{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5J7WG3XZSONCLGJ7X2VSXBXXI7","short_pith_number":"pith:5J7WG3XZ","canonical_record":{"source":{"id":"2503.07002","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T07:32:53Z","cross_cats_sorted":[],"title_canon_sha256":"9ff2e9c13290686b040166091c5e70f6b547999cd39481bf7b987c4437f8bd86","abstract_canon_sha256":"129f2d26b4183eaf27b5f6260b7510966b1044af7224935656caddb4291e4091"},"schema_version":"1.0"},"canonical_sha256":"ea7f636ef9939a25993fbeab2b86f747c0d41c7dfd31e3fd9ad32b03f2b124f2","source":{"kind":"arxiv","id":"2503.07002","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07002","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07002v1","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07002","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"pith_short_12","alias_value":"5J7WG3XZSONC","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"pith_short_16","alias_value":"5J7WG3XZSONCLGJ7","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"pith_short_8","alias_value":"5J7WG3XZ","created_at":"2026-07-05T10:27:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5J7WG3XZSONCLGJ7X2VSXBXXI7","target":"record","payload":{"canonical_record":{"source":{"id":"2503.07002","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T07:32:53Z","cross_cats_sorted":[],"title_canon_sha256":"9ff2e9c13290686b040166091c5e70f6b547999cd39481bf7b987c4437f8bd86","abstract_canon_sha256":"129f2d26b4183eaf27b5f6260b7510966b1044af7224935656caddb4291e4091"},"schema_version":"1.0"},"canonical_sha256":"ea7f636ef9939a25993fbeab2b86f747c0d41c7dfd31e3fd9ad32b03f2b124f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:47.628449Z","signature_b64":"ocqtW3xb4Ov9OctL6R1jmA27esuznwlP89gYNtTKYappx4TKfkEsDnEyNHZgC1OTsoE7MWv2cCl1cVgyvcCYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea7f636ef9939a25993fbeab2b86f747c0d41c7dfd31e3fd9ad32b03f2b124f2","last_reissued_at":"2026-07-05T10:27:47.627528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:47.627528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.07002","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":"2026-07-05T10:27:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wHc9bbVIof0MPDhUcdP0KqjqEH+pX97/icThdWKPwR7aU9gn51m/XP8/6HaPburYw9JQuKbukRBOd/5zIEToDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:21:53.715742Z"},"content_sha256":"15b7afc4e8587d5daa8cb97c8a000641335358eb865bbf29663e463b7625f721","schema_version":"1.0","event_id":"sha256:15b7afc4e8587d5daa8cb97c8a000641335358eb865bbf29663e463b7625f721"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5J7WG3XZSONCLGJ7X2VSXBXXI7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"B\\\"orje F. Karlsson, Jiazheng Liu, Sipeng Zheng, Zongqing Lu","submitted_at":"2025-03-10T07:32:53Z","abstract_excerpt":"Multimodal large language models (MLLMs), built on large-scale pre-trained vision towers and language models, have shown great capabilities in multimodal understanding. However, most existing MLLMs are trained on single-turn vision question-answering tasks, which do not accurately reflect real-world human conversations. In this paper, we introduce MMDiag, a multi-turn multimodal dialogue dataset. This dataset is collaboratively generated through deliberately designed rules and GPT assistance, featuring strong correlations between questions, between questions and images, and among different ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07002","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/2503.07002/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":"2026-07-05T10:27:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ew4BIiIVHcIgpWO7XWbeGC6Z65Z6pSjW+HjtCVyzjSZYR+DxC62uniPbqqnX8B5HyoUIVWBfqa9FjNMTX88Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:21:53.716333Z"},"content_sha256":"b9943067f411320f568ee32104d67aa03810c50cf191a94b3a3b65ecbb41dc1e","schema_version":"1.0","event_id":"sha256:b9943067f411320f568ee32104d67aa03810c50cf191a94b3a3b65ecbb41dc1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5J7WG3XZSONCLGJ7X2VSXBXXI7/bundle.json","state_url":"https://pith.science/pith/5J7WG3XZSONCLGJ7X2VSXBXXI7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5J7WG3XZSONCLGJ7X2VSXBXXI7/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":"2026-08-14T19:21:53Z","links":{"resolver":"https://pith.science/pith/5J7WG3XZSONCLGJ7X2VSXBXXI7","bundle":"https://pith.science/pith/5J7WG3XZSONCLGJ7X2VSXBXXI7/bundle.json","state":"https://pith.science/pith/5J7WG3XZSONCLGJ7X2VSXBXXI7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5J7WG3XZSONCLGJ7X2VSXBXXI7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5J7WG3XZSONCLGJ7X2VSXBXXI7","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":"129f2d26b4183eaf27b5f6260b7510966b1044af7224935656caddb4291e4091","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T07:32:53Z","title_canon_sha256":"9ff2e9c13290686b040166091c5e70f6b547999cd39481bf7b987c4437f8bd86"},"schema_version":"1.0","source":{"id":"2503.07002","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07002","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07002v1","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07002","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"pith_short_12","alias_value":"5J7WG3XZSONC","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"pith_short_16","alias_value":"5J7WG3XZSONCLGJ7","created_at":"2026-07-05T10:27:47Z"},{"alias_kind":"pith_short_8","alias_value":"5J7WG3XZ","created_at":"2026-07-05T10:27:47Z"}],"graph_snapshots":[{"event_id":"sha256:b9943067f411320f568ee32104d67aa03810c50cf191a94b3a3b65ecbb41dc1e","target":"graph","created_at":"2026-07-05T10:27:47Z","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/2503.07002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs), built on large-scale pre-trained vision towers and language models, have shown great capabilities in multimodal understanding. However, most existing MLLMs are trained on single-turn vision question-answering tasks, which do not accurately reflect real-world human conversations. In this paper, we introduce MMDiag, a multi-turn multimodal dialogue dataset. This dataset is collaboratively generated through deliberately designed rules and GPT assistance, featuring strong correlations between questions, between questions and images, and among different ima","authors_text":"B\\\"orje F. Karlsson, Jiazheng Liu, Sipeng Zheng, Zongqing Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T07:32:53Z","title":"Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07002","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":"sha256:15b7afc4e8587d5daa8cb97c8a000641335358eb865bbf29663e463b7625f721","target":"record","created_at":"2026-07-05T10:27:47Z","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":"129f2d26b4183eaf27b5f6260b7510966b1044af7224935656caddb4291e4091","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T07:32:53Z","title_canon_sha256":"9ff2e9c13290686b040166091c5e70f6b547999cd39481bf7b987c4437f8bd86"},"schema_version":"1.0","source":{"id":"2503.07002","kind":"arxiv","version":1}},"canonical_sha256":"ea7f636ef9939a25993fbeab2b86f747c0d41c7dfd31e3fd9ad32b03f2b124f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea7f636ef9939a25993fbeab2b86f747c0d41c7dfd31e3fd9ad32b03f2b124f2","first_computed_at":"2026-07-05T10:27:47.627528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:47.627528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ocqtW3xb4Ov9OctL6R1jmA27esuznwlP89gYNtTKYappx4TKfkEsDnEyNHZgC1OTsoE7MWv2cCl1cVgyvcCYBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:47.628449Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.07002","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15b7afc4e8587d5daa8cb97c8a000641335358eb865bbf29663e463b7625f721","sha256:b9943067f411320f568ee32104d67aa03810c50cf191a94b3a3b65ecbb41dc1e"],"state_sha256":"e772fd3a771076de7e54073f6b43cb1ac5f62f610268cfa1c6e6b5f1331750f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bZSvY6t1xc1qpvae224djtKi/5Zpw6AAD9pD1spccHfqTpJUfdlYVNp9KyKAD89jUzNOeJJb3RvoylGsP5flDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:21:53.723145Z","bundle_sha256":"ce608086bf2ce48de1042483ac952fb09b8726ff6f35106b82e425b5db42c8a3"}}