{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:U3K76FVNN3IIR4OJG7KJQTWXIU","short_pith_number":"pith:U3K76FVN","canonical_record":{"source":{"id":"1908.04289","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-10T05:57:01Z","cross_cats_sorted":["cs.SD","eess.AS","eess.IV"],"title_canon_sha256":"890b10a56c9b53ab592ceec8145c00a6552517e88fcbd8553519e928f10ed858","abstract_canon_sha256":"7c84eed118ee5933584b821a1b79423c5ca54663232dcea71ebd4a6c8fd85bc2"},"schema_version":"1.0"},"canonical_sha256":"a6d5ff16ad6ed088f1c937d4984ed74539d3001c8f604929e82ad62868e2be79","source":{"kind":"arxiv","id":"1908.04289","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04289","created_at":"2026-07-04T23:54:29Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04289v1","created_at":"2026-07-04T23:54:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04289","created_at":"2026-07-04T23:54:29Z"},{"alias_kind":"pith_short_12","alias_value":"U3K76FVNN3II","created_at":"2026-07-04T23:54:29Z"},{"alias_kind":"pith_short_16","alias_value":"U3K76FVNN3IIR4OJ","created_at":"2026-07-04T23:54:29Z"},{"alias_kind":"pith_short_8","alias_value":"U3K76FVN","created_at":"2026-07-04T23:54:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:U3K76FVNN3IIR4OJG7KJQTWXIU","target":"record","payload":{"canonical_record":{"source":{"id":"1908.04289","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-10T05:57:01Z","cross_cats_sorted":["cs.SD","eess.AS","eess.IV"],"title_canon_sha256":"890b10a56c9b53ab592ceec8145c00a6552517e88fcbd8553519e928f10ed858","abstract_canon_sha256":"7c84eed118ee5933584b821a1b79423c5ca54663232dcea71ebd4a6c8fd85bc2"},"schema_version":"1.0"},"canonical_sha256":"a6d5ff16ad6ed088f1c937d4984ed74539d3001c8f604929e82ad62868e2be79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:54:29.157044Z","signature_b64":"wFF8d/tWxWvgk5WbRTY2zplLq2CVPXGW0/X1+N9myYB/33RyyH5wgzMy5a4zUKpKdDuwbuOzoSY2+fzi1tbKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6d5ff16ad6ed088f1c937d4984ed74539d3001c8f604929e82ad62868e2be79","last_reissued_at":"2026-07-04T23:54:29.156625Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:54:29.156625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.04289","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":"2026-07-04T23:54:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OHFUL173abrjRB3e42eApvALSNYT47VEcznrkDxGZHoilW3omxp7WhPp42mRvJA4ZRGUlSmXgm4P1JEFPyxaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:19:24.162642Z"},"content_sha256":"b0a9a9f597383983ab156311370878971dd77f2147bdfc79f138e59437df202f","schema_version":"1.0","event_id":"sha256:b0a9a9f597383983ab156311370878971dd77f2147bdfc79f138e59437df202f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:U3K76FVNN3IIR4OJG7KJQTWXIU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-modality Latent Interaction Network for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","eess.IV"],"primary_cat":"cs.CV","authors_text":"Haoxuan You, Hongsheng Li, Peng Gao, Xiaogang Wang, Zhanpeng Zhang","submitted_at":"2019-08-10T05:57:01Z","abstract_excerpt":"Exploiting relationships between visual regions and question words have achieved great success in learning multi-modality features for Visual Question Answering (VQA). However, we argue that existing methods mostly model relations between individual visual regions and words, which are not enough to correctly answer the question. From humans' perspective, answering a visual question requires understanding the summarizations of visual and language information. In this paper, we proposed the Multi-modality Latent Interaction module (MLI) to tackle this problem. The proposed module learns the cros"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04289","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/1908.04289/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":"2026-07-04T23:54:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kbr8sdyZCxMPedKkJklnH14zr3Tz0V4rXdTpQ+lJDDesMuRg8axUlN5QP82Nb4yw8O61GHMeU8HV5tnqryEAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:19:24.163170Z"},"content_sha256":"5ec0e1f218695ef3f960b6fc8f1026ab3311b519d0c33c7dc8eccc67ace73fcc","schema_version":"1.0","event_id":"sha256:5ec0e1f218695ef3f960b6fc8f1026ab3311b519d0c33c7dc8eccc67ace73fcc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U3K76FVNN3IIR4OJG7KJQTWXIU/bundle.json","state_url":"https://pith.science/pith/U3K76FVNN3IIR4OJG7KJQTWXIU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U3K76FVNN3IIR4OJG7KJQTWXIU/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":"2026-08-15T23:19:24Z","links":{"resolver":"https://pith.science/pith/U3K76FVNN3IIR4OJG7KJQTWXIU","bundle":"https://pith.science/pith/U3K76FVNN3IIR4OJG7KJQTWXIU/bundle.json","state":"https://pith.science/pith/U3K76FVNN3IIR4OJG7KJQTWXIU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U3K76FVNN3IIR4OJG7KJQTWXIU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:U3K76FVNN3IIR4OJG7KJQTWXIU","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":"7c84eed118ee5933584b821a1b79423c5ca54663232dcea71ebd4a6c8fd85bc2","cross_cats_sorted":["cs.SD","eess.AS","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-10T05:57:01Z","title_canon_sha256":"890b10a56c9b53ab592ceec8145c00a6552517e88fcbd8553519e928f10ed858"},"schema_version":"1.0","source":{"id":"1908.04289","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04289","created_at":"2026-07-04T23:54:29Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04289v1","created_at":"2026-07-04T23:54:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04289","created_at":"2026-07-04T23:54:29Z"},{"alias_kind":"pith_short_12","alias_value":"U3K76FVNN3II","created_at":"2026-07-04T23:54:29Z"},{"alias_kind":"pith_short_16","alias_value":"U3K76FVNN3IIR4OJ","created_at":"2026-07-04T23:54:29Z"},{"alias_kind":"pith_short_8","alias_value":"U3K76FVN","created_at":"2026-07-04T23:54:29Z"}],"graph_snapshots":[{"event_id":"sha256:5ec0e1f218695ef3f960b6fc8f1026ab3311b519d0c33c7dc8eccc67ace73fcc","target":"graph","created_at":"2026-07-04T23:54:29Z","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/1908.04289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploiting relationships between visual regions and question words have achieved great success in learning multi-modality features for Visual Question Answering (VQA). However, we argue that existing methods mostly model relations between individual visual regions and words, which are not enough to correctly answer the question. From humans' perspective, answering a visual question requires understanding the summarizations of visual and language information. In this paper, we proposed the Multi-modality Latent Interaction module (MLI) to tackle this problem. The proposed module learns the cros","authors_text":"Haoxuan You, Hongsheng Li, Peng Gao, Xiaogang Wang, Zhanpeng Zhang","cross_cats":["cs.SD","eess.AS","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-10T05:57:01Z","title":"Multi-modality Latent Interaction Network for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04289","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:b0a9a9f597383983ab156311370878971dd77f2147bdfc79f138e59437df202f","target":"record","created_at":"2026-07-04T23:54:29Z","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":"7c84eed118ee5933584b821a1b79423c5ca54663232dcea71ebd4a6c8fd85bc2","cross_cats_sorted":["cs.SD","eess.AS","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-10T05:57:01Z","title_canon_sha256":"890b10a56c9b53ab592ceec8145c00a6552517e88fcbd8553519e928f10ed858"},"schema_version":"1.0","source":{"id":"1908.04289","kind":"arxiv","version":1}},"canonical_sha256":"a6d5ff16ad6ed088f1c937d4984ed74539d3001c8f604929e82ad62868e2be79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6d5ff16ad6ed088f1c937d4984ed74539d3001c8f604929e82ad62868e2be79","first_computed_at":"2026-07-04T23:54:29.156625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:54:29.156625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wFF8d/tWxWvgk5WbRTY2zplLq2CVPXGW0/X1+N9myYB/33RyyH5wgzMy5a4zUKpKdDuwbuOzoSY2+fzi1tbKAw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:54:29.157044Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.04289","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0a9a9f597383983ab156311370878971dd77f2147bdfc79f138e59437df202f","sha256:5ec0e1f218695ef3f960b6fc8f1026ab3311b519d0c33c7dc8eccc67ace73fcc"],"state_sha256":"fa14198aefeb07baa32230466e0399fdc4595e921f03948cc573633de5ff1e38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"meKn2r7foGkK6wuy6nH5n5Gg+f+Kbr4T0HTOYtMFcyPF3f63mwseopsmHz9Zhmx90QSoE3hvu/5o74DDaJmuAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T23:19:24.167615Z","bundle_sha256":"3fae9a02773b155b268b7ff9422879227ded59b77dae39907e8245d41964b4bc"}}