{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LBSVOBZXVU7PJDH53JYPTHWFWO","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":"0b32bdf8770c3f6ea5d829861b8e72b498992551040cca1e641b3326ec6d4030","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2022-09-07T13:25:09Z","title_canon_sha256":"c67474b0926d5fd42d6abd5ccfcf4f020aea7c85ec18af86ae28db5602e23a0d"},"schema_version":"1.0","source":{"id":"2209.03126","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.03126","created_at":"2026-07-05T05:18:06Z"},{"alias_kind":"arxiv_version","alias_value":"2209.03126v2","created_at":"2026-07-05T05:18:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.03126","created_at":"2026-07-05T05:18:06Z"},{"alias_kind":"pith_short_12","alias_value":"LBSVOBZXVU7P","created_at":"2026-07-05T05:18:06Z"},{"alias_kind":"pith_short_16","alias_value":"LBSVOBZXVU7PJDH5","created_at":"2026-07-05T05:18:06Z"},{"alias_kind":"pith_short_8","alias_value":"LBSVOBZX","created_at":"2026-07-05T05:18:06Z"}],"graph_snapshots":[{"event_id":"sha256:7b8f1f406259ae37a7c2c633af8630a1ad82f712f1a9b2f2bd4d0468f8d1051d","target":"graph","created_at":"2026-07-05T05:18:06Z","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/2209.03126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is increasing interest in the use of multimodal data in various web applications, such as digital advertising and e-commerce. Typical methods for extracting important information from multimodal data rely on a mid-fusion architecture that combines the feature representations from multiple encoders. However, as the number of modalities increases, several potential problems with the mid-fusion model structure arise, such as an increase in the dimensionality of the concatenated multimodal features and missing modalities. To address these problems, we propose a new concept that considers mul","authors_text":"Hitoshi Iyatomi, Riku Togashi, Shunsuke Kitada, Yuki Iwazaki","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2022-09-07T13:25:09Z","title":"DM$^2$S$^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.03126","kind":"arxiv","version":2},"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":"sha256:88a17563f2a5aae82aa850303116d12e73f364bb0162d542d5f1178120447edb","target":"record","created_at":"2026-07-05T05:18:06Z","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":"0b32bdf8770c3f6ea5d829861b8e72b498992551040cca1e641b3326ec6d4030","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2022-09-07T13:25:09Z","title_canon_sha256":"c67474b0926d5fd42d6abd5ccfcf4f020aea7c85ec18af86ae28db5602e23a0d"},"schema_version":"1.0","source":{"id":"2209.03126","kind":"arxiv","version":2}},"canonical_sha256":"5865570737ad3ef48cfdda70f99ec5b3bf39ec5b89f12fb4833445f978de895f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5865570737ad3ef48cfdda70f99ec5b3bf39ec5b89f12fb4833445f978de895f","first_computed_at":"2026-07-05T05:18:06.807576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:18:06.807576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9GL8nFEGOZBR1kB3fZHKHLhxcCfB+ikRsii03VJxQgdEUEK8Y+d+tuo4xs6hNlKAJLPMI6pwzDSRRH447IkGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:18:06.808047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.03126","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88a17563f2a5aae82aa850303116d12e73f364bb0162d542d5f1178120447edb","sha256:7b8f1f406259ae37a7c2c633af8630a1ad82f712f1a9b2f2bd4d0468f8d1051d"],"state_sha256":"1b4b3842b5529d4a90d805f22bbfc89e6fb4469981d119be9c0a0982b890fcfc"}