{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GTB6STYKAEBXEHSCDOQK65US2D","short_pith_number":"pith:GTB6STYK","canonical_record":{"source":{"id":"2201.08054","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-20T08:38:31Z","cross_cats_sorted":[],"title_canon_sha256":"2b3ea6f844ea6c742db78509a527c137d5ccdfc53512875eb0f5df578c0543e7","abstract_canon_sha256":"8d5c7496c8f4943d8df2309817502a5c7080ec8dc44ad7e24539b0db8cbacc3b"},"schema_version":"1.0"},"canonical_sha256":"34c3e94f0a0103721e421ba0af7692d0ce806f33cd8e91f625be4d706f4099f7","source":{"kind":"arxiv","id":"2201.08054","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.08054","created_at":"2026-07-05T04:26:35Z"},{"alias_kind":"arxiv_version","alias_value":"2201.08054v3","created_at":"2026-07-05T04:26:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08054","created_at":"2026-07-05T04:26:35Z"},{"alias_kind":"pith_short_12","alias_value":"GTB6STYKAEBX","created_at":"2026-07-05T04:26:35Z"},{"alias_kind":"pith_short_16","alias_value":"GTB6STYKAEBXEHSC","created_at":"2026-07-05T04:26:35Z"},{"alias_kind":"pith_short_8","alias_value":"GTB6STYK","created_at":"2026-07-05T04:26:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GTB6STYKAEBXEHSCDOQK65US2D","target":"record","payload":{"canonical_record":{"source":{"id":"2201.08054","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-20T08:38:31Z","cross_cats_sorted":[],"title_canon_sha256":"2b3ea6f844ea6c742db78509a527c137d5ccdfc53512875eb0f5df578c0543e7","abstract_canon_sha256":"8d5c7496c8f4943d8df2309817502a5c7080ec8dc44ad7e24539b0db8cbacc3b"},"schema_version":"1.0"},"canonical_sha256":"34c3e94f0a0103721e421ba0af7692d0ce806f33cd8e91f625be4d706f4099f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:35.628837Z","signature_b64":"YP3Da/viswnHMTJqM/hTwp/51uR2+E93s0pYOEtnT9Mctt1kftQl7CLgL+33SmPVXsMvl51Oax8/1Kv9F7Z1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34c3e94f0a0103721e421ba0af7692d0ce806f33cd8e91f625be4d706f4099f7","last_reissued_at":"2026-07-05T04:26:35.628337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:35.628337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.08054","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:26:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6DX28BkSfy2gNliPFqdUqqS2dg7Y8sOjbpDYCOSee4mgrRWZGFaQXBbKAWz2PF4JC5elUAEbRjlmn1CXvMV+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:06:14.375469Z"},"content_sha256":"1072cd591380110b1dc35c5e4a73795024f56513ab9680d540dc9c50d2923cd3","schema_version":"1.0","event_id":"sha256:1072cd591380110b1dc35c5e4a73795024f56513ab9680d540dc9c50d2923cd3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GTB6STYKAEBXEHSCDOQK65US2D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VISA: An Ambiguous Subtitles Dataset for Visual Scene-Aware Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenhui Chu, Sadao Kurohashi, Shuichiro Shimizu, Weiqi Gu, Yihang Li","submitted_at":"2022-01-20T08:38:31Z","abstract_excerpt":"Existing multimodal machine translation (MMT) datasets consist of images and video captions or general subtitles, which rarely contain linguistic ambiguity, making visual information not so effective to generate appropriate translations. We introduce VISA, a new dataset that consists of 40k Japanese-English parallel sentence pairs and corresponding video clips with the following key features: (1) the parallel sentences are subtitles from movies and TV episodes; (2) the source subtitles are ambiguous, which means they have multiple possible translations with different meanings; (3) we divide th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08054","kind":"arxiv","version":3},"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/2201.08054/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":"2026-07-05T04:26:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MuQECkB2aC0QaEalgXz9FKMwE4DJxrxnXdFfhfxlVW72GU2HoNVzfdU6qPROseSEoGZGfFv88PSg5A5KCWTVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:06:14.376007Z"},"content_sha256":"9548cb99674dc83d1f1788b37f874a7a0385aa2b3a07ee7e36bf149e7885e719","schema_version":"1.0","event_id":"sha256:9548cb99674dc83d1f1788b37f874a7a0385aa2b3a07ee7e36bf149e7885e719"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GTB6STYKAEBXEHSCDOQK65US2D/bundle.json","state_url":"https://pith.science/pith/GTB6STYKAEBXEHSCDOQK65US2D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GTB6STYKAEBXEHSCDOQK65US2D/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":"2026-08-18T04:06:14Z","links":{"resolver":"https://pith.science/pith/GTB6STYKAEBXEHSCDOQK65US2D","bundle":"https://pith.science/pith/GTB6STYKAEBXEHSCDOQK65US2D/bundle.json","state":"https://pith.science/pith/GTB6STYKAEBXEHSCDOQK65US2D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GTB6STYKAEBXEHSCDOQK65US2D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GTB6STYKAEBXEHSCDOQK65US2D","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":"8d5c7496c8f4943d8df2309817502a5c7080ec8dc44ad7e24539b0db8cbacc3b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-20T08:38:31Z","title_canon_sha256":"2b3ea6f844ea6c742db78509a527c137d5ccdfc53512875eb0f5df578c0543e7"},"schema_version":"1.0","source":{"id":"2201.08054","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.08054","created_at":"2026-07-05T04:26:35Z"},{"alias_kind":"arxiv_version","alias_value":"2201.08054v3","created_at":"2026-07-05T04:26:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08054","created_at":"2026-07-05T04:26:35Z"},{"alias_kind":"pith_short_12","alias_value":"GTB6STYKAEBX","created_at":"2026-07-05T04:26:35Z"},{"alias_kind":"pith_short_16","alias_value":"GTB6STYKAEBXEHSC","created_at":"2026-07-05T04:26:35Z"},{"alias_kind":"pith_short_8","alias_value":"GTB6STYK","created_at":"2026-07-05T04:26:35Z"}],"graph_snapshots":[{"event_id":"sha256:9548cb99674dc83d1f1788b37f874a7a0385aa2b3a07ee7e36bf149e7885e719","target":"graph","created_at":"2026-07-05T04:26:35Z","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/2201.08054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing multimodal machine translation (MMT) datasets consist of images and video captions or general subtitles, which rarely contain linguistic ambiguity, making visual information not so effective to generate appropriate translations. We introduce VISA, a new dataset that consists of 40k Japanese-English parallel sentence pairs and corresponding video clips with the following key features: (1) the parallel sentences are subtitles from movies and TV episodes; (2) the source subtitles are ambiguous, which means they have multiple possible translations with different meanings; (3) we divide th","authors_text":"Chenhui Chu, Sadao Kurohashi, Shuichiro Shimizu, Weiqi Gu, Yihang Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-20T08:38:31Z","title":"VISA: An Ambiguous Subtitles Dataset for Visual Scene-Aware Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08054","kind":"arxiv","version":3},"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":"sha256:1072cd591380110b1dc35c5e4a73795024f56513ab9680d540dc9c50d2923cd3","target":"record","created_at":"2026-07-05T04:26:35Z","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":"8d5c7496c8f4943d8df2309817502a5c7080ec8dc44ad7e24539b0db8cbacc3b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-20T08:38:31Z","title_canon_sha256":"2b3ea6f844ea6c742db78509a527c137d5ccdfc53512875eb0f5df578c0543e7"},"schema_version":"1.0","source":{"id":"2201.08054","kind":"arxiv","version":3}},"canonical_sha256":"34c3e94f0a0103721e421ba0af7692d0ce806f33cd8e91f625be4d706f4099f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34c3e94f0a0103721e421ba0af7692d0ce806f33cd8e91f625be4d706f4099f7","first_computed_at":"2026-07-05T04:26:35.628337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:35.628337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YP3Da/viswnHMTJqM/hTwp/51uR2+E93s0pYOEtnT9Mctt1kftQl7CLgL+33SmPVXsMvl51Oax8/1Kv9F7Z1Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:35.628837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.08054","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1072cd591380110b1dc35c5e4a73795024f56513ab9680d540dc9c50d2923cd3","sha256:9548cb99674dc83d1f1788b37f874a7a0385aa2b3a07ee7e36bf149e7885e719"],"state_sha256":"89246ff08aabacb552468baf77ee73c56e7d48693d2f235e3489d389205a782c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"smv9AYpG3g6cNz3Jt8MZQYTrru1RcHza1wOcUNT6Enktg+C2e9Ty4TEePO0ij4iIcwRgXEg4AfDLfvXVcjv2Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T04:06:14.382165Z","bundle_sha256":"49289263d51393129b308580124f39cecfd0a9b51488cf3141d060f6cbfb84ff"}}