{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7UNVQEXHUFW3MFROT6Y7DAKLW4","short_pith_number":"pith:7UNVQEXH","canonical_record":{"source":{"id":"2305.00581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-30T21:22:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8acab277dd90ad78fddca690896afcdeeb5f8385767a4817aa1295785f9dc768","abstract_canon_sha256":"ed4c4d65fc330f068849ec8fb99eaef6a8b51910ca4f2c08b8ccd8d6be29a6b7"},"schema_version":"1.0"},"canonical_sha256":"fd1b5812e7a16db6162e9fb1f1814bb737749efba3e66d6a04688f200964ed7f","source":{"kind":"arxiv","id":"2305.00581","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.00581","created_at":"2026-07-05T06:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2305.00581v1","created_at":"2026-07-05T06:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00581","created_at":"2026-07-05T06:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"7UNVQEXHUFW3","created_at":"2026-07-05T06:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"7UNVQEXHUFW3MFRO","created_at":"2026-07-05T06:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"7UNVQEXH","created_at":"2026-07-05T06:05:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7UNVQEXHUFW3MFROT6Y7DAKLW4","target":"record","payload":{"canonical_record":{"source":{"id":"2305.00581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-30T21:22:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8acab277dd90ad78fddca690896afcdeeb5f8385767a4817aa1295785f9dc768","abstract_canon_sha256":"ed4c4d65fc330f068849ec8fb99eaef6a8b51910ca4f2c08b8ccd8d6be29a6b7"},"schema_version":"1.0"},"canonical_sha256":"fd1b5812e7a16db6162e9fb1f1814bb737749efba3e66d6a04688f200964ed7f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:43.041246Z","signature_b64":"bSI4rlND2CluBFAeAMgDK3egie9/btkW4W70JxrQYEJ1Nj1YUhIChnJm6LWfLgEM7uHk+23uwb6pcsVBf2rKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd1b5812e7a16db6162e9fb1f1814bb737749efba3e66d6a04688f200964ed7f","last_reissued_at":"2026-07-05T06:05:43.040846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:43.040846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.00581","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":"2026-07-05T06:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DKNZRQUhcbPi2zXcq/3ecccY+TJiz3u0Xc6b5x60FBX0HMyFO8iwxK4Q+ikd655zb9yc6tE1Hnj/swCaQuGaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:51:52.819627Z"},"content_sha256":"9b3aaa72dc1fba20f6f3f1835d9d25ce0b226b4283577197dcc444f4a2336477","schema_version":"1.0","event_id":"sha256:9b3aaa72dc1fba20f6f3f1835d9d25ce0b226b4283577197dcc444f4a2336477"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7UNVQEXHUFW3MFROT6Y7DAKLW4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Graph Transformer for Multimodal Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Xin Eric Wang, Xuehai He","submitted_at":"2023-04-30T21:22:35Z","abstract_excerpt":"Despite the success of Transformer models in vision and language tasks, they often learn knowledge from enormous data implicitly and cannot utilize structured input data directly. On the other hand, structured learning approaches such as graph neural networks (GNNs) that integrate prior information can barely compete with Transformer models. In this work, we aim to benefit from both worlds and propose a novel Multimodal Graph Transformer for question answering tasks that requires performing reasoning across multiple modalities. We introduce a graph-involved plug-and-play quasi-attention mechan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00581","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/2305.00581/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":"2026-07-05T06:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nj7YBaLuEydL3Jjnef0D73NiUclTRGVTcEz3SKmB12ltGYZG1hlln8NurtI+FMqItdNtqqz5tN8RwxDzJivnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:51:52.820120Z"},"content_sha256":"e79fb8fa07a0b3a7c325e9fd39d1390ff3e672ed9367971d2b349c45130cf9bd","schema_version":"1.0","event_id":"sha256:e79fb8fa07a0b3a7c325e9fd39d1390ff3e672ed9367971d2b349c45130cf9bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7UNVQEXHUFW3MFROT6Y7DAKLW4/bundle.json","state_url":"https://pith.science/pith/7UNVQEXHUFW3MFROT6Y7DAKLW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7UNVQEXHUFW3MFROT6Y7DAKLW4/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":"2026-08-04T21:51:52Z","links":{"resolver":"https://pith.science/pith/7UNVQEXHUFW3MFROT6Y7DAKLW4","bundle":"https://pith.science/pith/7UNVQEXHUFW3MFROT6Y7DAKLW4/bundle.json","state":"https://pith.science/pith/7UNVQEXHUFW3MFROT6Y7DAKLW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7UNVQEXHUFW3MFROT6Y7DAKLW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7UNVQEXHUFW3MFROT6Y7DAKLW4","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":"ed4c4d65fc330f068849ec8fb99eaef6a8b51910ca4f2c08b8ccd8d6be29a6b7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-30T21:22:35Z","title_canon_sha256":"8acab277dd90ad78fddca690896afcdeeb5f8385767a4817aa1295785f9dc768"},"schema_version":"1.0","source":{"id":"2305.00581","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.00581","created_at":"2026-07-05T06:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2305.00581v1","created_at":"2026-07-05T06:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00581","created_at":"2026-07-05T06:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"7UNVQEXHUFW3","created_at":"2026-07-05T06:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"7UNVQEXHUFW3MFRO","created_at":"2026-07-05T06:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"7UNVQEXH","created_at":"2026-07-05T06:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:e79fb8fa07a0b3a7c325e9fd39d1390ff3e672ed9367971d2b349c45130cf9bd","target":"graph","created_at":"2026-07-05T06:05:43Z","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/2305.00581/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the success of Transformer models in vision and language tasks, they often learn knowledge from enormous data implicitly and cannot utilize structured input data directly. On the other hand, structured learning approaches such as graph neural networks (GNNs) that integrate prior information can barely compete with Transformer models. In this work, we aim to benefit from both worlds and propose a novel Multimodal Graph Transformer for question answering tasks that requires performing reasoning across multiple modalities. We introduce a graph-involved plug-and-play quasi-attention mechan","authors_text":"Xin Eric Wang, Xuehai He","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-30T21:22:35Z","title":"Multimodal Graph Transformer for Multimodal Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00581","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":"sha256:9b3aaa72dc1fba20f6f3f1835d9d25ce0b226b4283577197dcc444f4a2336477","target":"record","created_at":"2026-07-05T06:05:43Z","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":"ed4c4d65fc330f068849ec8fb99eaef6a8b51910ca4f2c08b8ccd8d6be29a6b7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-30T21:22:35Z","title_canon_sha256":"8acab277dd90ad78fddca690896afcdeeb5f8385767a4817aa1295785f9dc768"},"schema_version":"1.0","source":{"id":"2305.00581","kind":"arxiv","version":1}},"canonical_sha256":"fd1b5812e7a16db6162e9fb1f1814bb737749efba3e66d6a04688f200964ed7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd1b5812e7a16db6162e9fb1f1814bb737749efba3e66d6a04688f200964ed7f","first_computed_at":"2026-07-05T06:05:43.040846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:43.040846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bSI4rlND2CluBFAeAMgDK3egie9/btkW4W70JxrQYEJ1Nj1YUhIChnJm6LWfLgEM7uHk+23uwb6pcsVBf2rKCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:43.041246Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.00581","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b3aaa72dc1fba20f6f3f1835d9d25ce0b226b4283577197dcc444f4a2336477","sha256:e79fb8fa07a0b3a7c325e9fd39d1390ff3e672ed9367971d2b349c45130cf9bd"],"state_sha256":"ed704cc1faf17cee481dd81f3d4f8ff3befcd2b923383527c52d91abe66e9cfb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DiBZReaooUzm5Fv9NqCQzhKjCBMPAAR9QxHEqKqKUXCoGEF6KYS0LjW+XFp/QfLj5Grb7re082OChonhnG2QCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:51:52.823376Z","bundle_sha256":"3972377f1d74e05a4f79533ade9a86edd4a1d6adf0186a77008155c52a575f69"}}