],"title_canon_sha256":"817ccf7b320574580c4f4c125c4341a923a59caa97b65e49fa58c1b4fdc4a772","abstract_canon_sha256":"d4ad41222027fd9dbd2df435b43f8d420d9a7df380c602fd40cea571ea121086"},"schema_version":"1.0"},"canonical_sha256":"f262559cec6d64c64416e592b4524516765320bb700e62faf99a8b088a9d5cb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:40.487365Z","signature_b64":"jB3rSyDGaOZcYNbHfcu9GOsQSoK1cgo8qd2F87MSdazQtd+MaLmO7lUpD89j2Bg3ZolMW+flkyrpCvDAbeqnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f262559cec6d64c64416e592b4524516765320bb700e62faf99a8b088a9d5cb7","last_reissued_at":"2026-06-09T01:05:40.486941Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:40.486941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.08572","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":"2026-06-09T01:05:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zkwC/lGzUmgNV/2eOEf1rWodydpmbJt/HrH1is8Bs+0iAnrHdk3icTDTTxbxHvvmokyEUbJh3hgdr2ThskiXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T23:16:08.108987Z"},"content_sha256":"7561f66f11a9be6c802d8e387268d7537387581db7c57f979636dd4d0cfc4446","schema_version":"1.0","event_id":"sha256:7561f66f11a9be6c802d8e387268d7537387581db7c57f979636dd4d0cfc4446"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6JRFLHHMNVSMMRAW4WJLIUSFCZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An Ping, Han Wang, Hanyan Bian, Haowen Chen, Jiahao Wang, Jiaheng Liu, Jiaqi Wang, Junze Li, Shihao Li, Yanghai Wang, Yichi Ren, Yiyang Hu, Yize Zhang, Yuanxing Zhang, Zhuze Xu, Zijie Zhang","submitted_at":"2026-06-07T11:03:33Z","abstract_excerpt":"While Omni-modal Large Language Models (OLLMs) have demonstrated impressive capabilities in jointly processing audio and visual streams, their ability to strictly adhere to complex, multi-faceted user instructions remains largely unexplored. Existing benchmarks primarily focus on holistic video understanding or text-only instruction following, failing to capture the intricate interplay between modalities and user constraints. To bridge this gap, we introduce OmniCap-IF, the first comprehensive benchmark specifically designed to evaluate instruction-following capabilities in omni-modal captioni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08572","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/2606.08572/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":"2026-06-09T01:05:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C/g+Cn6bUpU0ThreaZzTGrXnZGqCCywonM+3Vdc/9x3RKQNfQ64SMpwlqEO0IfP7d2knfckU1QEsV7AvLHCmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T23:16:08.109382Z"},"content_sha256":"e7422bbff8bc3cd0a0bb0637391b07b230d9e915439681fe20e6f78dcf5d6e45","schema_version":"1.0","event_id":"sha256:e7422bbff8bc3cd0a0bb0637391b07b230d9e915439681fe20e6f78dcf5d6e45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6JRFLHHMNVSMMRAW4WJLIUSFCZ/bundle.json","state_url":"https://pith.science/pith/6JRFLHHMNVSMMRAW4WJLIUSFCZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6JRFLHHMNVSMMRAW4WJLIUSFCZ/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":"2026-06-20T23:16:08Z","links":{"resolver":"https://pith.science/pith/6JRFLHHMNVSMMRAW4WJLIUSFCZ","bundle":"https://pith.science/pith/6JRFLHHMNVSMMRAW4WJLIUSFCZ/bundle.json","state":"https://pith.science/pith/6JRFLHHMNVSMMRAW4WJLIUSFCZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6JRFLHHMNVSMMRAW4WJLIUSFCZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6JRFLHHMNVSMMRAW4WJLIUSFCZ","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":"d4ad41222027fd9dbd2df435b43f8d420d9a7df380c602fd40cea571ea121086","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T11:03:33Z","title_canon_sha256":"817ccf7b320574580c4f4c125c4341a923a59caa97b65e49fa58c1b4fdc4a772"},"schema_version":"1.0","source":{"id":"2606.08572","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08572","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08572v1","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08572","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"6JRFLHHMNVSM","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"6JRFLHHMNVSMMRAW","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"6JRFLHHM","created_at":"2026-06-09T01:05:40Z"}],"graph_snapshots":[{"event_id":"sha256:e7422bbff8bc3cd0a0bb0637391b07b230d9e915439681fe20e6f78dcf5d6e45","target":"graph","created_at":"2026-06-09T01:05:40Z","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/2606.08572/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Omni-modal Large Language Models (OLLMs) have demonstrated impressive capabilities in jointly processing audio and visual streams, their ability to strictly adhere to complex, multi-faceted user instructions remains largely unexplored. Existing benchmarks primarily focus on holistic video understanding or text-only instruction following, failing to capture the intricate interplay between modalities and user constraints. To bridge this gap, we introduce OmniCap-IF, the first comprehensive benchmark specifically designed to evaluate instruction-following capabilities in omni-modal captioni","authors_text":"An Ping, Han Wang, Hanyan Bian, Haowen Chen, Jiahao Wang, Jiaheng Liu, Jiaqi Wang, Junze Li, Shihao Li, Yanghai Wang, Yichi Ren, Yiyang Hu, Yize Zhang, Yuanxing Zhang, Zhuze Xu, Zijie Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T11:03:33Z","title":"OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08572","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":"sha256:7561f66f11a9be6c802d8e387268d7537387581db7c57f979636dd4d0cfc4446","target":"record","created_at":"2026-06-09T01:05:40Z","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":"d4ad41222027fd9dbd2df435b43f8d420d9a7df380c602fd40cea571ea121086","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T11:03:33Z","title_canon_sha256":"817ccf7b320574580c4f4c125c4341a923a59caa97b65e49fa58c1b4fdc4a772"},"schema_version":"1.0","source":{"id":"2606.08572","kind":"arxiv","version":1}},"canonical_sha256":"f262559cec6d64c64416e592b4524516765320bb700e62faf99a8b088a9d5cb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f262559cec6d64c64416e592b4524516765320bb700e62faf99a8b088a9d5cb7","first_computed_at":"2026-06-09T01:05:40.486941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:40.486941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jB3rSyDGaOZcYNbHfcu9GOsQSoK1cgo8qd2F87MSdazQtd+MaLmO7lUpD89j2Bg3ZolMW+flkyrpCvDAbeqnAA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:40.487365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08572","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7561f66f11a9be6c802d8e387268d7537387581db7c57f979636dd4d0cfc4446","sha256:e7422bbff8bc3cd0a0bb0637391b07b230d9e915439681fe20e6f78dcf5d6e45"],"state_sha256":"511bb5b4a4c65b7340a290a19908f6aad7e076f1ff407b7b40af6e8e29d54473"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gxtbrMaxypOZEHHFH99AibEfzsRAxc1Fa1knk3Fn3aInrgvvExedFQQMfu2gzfMb5zjA2zbUdu7JdAX6vpOUBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T23:16:08.111467Z","bundle_sha256":"e3d1f3cda99bccd0795b7ebb688be10cdfabe7e444c9c2af0087f6bb4f1da8ac"}}