{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OTZ6UZYBWZMHJDFGW7FCN42SQ5","short_pith_number":"pith:OTZ6UZYB","canonical_record":{"source":{"id":"2505.23308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-29T10:06:48Z","cross_cats_sorted":["cs.AI","eess.IV"],"title_canon_sha256":"39cf4b3849caf5d37ca55a01ca761a441df3ecefc4f6d3253fb0543f24545955","abstract_canon_sha256":"126e1c3abc7f49eb129005e2e73689db97620595d9983bb5a4d4f415fe3db5f0"},"schema_version":"1.0"},"canonical_sha256":"74f3ea6701b658748ca6b7ca26f3528752ae9608f3d45c52de63f7e0303480b5","source":{"kind":"arxiv","id":"2505.23308","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23308","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23308v1","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23308","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"pith_short_12","alias_value":"OTZ6UZYBWZMH","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"pith_short_16","alias_value":"OTZ6UZYBWZMHJDFG","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"pith_short_8","alias_value":"OTZ6UZYB","created_at":"2026-07-05T11:11:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OTZ6UZYBWZMHJDFGW7FCN42SQ5","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-29T10:06:48Z","cross_cats_sorted":["cs.AI","eess.IV"],"title_canon_sha256":"39cf4b3849caf5d37ca55a01ca761a441df3ecefc4f6d3253fb0543f24545955","abstract_canon_sha256":"126e1c3abc7f49eb129005e2e73689db97620595d9983bb5a4d4f415fe3db5f0"},"schema_version":"1.0"},"canonical_sha256":"74f3ea6701b658748ca6b7ca26f3528752ae9608f3d45c52de63f7e0303480b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:59.242294Z","signature_b64":"6C0zk2Ng5iQNYe5vmugMzokR8qrIle8Qq4FakXO/AUzfzLDaglrmWP1guW++LtZ6Xri8x6gPuRuCncI8V2C0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74f3ea6701b658748ca6b7ca26f3528752ae9608f3d45c52de63f7e0303480b5","last_reissued_at":"2026-07-05T11:11:59.241807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:59.241807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23308","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":"2026-07-05T11:11:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ZPJn+4oSH20adoMEDK1kqrIBGFuX/4AaSd+RdOuK2T4ZVJgD5h7SDMPhJv7NL+PbC0XMUKplWOamyn6f987BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:51:41.945072Z"},"content_sha256":"aa484d7e00296670befda25ab4cd00fcc330073b618eb6faaee524b977893eb2","schema_version":"1.0","event_id":"sha256:aa484d7e00296670befda25ab4cd00fcc330073b618eb6faaee524b977893eb2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OTZ6UZYBWZMHJDFGW7FCN42SQ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spoken question answering for visual queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.IV"],"primary_cat":"eess.AS","authors_text":"Assaf Arbelle, Avihu Dekel, Hagai Aronowitz, Nimrod Shabtay, Ron Hoory, Zvi Kons","submitted_at":"2025-05-29T10:06:48Z","abstract_excerpt":"Question answering (QA) systems are designed to answer natural language questions. Visual QA (VQA) and Spoken QA (SQA) systems extend the textual QA system to accept visual and spoken input respectively.\n  This work aims to create a system that enables user interaction through both speech and images. That is achieved through the fusion of text, speech, and image modalities to tackle the task of spoken VQA (SVQA). The resulting multi-modal model has textual, visual, and spoken inputs and can answer spoken questions on images.\n  Training and evaluating SVQA models requires a dataset for all thre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23308","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/2505.23308/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":"2026-07-05T11:11:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gJ1ds6RmVa/MuG6UprHmkPYuB32vSCcqVoK35gNWBzI5iD2AMwY43LOM8DnusNuLJpVgoucvgpmV46xB7hXcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:51:41.945992Z"},"content_sha256":"0e5fc01f0b699ccd51a7a11bfecae5bdb2eee9c6a4b3cbd6f1e61c17df09d0f4","schema_version":"1.0","event_id":"sha256:0e5fc01f0b699ccd51a7a11bfecae5bdb2eee9c6a4b3cbd6f1e61c17df09d0f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OTZ6UZYBWZMHJDFGW7FCN42SQ5/bundle.json","state_url":"https://pith.science/pith/OTZ6UZYBWZMHJDFGW7FCN42SQ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OTZ6UZYBWZMHJDFGW7FCN42SQ5/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":"2026-08-06T03:51:41Z","links":{"resolver":"https://pith.science/pith/OTZ6UZYBWZMHJDFGW7FCN42SQ5","bundle":"https://pith.science/pith/OTZ6UZYBWZMHJDFGW7FCN42SQ5/bundle.json","state":"https://pith.science/pith/OTZ6UZYBWZMHJDFGW7FCN42SQ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OTZ6UZYBWZMHJDFGW7FCN42SQ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OTZ6UZYBWZMHJDFGW7FCN42SQ5","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":"126e1c3abc7f49eb129005e2e73689db97620595d9983bb5a4d4f415fe3db5f0","cross_cats_sorted":["cs.AI","eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-29T10:06:48Z","title_canon_sha256":"39cf4b3849caf5d37ca55a01ca761a441df3ecefc4f6d3253fb0543f24545955"},"schema_version":"1.0","source":{"id":"2505.23308","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23308","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23308v1","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23308","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"pith_short_12","alias_value":"OTZ6UZYBWZMH","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"pith_short_16","alias_value":"OTZ6UZYBWZMHJDFG","created_at":"2026-07-05T11:11:59Z"},{"alias_kind":"pith_short_8","alias_value":"OTZ6UZYB","created_at":"2026-07-05T11:11:59Z"}],"graph_snapshots":[{"event_id":"sha256:0e5fc01f0b699ccd51a7a11bfecae5bdb2eee9c6a4b3cbd6f1e61c17df09d0f4","target":"graph","created_at":"2026-07-05T11:11:59Z","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/2505.23308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Question answering (QA) systems are designed to answer natural language questions. Visual QA (VQA) and Spoken QA (SQA) systems extend the textual QA system to accept visual and spoken input respectively.\n  This work aims to create a system that enables user interaction through both speech and images. That is achieved through the fusion of text, speech, and image modalities to tackle the task of spoken VQA (SVQA). The resulting multi-modal model has textual, visual, and spoken inputs and can answer spoken questions on images.\n  Training and evaluating SVQA models requires a dataset for all thre","authors_text":"Assaf Arbelle, Avihu Dekel, Hagai Aronowitz, Nimrod Shabtay, Ron Hoory, Zvi Kons","cross_cats":["cs.AI","eess.IV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-29T10:06:48Z","title":"Spoken question answering for visual queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23308","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:aa484d7e00296670befda25ab4cd00fcc330073b618eb6faaee524b977893eb2","target":"record","created_at":"2026-07-05T11:11:59Z","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":"126e1c3abc7f49eb129005e2e73689db97620595d9983bb5a4d4f415fe3db5f0","cross_cats_sorted":["cs.AI","eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-29T10:06:48Z","title_canon_sha256":"39cf4b3849caf5d37ca55a01ca761a441df3ecefc4f6d3253fb0543f24545955"},"schema_version":"1.0","source":{"id":"2505.23308","kind":"arxiv","version":1}},"canonical_sha256":"74f3ea6701b658748ca6b7ca26f3528752ae9608f3d45c52de63f7e0303480b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74f3ea6701b658748ca6b7ca26f3528752ae9608f3d45c52de63f7e0303480b5","first_computed_at":"2026-07-05T11:11:59.241807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:59.241807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6C0zk2Ng5iQNYe5vmugMzokR8qrIle8Qq4FakXO/AUzfzLDaglrmWP1guW++LtZ6Xri8x6gPuRuCncI8V2C0CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:59.242294Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23308","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa484d7e00296670befda25ab4cd00fcc330073b618eb6faaee524b977893eb2","sha256:0e5fc01f0b699ccd51a7a11bfecae5bdb2eee9c6a4b3cbd6f1e61c17df09d0f4"],"state_sha256":"bdfcac709949595cb71ddc35e3d362d47059d77e58cb2321fcbca65c02c7a33c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vHkQwdxcUoiHNGnTB/tL+ut8kmqpS7vNoyfVIsB9hX0g1yqrUUZsre+7Grjz45MYSezyp91OZtvw4sDKmcFIDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:51:41.951540Z","bundle_sha256":"4ee1f7e89cfe93ef4956c0ae3315792b07be9e86e8828e1947d4c6e6830d7dae"}}