{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4XH2TP3KGXXK2K6DYUQ2I5YHW2","short_pith_number":"pith:4XH2TP3K","canonical_record":{"source":{"id":"2309.07387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T02:09:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"45c67ab33ab91e1e9a89dfb7bb8cb3b9445a4defdc029fa03155f9b41a1a20f3","abstract_canon_sha256":"b3700c27d2fd4f37e1ecc92c085a97259424e0325a7752a9902a564d642720a2"},"schema_version":"1.0"},"canonical_sha256":"e5cfa9bf6a35eead2bc3c521a47707b691b64a0aae11d3e7f0ff41b38cd6969b","source":{"kind":"arxiv","id":"2309.07387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07387","created_at":"2026-07-05T06:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07387v1","created_at":"2026-07-05T06:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07387","created_at":"2026-07-05T06:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"4XH2TP3KGXXK","created_at":"2026-07-05T06:50:34Z"},{"alias_kind":"pith_short_16","alias_value":"4XH2TP3KGXXK2K6D","created_at":"2026-07-05T06:50:34Z"},{"alias_kind":"pith_short_8","alias_value":"4XH2TP3K","created_at":"2026-07-05T06:50:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4XH2TP3KGXXK2K6DYUQ2I5YHW2","target":"record","payload":{"canonical_record":{"source":{"id":"2309.07387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T02:09:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"45c67ab33ab91e1e9a89dfb7bb8cb3b9445a4defdc029fa03155f9b41a1a20f3","abstract_canon_sha256":"b3700c27d2fd4f37e1ecc92c085a97259424e0325a7752a9902a564d642720a2"},"schema_version":"1.0"},"canonical_sha256":"e5cfa9bf6a35eead2bc3c521a47707b691b64a0aae11d3e7f0ff41b38cd6969b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:34.789487Z","signature_b64":"jJQ3E795Z1DrCyzhmv+kXpfdWgbAbGTUJtW0cSQJBTn9Qr5MCMpV0oNNvPMc5Dzb/lNWRTJ8qZzFbRNf6dqsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5cfa9bf6a35eead2bc3c521a47707b691b64a0aae11d3e7f0ff41b38cd6969b","last_reissued_at":"2026-07-05T06:50:34.788988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:34.788988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.07387","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":"2026-07-05T06:50:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VgW1N4isXqVXfj1ULhXv0n/i55hKZGfRpO63zWGd9H0EnKV/Jhq1foCXAD2aPkIUY3MFHD0AgwnJ4A/Jxi7GDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T05:46:31.987988Z"},"content_sha256":"8fe19386e6d4f1d60d7f90f9105e6346d8dd7ee7471c34f3bcf63810142425bb","schema_version":"1.0","event_id":"sha256:8fe19386e6d4f1d60d7f90f9105e6346d8dd7ee7471c34f3bcf63810142425bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4XH2TP3KGXXK2K6DYUQ2I5YHW2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VDialogUE: A Unified Evaluation Benchmark for Visually-grounded Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Binyuan Hui, Fei Huang, Min Yang, Run Luo, Wanwei He, Yongbin Li, Yunshui Li, Yuxing Long, Zhaochao Yin","submitted_at":"2023-09-14T02:09:20Z","abstract_excerpt":"Visually-grounded dialog systems, which integrate multiple modes of communication such as text and visual inputs, have become an increasingly popular area of investigation. However, the absence of a standardized evaluation framework poses a challenge in assessing the development of this field. To this end, we propose \\textbf{VDialogUE}, a \\textbf{V}isually-grounded \\textbf{Dialog}ue benchmark for \\textbf{U}nified \\textbf{E}valuation. It defines five core multi-modal dialogue tasks and covers six datasets. Furthermore, in order to provide a comprehensive assessment of the model's performance ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07387","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/2309.07387/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":"2026-07-05T06:50:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pj5TiUH/QsrQnyVDlvkJhv2fuf7AfAZEybj7RGTroyjseNOgpbzS30NXa9clYXWv/E48GUy9Ede11nxN1pIhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T05:46:31.988387Z"},"content_sha256":"ef15df4132c19416ab1dec12d30c651b33dd649bc7b9b6a1296a3bc5e0d4a56f","schema_version":"1.0","event_id":"sha256:ef15df4132c19416ab1dec12d30c651b33dd649bc7b9b6a1296a3bc5e0d4a56f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4XH2TP3KGXXK2K6DYUQ2I5YHW2/bundle.json","state_url":"https://pith.science/pith/4XH2TP3KGXXK2K6DYUQ2I5YHW2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4XH2TP3KGXXK2K6DYUQ2I5YHW2/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":"2026-07-08T05:46:31Z","links":{"resolver":"https://pith.science/pith/4XH2TP3KGXXK2K6DYUQ2I5YHW2","bundle":"https://pith.science/pith/4XH2TP3KGXXK2K6DYUQ2I5YHW2/bundle.json","state":"https://pith.science/pith/4XH2TP3KGXXK2K6DYUQ2I5YHW2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4XH2TP3KGXXK2K6DYUQ2I5YHW2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4XH2TP3KGXXK2K6DYUQ2I5YHW2","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":"b3700c27d2fd4f37e1ecc92c085a97259424e0325a7752a9902a564d642720a2","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T02:09:20Z","title_canon_sha256":"45c67ab33ab91e1e9a89dfb7bb8cb3b9445a4defdc029fa03155f9b41a1a20f3"},"schema_version":"1.0","source":{"id":"2309.07387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07387","created_at":"2026-07-05T06:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07387v1","created_at":"2026-07-05T06:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07387","created_at":"2026-07-05T06:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"4XH2TP3KGXXK","created_at":"2026-07-05T06:50:34Z"},{"alias_kind":"pith_short_16","alias_value":"4XH2TP3KGXXK2K6D","created_at":"2026-07-05T06:50:34Z"},{"alias_kind":"pith_short_8","alias_value":"4XH2TP3K","created_at":"2026-07-05T06:50:34Z"}],"graph_snapshots":[{"event_id":"sha256:ef15df4132c19416ab1dec12d30c651b33dd649bc7b9b6a1296a3bc5e0d4a56f","target":"graph","created_at":"2026-07-05T06:50:34Z","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/2309.07387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visually-grounded dialog systems, which integrate multiple modes of communication such as text and visual inputs, have become an increasingly popular area of investigation. However, the absence of a standardized evaluation framework poses a challenge in assessing the development of this field. To this end, we propose \\textbf{VDialogUE}, a \\textbf{V}isually-grounded \\textbf{Dialog}ue benchmark for \\textbf{U}nified \\textbf{E}valuation. It defines five core multi-modal dialogue tasks and covers six datasets. Furthermore, in order to provide a comprehensive assessment of the model's performance ac","authors_text":"Binyuan Hui, Fei Huang, Min Yang, Run Luo, Wanwei He, Yongbin Li, Yunshui Li, Yuxing Long, Zhaochao Yin","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T02:09:20Z","title":"VDialogUE: A Unified Evaluation Benchmark for Visually-grounded Dialogue"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07387","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":"sha256:8fe19386e6d4f1d60d7f90f9105e6346d8dd7ee7471c34f3bcf63810142425bb","target":"record","created_at":"2026-07-05T06:50:34Z","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":"b3700c27d2fd4f37e1ecc92c085a97259424e0325a7752a9902a564d642720a2","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T02:09:20Z","title_canon_sha256":"45c67ab33ab91e1e9a89dfb7bb8cb3b9445a4defdc029fa03155f9b41a1a20f3"},"schema_version":"1.0","source":{"id":"2309.07387","kind":"arxiv","version":1}},"canonical_sha256":"e5cfa9bf6a35eead2bc3c521a47707b691b64a0aae11d3e7f0ff41b38cd6969b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5cfa9bf6a35eead2bc3c521a47707b691b64a0aae11d3e7f0ff41b38cd6969b","first_computed_at":"2026-07-05T06:50:34.788988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:34.788988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jJQ3E795Z1DrCyzhmv+kXpfdWgbAbGTUJtW0cSQJBTn9Qr5MCMpV0oNNvPMc5Dzb/lNWRTJ8qZzFbRNf6dqsCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:34.789487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.07387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fe19386e6d4f1d60d7f90f9105e6346d8dd7ee7471c34f3bcf63810142425bb","sha256:ef15df4132c19416ab1dec12d30c651b33dd649bc7b9b6a1296a3bc5e0d4a56f"],"state_sha256":"3b5a135c043d41fc033ae9718eb7b9343bd1cef89a453f0153c1fe1e677b23bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3268H/VWsDXsMXc0N0XNjqMZo0MFGa5eUt1lpTNHQ7RqJLgVNalXYCgkcP1Pgs+CC5aLDHnr/S3uDSoTDOYpDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T05:46:31.990601Z","bundle_sha256":"59a74da6f61ccc642d51baffda73208e43011a2bbeb8fdd805de27e84d6081d8"}}