{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LUWYOS3XW5GRDYGCEH672XLYNC","short_pith_number":"pith:LUWYOS3X","canonical_record":{"source":{"id":"2403.17545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T09:49:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e6b1c2cfac3f82cfd898e60be0c26cdcf3395323dc974b911d912212216afd5d","abstract_canon_sha256":"acecf1637825170c8d1d3b25b2061cbd392a667723795fd38eccdbcf784c8e20"},"schema_version":"1.0"},"canonical_sha256":"5d2d874b77b74d11e0c221fdfd5d7868a1a655aa037f80687292195b4d392996","source":{"kind":"arxiv","id":"2403.17545","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17545","created_at":"2026-07-05T08:00:52Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17545v1","created_at":"2026-07-05T08:00:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17545","created_at":"2026-07-05T08:00:52Z"},{"alias_kind":"pith_short_12","alias_value":"LUWYOS3XW5GR","created_at":"2026-07-05T08:00:52Z"},{"alias_kind":"pith_short_16","alias_value":"LUWYOS3XW5GRDYGC","created_at":"2026-07-05T08:00:52Z"},{"alias_kind":"pith_short_8","alias_value":"LUWYOS3X","created_at":"2026-07-05T08:00:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LUWYOS3XW5GRDYGCEH672XLYNC","target":"record","payload":{"canonical_record":{"source":{"id":"2403.17545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T09:49:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e6b1c2cfac3f82cfd898e60be0c26cdcf3395323dc974b911d912212216afd5d","abstract_canon_sha256":"acecf1637825170c8d1d3b25b2061cbd392a667723795fd38eccdbcf784c8e20"},"schema_version":"1.0"},"canonical_sha256":"5d2d874b77b74d11e0c221fdfd5d7868a1a655aa037f80687292195b4d392996","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:52.164601Z","signature_b64":"iNdLiL2C6SHZB2s4TxQaZGrGcjhi66/vQlc/PNMwBiX0sk3bQI8FVfUo30Fbyf28/ep2/6uDVi0MGnJu3xIxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d2d874b77b74d11e0c221fdfd5d7868a1a655aa037f80687292195b4d392996","last_reissued_at":"2026-07-05T08:00:52.164138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:52.164138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.17545","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":"2026-07-05T08:00:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/LaM3IiFpPnaEDrYbVY6HT/n8m1jkvi81jwbBO8GtvXehxIqKCDefbNbm2AFe0hRtcza2ONNuJuO/lE+eNFzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:55:17.471668Z"},"content_sha256":"d3b6a43981eefa2c5634cb96fbee485d9717ad4782fbc08f8d69b96d8ff3a8ed","schema_version":"1.0","event_id":"sha256:d3b6a43981eefa2c5634cb96fbee485d9717ad4782fbc08f8d69b96d8ff3a8ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LUWYOS3XW5GRDYGCEH672XLYNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Akishige Yuguchi, Koichiro Yoshino, Seiya Kawano, Shun Inadumi, Yasutomo Kawanishi","submitted_at":"2024-03-26T09:49:35Z","abstract_excerpt":"Situated conversations, which refer to visual information as visual question answering (VQA), often contain ambiguities caused by reliance on directive information. This problem is exacerbated because some languages, such as Japanese, often omit subjective or objective terms. Such ambiguities in questions are often clarified by the contexts in conversational situations, such as joint attention with a user or user gaze information. In this study, we propose the Gaze-grounded VQA dataset (GazeVQA) that clarifies ambiguous questions using gaze information by focusing on a clarification process co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17545","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/2403.17545/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":"2026-07-05T08:00:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s99Z9qj+JICLnmGur1ii1t/2wzSwbYAoQ+E698xGNk6CTqZnd5nmY4ACGu3u0eslvmDPYVgsCtpqb4R+SHezDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:55:17.472152Z"},"content_sha256":"75562e0d5c243d8ee3330a3f315494b02cc3224e2077896f6650e274fe5e6f81","schema_version":"1.0","event_id":"sha256:75562e0d5c243d8ee3330a3f315494b02cc3224e2077896f6650e274fe5e6f81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LUWYOS3XW5GRDYGCEH672XLYNC/bundle.json","state_url":"https://pith.science/pith/LUWYOS3XW5GRDYGCEH672XLYNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LUWYOS3XW5GRDYGCEH672XLYNC/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":"2026-08-03T15:55:17Z","links":{"resolver":"https://pith.science/pith/LUWYOS3XW5GRDYGCEH672XLYNC","bundle":"https://pith.science/pith/LUWYOS3XW5GRDYGCEH672XLYNC/bundle.json","state":"https://pith.science/pith/LUWYOS3XW5GRDYGCEH672XLYNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LUWYOS3XW5GRDYGCEH672XLYNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LUWYOS3XW5GRDYGCEH672XLYNC","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":"acecf1637825170c8d1d3b25b2061cbd392a667723795fd38eccdbcf784c8e20","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T09:49:35Z","title_canon_sha256":"e6b1c2cfac3f82cfd898e60be0c26cdcf3395323dc974b911d912212216afd5d"},"schema_version":"1.0","source":{"id":"2403.17545","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17545","created_at":"2026-07-05T08:00:52Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17545v1","created_at":"2026-07-05T08:00:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17545","created_at":"2026-07-05T08:00:52Z"},{"alias_kind":"pith_short_12","alias_value":"LUWYOS3XW5GR","created_at":"2026-07-05T08:00:52Z"},{"alias_kind":"pith_short_16","alias_value":"LUWYOS3XW5GRDYGC","created_at":"2026-07-05T08:00:52Z"},{"alias_kind":"pith_short_8","alias_value":"LUWYOS3X","created_at":"2026-07-05T08:00:52Z"}],"graph_snapshots":[{"event_id":"sha256:75562e0d5c243d8ee3330a3f315494b02cc3224e2077896f6650e274fe5e6f81","target":"graph","created_at":"2026-07-05T08:00:52Z","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/2403.17545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Situated conversations, which refer to visual information as visual question answering (VQA), often contain ambiguities caused by reliance on directive information. This problem is exacerbated because some languages, such as Japanese, often omit subjective or objective terms. Such ambiguities in questions are often clarified by the contexts in conversational situations, such as joint attention with a user or user gaze information. In this study, we propose the Gaze-grounded VQA dataset (GazeVQA) that clarifies ambiguous questions using gaze information by focusing on a clarification process co","authors_text":"Akishige Yuguchi, Koichiro Yoshino, Seiya Kawano, Shun Inadumi, Yasutomo Kawanishi","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T09:49:35Z","title":"A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17545","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:d3b6a43981eefa2c5634cb96fbee485d9717ad4782fbc08f8d69b96d8ff3a8ed","target":"record","created_at":"2026-07-05T08:00:52Z","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":"acecf1637825170c8d1d3b25b2061cbd392a667723795fd38eccdbcf784c8e20","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T09:49:35Z","title_canon_sha256":"e6b1c2cfac3f82cfd898e60be0c26cdcf3395323dc974b911d912212216afd5d"},"schema_version":"1.0","source":{"id":"2403.17545","kind":"arxiv","version":1}},"canonical_sha256":"5d2d874b77b74d11e0c221fdfd5d7868a1a655aa037f80687292195b4d392996","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d2d874b77b74d11e0c221fdfd5d7868a1a655aa037f80687292195b4d392996","first_computed_at":"2026-07-05T08:00:52.164138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:52.164138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iNdLiL2C6SHZB2s4TxQaZGrGcjhi66/vQlc/PNMwBiX0sk3bQI8FVfUo30Fbyf28/ep2/6uDVi0MGnJu3xIxCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:52.164601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.17545","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3b6a43981eefa2c5634cb96fbee485d9717ad4782fbc08f8d69b96d8ff3a8ed","sha256:75562e0d5c243d8ee3330a3f315494b02cc3224e2077896f6650e274fe5e6f81"],"state_sha256":"790bf056baad9566b970ad70be33c5e23c18ff369acb2249b8d8d1fa1a94b108"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GPPuxLTJ0JGIjik45WuZmgSFTm0SKKdb+9chy4IlMWaiVfovV0U3RM/dCLJ2oKpgJYv78MeAkNVY17lB6wCVCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:55:17.475566Z","bundle_sha256":"cfce039e83b3ac0b371fcd7143a40e5bd95f7f462b7d32707c4f6c412670d4d2"}}