{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UAAIN4SGEBGSRYLQOAJT3KGL7M","short_pith_number":"pith:UAAIN4SG","canonical_record":{"source":{"id":"2606.04588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T08:27:53Z","cross_cats_sorted":[],"title_canon_sha256":"2686906b330fb84d75f6adb3bd0689750d45968fc65d27e7998b277b22d4c2ef","abstract_canon_sha256":"0381e8f065b73b2d1ab9b07d8037e128f949c1f168f6ea4423d1a177c5b2baab"},"schema_version":"1.0"},"canonical_sha256":"a00086f246204d28e17070133da8cbfb10ee8939d424af1c49a4a9798ad84f7b","source":{"kind":"arxiv","id":"2606.04588","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04588","created_at":"2026-06-04T01:09:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04588v1","created_at":"2026-06-04T01:09:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04588","created_at":"2026-06-04T01:09:19Z"},{"alias_kind":"pith_short_12","alias_value":"UAAIN4SGEBGS","created_at":"2026-06-04T01:09:19Z"},{"alias_kind":"pith_short_16","alias_value":"UAAIN4SGEBGSRYLQ","created_at":"2026-06-04T01:09:19Z"},{"alias_kind":"pith_short_8","alias_value":"UAAIN4SG","created_at":"2026-06-04T01:09:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UAAIN4SGEBGSRYLQOAJT3KGL7M","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T08:27:53Z","cross_cats_sorted":[],"title_canon_sha256":"2686906b330fb84d75f6adb3bd0689750d45968fc65d27e7998b277b22d4c2ef","abstract_canon_sha256":"0381e8f065b73b2d1ab9b07d8037e128f949c1f168f6ea4423d1a177c5b2baab"},"schema_version":"1.0"},"canonical_sha256":"a00086f246204d28e17070133da8cbfb10ee8939d424af1c49a4a9798ad84f7b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:19.983437Z","signature_b64":"Ps0NnLiiITu45drJ4TdAJYu7fQWytUfz6ajTfhAYdZSkZb+QZA2rTco11oq2PTpbRms2B0ULA0bNQQ37d8uVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a00086f246204d28e17070133da8cbfb10ee8939d424af1c49a4a9798ad84f7b","last_reissued_at":"2026-06-04T01:09:19.982567Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:19.982567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04588","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":"2026-06-04T01:09:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HifGpU3u2fIiPpb5yaXYvF6IlT01ItlTIGZ0hbhqKrsMoOPpHxH0UsgAU4mSMyRJiMg6L/mG/6vUImpMFDkODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T17:32:14.002056Z"},"content_sha256":"f363fbc9c435737e6ee6f266bd04fdc1bd78a549af6d22a1ff24f46880c9a1e7","schema_version":"1.0","event_id":"sha256:f363fbc9c435737e6ee6f266bd04fdc1bd78a549af6d22a1ff24f46880c9a1e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UAAIN4SGEBGSRYLQOAJT3KGL7M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VCIFBench: Evaluating Complex Instruction Following for Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huangchen Xu, Yi Chang, Yuan Wu","submitted_at":"2026-06-03T08:27:53Z","abstract_excerpt":"Multimodal large language models have made rapid progress in video understanding, yet existing benchmarks largely rely on simple prompts and provide limited evidence about whether models can satisfy explicit output constraints. We introduce VCIFBench, a benchmark for evaluating complex instruction following in video understanding. VCIFBench constructs constraint-rich instructions from both benchmark-adapted and directly video-grounded prompts, covering content, format, style, and structure requirements, and evaluates model outputs with a hybrid verification pipeline. The benchmark contains 306"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04588","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/2606.04588/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":"2026-06-04T01:09:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9A399kAJIdlaGf8ZeEW9gfaST7C/lIoo7Nnr0v3QKi309rmqxfl6I7y9rLIk67tWIsoAyRmkkrl+b2aKSdepDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T17:32:14.002436Z"},"content_sha256":"af2be1eec7341e1614277f68b19a2f54a45830fb3431ee23703a6f28f4139422","schema_version":"1.0","event_id":"sha256:af2be1eec7341e1614277f68b19a2f54a45830fb3431ee23703a6f28f4139422"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UAAIN4SGEBGSRYLQOAJT3KGL7M/bundle.json","state_url":"https://pith.science/pith/UAAIN4SGEBGSRYLQOAJT3KGL7M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UAAIN4SGEBGSRYLQOAJT3KGL7M/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":"2026-06-28T17:32:14Z","links":{"resolver":"https://pith.science/pith/UAAIN4SGEBGSRYLQOAJT3KGL7M","bundle":"https://pith.science/pith/UAAIN4SGEBGSRYLQOAJT3KGL7M/bundle.json","state":"https://pith.science/pith/UAAIN4SGEBGSRYLQOAJT3KGL7M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UAAIN4SGEBGSRYLQOAJT3KGL7M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UAAIN4SGEBGSRYLQOAJT3KGL7M","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":"0381e8f065b73b2d1ab9b07d8037e128f949c1f168f6ea4423d1a177c5b2baab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T08:27:53Z","title_canon_sha256":"2686906b330fb84d75f6adb3bd0689750d45968fc65d27e7998b277b22d4c2ef"},"schema_version":"1.0","source":{"id":"2606.04588","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04588","created_at":"2026-06-04T01:09:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04588v1","created_at":"2026-06-04T01:09:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04588","created_at":"2026-06-04T01:09:19Z"},{"alias_kind":"pith_short_12","alias_value":"UAAIN4SGEBGS","created_at":"2026-06-04T01:09:19Z"},{"alias_kind":"pith_short_16","alias_value":"UAAIN4SGEBGSRYLQ","created_at":"2026-06-04T01:09:19Z"},{"alias_kind":"pith_short_8","alias_value":"UAAIN4SG","created_at":"2026-06-04T01:09:19Z"}],"graph_snapshots":[{"event_id":"sha256:af2be1eec7341e1614277f68b19a2f54a45830fb3431ee23703a6f28f4139422","target":"graph","created_at":"2026-06-04T01:09:19Z","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/2606.04588/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models have made rapid progress in video understanding, yet existing benchmarks largely rely on simple prompts and provide limited evidence about whether models can satisfy explicit output constraints. We introduce VCIFBench, a benchmark for evaluating complex instruction following in video understanding. VCIFBench constructs constraint-rich instructions from both benchmark-adapted and directly video-grounded prompts, covering content, format, style, and structure requirements, and evaluates model outputs with a hybrid verification pipeline. The benchmark contains 306","authors_text":"Huangchen Xu, Yi Chang, Yuan Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T08:27:53Z","title":"VCIFBench: Evaluating Complex Instruction Following for Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04588","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:f363fbc9c435737e6ee6f266bd04fdc1bd78a549af6d22a1ff24f46880c9a1e7","target":"record","created_at":"2026-06-04T01:09:19Z","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":"0381e8f065b73b2d1ab9b07d8037e128f949c1f168f6ea4423d1a177c5b2baab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T08:27:53Z","title_canon_sha256":"2686906b330fb84d75f6adb3bd0689750d45968fc65d27e7998b277b22d4c2ef"},"schema_version":"1.0","source":{"id":"2606.04588","kind":"arxiv","version":1}},"canonical_sha256":"a00086f246204d28e17070133da8cbfb10ee8939d424af1c49a4a9798ad84f7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a00086f246204d28e17070133da8cbfb10ee8939d424af1c49a4a9798ad84f7b","first_computed_at":"2026-06-04T01:09:19.982567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:19.982567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ps0NnLiiITu45drJ4TdAJYu7fQWytUfz6ajTfhAYdZSkZb+QZA2rTco11oq2PTpbRms2B0ULA0bNQQ37d8uVBA==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:19.983437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04588","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f363fbc9c435737e6ee6f266bd04fdc1bd78a549af6d22a1ff24f46880c9a1e7","sha256:af2be1eec7341e1614277f68b19a2f54a45830fb3431ee23703a6f28f4139422"],"state_sha256":"ebbf14c776a4dbd91f12809aa2a4dbdaea6c4915a1702766e491cd5b2242c778"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RpNnGb6QqzWFwdjPDfkpUCSh4zkcP8G2Sr1PMYxLVBIysFS6psJ/SSpUe3NHNkFdPLVMlwc+jJDYwao5QtuJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T17:32:14.004325Z","bundle_sha256":"886e2f5a87b93d841c8b3d9a2585ae8f049854850eb4b16fbaa7cc3d367b6a5d"}}