{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LBSVOBZXVU7PJDH53JYPTHWFWO","short_pith_number":"pith:LBSVOBZX","schema_version":"1.0","canonical_sha256":"5865570737ad3ef48cfdda70f99ec5b3bf39ec5b89f12fb4833445f978de895f","source":{"kind":"arxiv","id":"2209.03126","version":2},"attestation_state":"computed","paper":{"title":"DM$^2$S$^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.MM","authors_text":"Hitoshi Iyatomi, Riku Togashi, Shunsuke Kitada, Yuki Iwazaki","submitted_at":"2022-09-07T13:25:09Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.03126","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2022-09-07T13:25:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"c67474b0926d5fd42d6abd5ccfcf4f020aea7c85ec18af86ae28db5602e23a0d","abstract_canon_sha256":"0b32bdf8770c3f6ea5d829861b8e72b498992551040cca1e641b3326ec6d4030"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:06.808047Z","signature_b64":"9GL8nFEGOZBR1kB3fZHKHLhxcCfB+ikRsii03VJxQgdEUEK8Y+d+tuo4xs6hNlKAJLPMI6pwzDSRRH447IkGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5865570737ad3ef48cfdda70f99ec5b3bf39ec5b89f12fb4833445f978de895f","last_reissued_at":"2026-07-05T05:18:06.807576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:06.807576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DM$^2$S$^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.MM","authors_text":"Hitoshi Iyatomi, Riku Togashi, Shunsuke Kitada, Yuki Iwazaki","submitted_at":"2022-09-07T13:25:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.03126","kind":"arxiv","version":2},"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/2209.03126/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.03126","created_at":"2026-07-05T05:18:06.807637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.03126v2","created_at":"2026-07-05T05:18:06.807637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.03126","created_at":"2026-07-05T05:18:06.807637+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBSVOBZXVU7P","created_at":"2026-07-05T05:18:06.807637+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBSVOBZXVU7PJDH5","created_at":"2026-07-05T05:18:06.807637+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBSVOBZX","created_at":"2026-07-05T05:18:06.807637+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBSVOBZXVU7PJDH53JYPTHWFWO","json":"https://pith.science/pith/LBSVOBZXVU7PJDH53JYPTHWFWO.json","graph_json":"https://pith.science/api/pith-number/LBSVOBZXVU7PJDH53JYPTHWFWO/graph.json","events_json":"https://pith.science/api/pith-number/LBSVOBZXVU7PJDH53JYPTHWFWO/events.json","paper":"https://pith.science/paper/LBSVOBZX"},"agent_actions":{"view_html":"https://pith.science/pith/LBSVOBZXVU7PJDH53JYPTHWFWO","download_json":"https://pith.science/pith/LBSVOBZXVU7PJDH53JYPTHWFWO.json","view_paper":"https://pith.science/paper/LBSVOBZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.03126&json=true","fetch_graph":"https://pith.science/api/pith-number/LBSVOBZXVU7PJDH53JYPTHWFWO/graph.json","fetch_events":"https://pith.science/api/pith-number/LBSVOBZXVU7PJDH53JYPTHWFWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBSVOBZXVU7PJDH53JYPTHWFWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBSVOBZXVU7PJDH53JYPTHWFWO/action/storage_attestation","attest_author":"https://pith.science/pith/LBSVOBZXVU7PJDH53JYPTHWFWO/action/author_attestation","sign_citation":"https://pith.science/pith/LBSVOBZXVU7PJDH53JYPTHWFWO/action/citation_signature","submit_replication":"https://pith.science/pith/LBSVOBZXVU7PJDH53JYPTHWFWO/action/replication_record"}},"created_at":"2026-07-05T05:18:06.807637+00:00","updated_at":"2026-07-05T05:18:06.807637+00:00"}