{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EMRPGEQLBPAJKSI42F734SJKUJ","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":"f59f7790994beff0008838e3b6090a7beb9482ce243a460263e98082f665abb6","cross_cats_sorted":["cs.CV","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T14:18:56Z","title_canon_sha256":"1dc3e107bd90c9ac222e1288275a0102033e7c79b849c765dbe31628d2b33b0c"},"schema_version":"1.0","source":{"id":"2406.09156","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09156","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09156v1","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09156","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_12","alias_value":"EMRPGEQLBPAJ","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_16","alias_value":"EMRPGEQLBPAJKSI4","created_at":"2026-07-05T08:31:29Z"},{"alias_kind":"pith_short_8","alias_value":"EMRPGEQL","created_at":"2026-07-05T08:31:29Z"}],"graph_snapshots":[{"event_id":"sha256:f113c65c2e98b2dc01952724fa0a8a9272db869d8430671f7a8d5294fea335fc","target":"graph","created_at":"2026-07-05T08:31:29Z","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/2406.09156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we work towards extending Audio-Visual Question Answering (AVQA) to multilingual settings. Existing AVQA research has predominantly revolved around English and replicating it for addressing AVQA in other languages requires a substantial allocation of resources. As a scalable solution, we leverage machine translation and present two multilingual AVQA datasets for eight languages created from existing benchmark AVQA datasets. This prevents extra human annotation efforts of collecting questions and answers manually. To this end, we propose, MERA framework, by leveraging state-of-th","authors_text":"Aalekhya Satya Narayani, Arun Balaji Buduru, Orchid Chetia Phukan, Priyabrata Mallick, Rajesh Sharma, Swarup Ranjan Behera","cross_cats":["cs.CV","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T14:18:56Z","title":"Towards Multilingual Audio-Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09156","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:a36dbc7f660fa3ecf879593d6ed902a654b9a77ba17b0dca7ed88bcea158f44d","target":"record","created_at":"2026-07-05T08:31:29Z","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":"f59f7790994beff0008838e3b6090a7beb9482ce243a460263e98082f665abb6","cross_cats_sorted":["cs.CV","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T14:18:56Z","title_canon_sha256":"1dc3e107bd90c9ac222e1288275a0102033e7c79b849c765dbe31628d2b33b0c"},"schema_version":"1.0","source":{"id":"2406.09156","kind":"arxiv","version":1}},"canonical_sha256":"2322f3120b0bc095491cd17fbe492aa2680fbddc315793ce55bc0858d029db0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2322f3120b0bc095491cd17fbe492aa2680fbddc315793ce55bc0858d029db0a","first_computed_at":"2026-07-05T08:31:29.164235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:29.164235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9wJmaEo+xtMoDZs1FUN8Ed3kRC+a9wGvXrXRXKp5PKAeQnS1i8ytyxBEY18tffwrANUrvMsmgMr5bFUAEKARBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:29.164751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09156","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a36dbc7f660fa3ecf879593d6ed902a654b9a77ba17b0dca7ed88bcea158f44d","sha256:f113c65c2e98b2dc01952724fa0a8a9272db869d8430671f7a8d5294fea335fc"],"state_sha256":"ba9864ee17a3303c105d845c424208968b3cd95401386a9c328f1bded3995153"}