{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YNHGXOP6UEHJCHE32ETV5AAWSM","short_pith_number":"pith:YNHGXOP6","canonical_record":{"source":{"id":"2205.12522","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-25T06:30:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"082671db8afd6da84126082da045959b2c689405f3e32a36c424740539f001ef","abstract_canon_sha256":"7096f8704cdfe6ac3d08fb9579af0433bd436a96ab8416bfc59713204a2edf4a"},"schema_version":"1.0"},"canonical_sha256":"c34e6bb9fea10e911c9bd1275e8016931f9444548a47a36dae5ca71f57402851","source":{"kind":"arxiv","id":"2205.12522","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12522","created_at":"2026-07-05T05:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12522v2","created_at":"2026-07-05T05:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12522","created_at":"2026-07-05T05:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"YNHGXOP6UEHJ","created_at":"2026-07-05T05:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"YNHGXOP6UEHJCHE3","created_at":"2026-07-05T05:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"YNHGXOP6","created_at":"2026-07-05T05:04:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YNHGXOP6UEHJCHE32ETV5AAWSM","target":"record","payload":{"canonical_record":{"source":{"id":"2205.12522","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-25T06:30:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"082671db8afd6da84126082da045959b2c689405f3e32a36c424740539f001ef","abstract_canon_sha256":"7096f8704cdfe6ac3d08fb9579af0433bd436a96ab8416bfc59713204a2edf4a"},"schema_version":"1.0"},"canonical_sha256":"c34e6bb9fea10e911c9bd1275e8016931f9444548a47a36dae5ca71f57402851","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:48.781084Z","signature_b64":"uBVxhYT+yx08oZ8H9jUk8D5j+EsW3WCCFRwYstFM1qehkMA8ObfQEishb19NSDFkr/AZVoTJKkuhVBK+R2ZJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c34e6bb9fea10e911c9bd1275e8016931f9444548a47a36dae5ca71f57402851","last_reissued_at":"2026-07-05T05:04:48.780589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:48.780589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.12522","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Ewwj0MGbyEBooVCdxzAkrJVIoYafpgnXz1Dy3ZhdmZ8Y5CPYn3mwObzwug06DWgppS/FGooaaAd7oDEa5SBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T16:15:28.918241Z"},"content_sha256":"1f70db0d1fa4264969991e8bdf1936edd84e97eacd4b0754de833370fbc541ad","schema_version":"1.0","event_id":"sha256:1f70db0d1fa4264969991e8bdf1936edd84e97eacd4b0754de833370fbc541ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YNHGXOP6UEHJCHE32ETV5AAWSM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ashish V. Thapliyal, Jordi Pont-Tuset, Radu Soricut, Xi Chen","submitted_at":"2022-05-25T06:30:19Z","abstract_excerpt":"Research in massively multilingual image captioning has been severely hampered by a lack of high-quality evaluation datasets. In this paper we present the Crossmodal-3600 dataset (XM3600 in short), a geographically diverse set of 3600 images annotated with human-generated reference captions in 36 languages. The images were selected from across the world, covering regions where the 36 languages are spoken, and annotated with captions that achieve consistency in terms of style across all languages, while avoiding annotation artifacts due to direct translation. We apply this benchmark to model se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12522","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/2205.12522/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":"2026-07-05T05:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IOwsOJPah1cBr6ZONlAmZqyd2SVq/TzOpIUfzqFlp48cLftS2iB+Lquv8k2LI93ZUEeb3ZjK1RzvOkrYOAwVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T16:15:28.918775Z"},"content_sha256":"49650b8a6323c2febf8b3377135616993bf27ed99d1ef4831106669d497f3ded","schema_version":"1.0","event_id":"sha256:49650b8a6323c2febf8b3377135616993bf27ed99d1ef4831106669d497f3ded"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YNHGXOP6UEHJCHE32ETV5AAWSM/bundle.json","state_url":"https://pith.science/pith/YNHGXOP6UEHJCHE32ETV5AAWSM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YNHGXOP6UEHJCHE32ETV5AAWSM/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":"2026-08-22T16:15:28Z","links":{"resolver":"https://pith.science/pith/YNHGXOP6UEHJCHE32ETV5AAWSM","bundle":"https://pith.science/pith/YNHGXOP6UEHJCHE32ETV5AAWSM/bundle.json","state":"https://pith.science/pith/YNHGXOP6UEHJCHE32ETV5AAWSM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YNHGXOP6UEHJCHE32ETV5AAWSM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YNHGXOP6UEHJCHE32ETV5AAWSM","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":"7096f8704cdfe6ac3d08fb9579af0433bd436a96ab8416bfc59713204a2edf4a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-25T06:30:19Z","title_canon_sha256":"082671db8afd6da84126082da045959b2c689405f3e32a36c424740539f001ef"},"schema_version":"1.0","source":{"id":"2205.12522","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12522","created_at":"2026-07-05T05:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12522v2","created_at":"2026-07-05T05:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12522","created_at":"2026-07-05T05:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"YNHGXOP6UEHJ","created_at":"2026-07-05T05:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"YNHGXOP6UEHJCHE3","created_at":"2026-07-05T05:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"YNHGXOP6","created_at":"2026-07-05T05:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:49650b8a6323c2febf8b3377135616993bf27ed99d1ef4831106669d497f3ded","target":"graph","created_at":"2026-07-05T05:04:48Z","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/2205.12522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Research in massively multilingual image captioning has been severely hampered by a lack of high-quality evaluation datasets. In this paper we present the Crossmodal-3600 dataset (XM3600 in short), a geographically diverse set of 3600 images annotated with human-generated reference captions in 36 languages. The images were selected from across the world, covering regions where the 36 languages are spoken, and annotated with captions that achieve consistency in terms of style across all languages, while avoiding annotation artifacts due to direct translation. We apply this benchmark to model se","authors_text":"Ashish V. Thapliyal, Jordi Pont-Tuset, Radu Soricut, Xi Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-25T06:30:19Z","title":"Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12522","kind":"arxiv","version":2},"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":"sha256:1f70db0d1fa4264969991e8bdf1936edd84e97eacd4b0754de833370fbc541ad","target":"record","created_at":"2026-07-05T05:04:48Z","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":"7096f8704cdfe6ac3d08fb9579af0433bd436a96ab8416bfc59713204a2edf4a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-25T06:30:19Z","title_canon_sha256":"082671db8afd6da84126082da045959b2c689405f3e32a36c424740539f001ef"},"schema_version":"1.0","source":{"id":"2205.12522","kind":"arxiv","version":2}},"canonical_sha256":"c34e6bb9fea10e911c9bd1275e8016931f9444548a47a36dae5ca71f57402851","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c34e6bb9fea10e911c9bd1275e8016931f9444548a47a36dae5ca71f57402851","first_computed_at":"2026-07-05T05:04:48.780589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:48.780589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uBVxhYT+yx08oZ8H9jUk8D5j+EsW3WCCFRwYstFM1qehkMA8ObfQEishb19NSDFkr/AZVoTJKkuhVBK+R2ZJBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:48.781084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.12522","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f70db0d1fa4264969991e8bdf1936edd84e97eacd4b0754de833370fbc541ad","sha256:49650b8a6323c2febf8b3377135616993bf27ed99d1ef4831106669d497f3ded"],"state_sha256":"15fc405999a45a38cc099466e47b4ce031b46681adb770f50ca4f92b1c05959a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uGxaRS2ESv4Yu1J+suz8CeGf91aXCAv6SQcYLD1nxcuYKVXk6Qy9gOo/W70BOutMmz2T3UqEqcjW1QHui1MtDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T16:15:28.924769Z","bundle_sha256":"91b228ce839d7e859c51c9515f9768f2e7362188cb0fbd37d008aab4c2649af4"}}