{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LHZA3TT7LFLUFPHVJKYLHRLSSC","short_pith_number":"pith:LHZA3TT7","canonical_record":{"source":{"id":"2302.12189","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-23T17:30:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"13bde5ed9efb7b45571dd2329aef26e8e527b53d977aa30bcb58400e6f0f8ba6","abstract_canon_sha256":"f90c68c82c1aea0dc8178cb2f3f94abcdfad93788e38f41ced5c0a3fc83a9b80"},"schema_version":"1.0"},"canonical_sha256":"59f20dce7f595742bcf54ab0b3c57290931ceaac9d5432649f6d756a09396543","source":{"kind":"arxiv","id":"2302.12189","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.12189","created_at":"2026-07-05T06:53:34Z"},{"alias_kind":"arxiv_version","alias_value":"2302.12189v3","created_at":"2026-07-05T06:53:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12189","created_at":"2026-07-05T06:53:34Z"},{"alias_kind":"pith_short_12","alias_value":"LHZA3TT7LFLU","created_at":"2026-07-05T06:53:34Z"},{"alias_kind":"pith_short_16","alias_value":"LHZA3TT7LFLUFPHV","created_at":"2026-07-05T06:53:34Z"},{"alias_kind":"pith_short_8","alias_value":"LHZA3TT7","created_at":"2026-07-05T06:53:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LHZA3TT7LFLUFPHVJKYLHRLSSC","target":"record","payload":{"canonical_record":{"source":{"id":"2302.12189","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-23T17:30:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"13bde5ed9efb7b45571dd2329aef26e8e527b53d977aa30bcb58400e6f0f8ba6","abstract_canon_sha256":"f90c68c82c1aea0dc8178cb2f3f94abcdfad93788e38f41ced5c0a3fc83a9b80"},"schema_version":"1.0"},"canonical_sha256":"59f20dce7f595742bcf54ab0b3c57290931ceaac9d5432649f6d756a09396543","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:34.741217Z","signature_b64":"NmfGU0qbyUrRx1W7eOgy626TfUqI18Yb0/kbMvnVFcyJ3NsgHj9R7jRJhyChviV7sIf5z//ZzUXefWwYLgtDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59f20dce7f595742bcf54ab0b3c57290931ceaac9d5432649f6d756a09396543","last_reissued_at":"2026-07-05T06:53:34.740662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:34.740662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.12189","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":"2026-07-05T06:53:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G68l+W0qR8sssthfB16MVHmMpJEIEfHBuV8oQ3yNxv77HafLl7JwhzrjAy4HdjkBM0ZRA3d3AotpnEu+7aE/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:23:26.867724Z"},"content_sha256":"e4d8796b542f727578f41f1f95c23bceedd440aa07adac70e86650eb04d96603","schema_version":"1.0","event_id":"sha256:e4d8796b542f727578f41f1f95c23bceedd440aa07adac70e86650eb04d96603"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LHZA3TT7LFLUFPHVJKYLHRLSSC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HL Dataset: Visually-grounded Description of Scenes, Actions and Rationales","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Albert Gatt, Kees van Deemter, Michele Cafagna","submitted_at":"2023-02-23T17:30:18Z","abstract_excerpt":"Current captioning datasets focus on object-centric captions, describing the visible objects in the image, e.g. \"people eating food in a park\". Although these datasets are useful to evaluate the ability of Vision & Language models to recognize and describe visual content, they do not support controlled experiments involving model testing or fine-tuning, with more high-level captions, which humans find easy and natural to produce. For example, people often describe images based on the type of scene they depict ('people at a holiday resort') and the actions they perform ('people having a picnic'"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12189","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/2302.12189/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":"2026-07-05T06:53:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oseEjxQmroZ7uH/bolnHlFh4v8FbLzvjEZ86cK4YqC6Aq5wbTuC0fg0z9XjqcSlfSU0ewVP4YkuZq7FIQzt2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:23:26.868228Z"},"content_sha256":"8bc9eca38cdfcdd47f148d1860451ee26b8d87c63cac3c3d45886b4f86a7f989","schema_version":"1.0","event_id":"sha256:8bc9eca38cdfcdd47f148d1860451ee26b8d87c63cac3c3d45886b4f86a7f989"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LHZA3TT7LFLUFPHVJKYLHRLSSC/bundle.json","state_url":"https://pith.science/pith/LHZA3TT7LFLUFPHVJKYLHRLSSC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LHZA3TT7LFLUFPHVJKYLHRLSSC/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":"2026-08-24T00:23:26Z","links":{"resolver":"https://pith.science/pith/LHZA3TT7LFLUFPHVJKYLHRLSSC","bundle":"https://pith.science/pith/LHZA3TT7LFLUFPHVJKYLHRLSSC/bundle.json","state":"https://pith.science/pith/LHZA3TT7LFLUFPHVJKYLHRLSSC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LHZA3TT7LFLUFPHVJKYLHRLSSC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LHZA3TT7LFLUFPHVJKYLHRLSSC","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":"f90c68c82c1aea0dc8178cb2f3f94abcdfad93788e38f41ced5c0a3fc83a9b80","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-23T17:30:18Z","title_canon_sha256":"13bde5ed9efb7b45571dd2329aef26e8e527b53d977aa30bcb58400e6f0f8ba6"},"schema_version":"1.0","source":{"id":"2302.12189","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.12189","created_at":"2026-07-05T06:53:34Z"},{"alias_kind":"arxiv_version","alias_value":"2302.12189v3","created_at":"2026-07-05T06:53:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12189","created_at":"2026-07-05T06:53:34Z"},{"alias_kind":"pith_short_12","alias_value":"LHZA3TT7LFLU","created_at":"2026-07-05T06:53:34Z"},{"alias_kind":"pith_short_16","alias_value":"LHZA3TT7LFLUFPHV","created_at":"2026-07-05T06:53:34Z"},{"alias_kind":"pith_short_8","alias_value":"LHZA3TT7","created_at":"2026-07-05T06:53:34Z"}],"graph_snapshots":[{"event_id":"sha256:8bc9eca38cdfcdd47f148d1860451ee26b8d87c63cac3c3d45886b4f86a7f989","target":"graph","created_at":"2026-07-05T06:53:34Z","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/2302.12189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current captioning datasets focus on object-centric captions, describing the visible objects in the image, e.g. \"people eating food in a park\". Although these datasets are useful to evaluate the ability of Vision & Language models to recognize and describe visual content, they do not support controlled experiments involving model testing or fine-tuning, with more high-level captions, which humans find easy and natural to produce. For example, people often describe images based on the type of scene they depict ('people at a holiday resort') and the actions they perform ('people having a picnic'","authors_text":"Albert Gatt, Kees van Deemter, Michele Cafagna","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-23T17:30:18Z","title":"HL Dataset: Visually-grounded Description of Scenes, Actions and Rationales"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12189","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:e4d8796b542f727578f41f1f95c23bceedd440aa07adac70e86650eb04d96603","target":"record","created_at":"2026-07-05T06:53:34Z","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":"f90c68c82c1aea0dc8178cb2f3f94abcdfad93788e38f41ced5c0a3fc83a9b80","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-23T17:30:18Z","title_canon_sha256":"13bde5ed9efb7b45571dd2329aef26e8e527b53d977aa30bcb58400e6f0f8ba6"},"schema_version":"1.0","source":{"id":"2302.12189","kind":"arxiv","version":3}},"canonical_sha256":"59f20dce7f595742bcf54ab0b3c57290931ceaac9d5432649f6d756a09396543","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59f20dce7f595742bcf54ab0b3c57290931ceaac9d5432649f6d756a09396543","first_computed_at":"2026-07-05T06:53:34.740662Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:34.740662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NmfGU0qbyUrRx1W7eOgy626TfUqI18Yb0/kbMvnVFcyJ3NsgHj9R7jRJhyChviV7sIf5z//ZzUXefWwYLgtDAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:34.741217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.12189","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4d8796b542f727578f41f1f95c23bceedd440aa07adac70e86650eb04d96603","sha256:8bc9eca38cdfcdd47f148d1860451ee26b8d87c63cac3c3d45886b4f86a7f989"],"state_sha256":"7c119477850be1341aa6f19e9330d8f241957dd346a37d7db22891ccc429a968"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8iZYm6fJSM4dz/HstgMQoI/v+OG4eecYHHLtLOyR4+NQYmSHMkKkCENib+6qcWRiSLo9/e0qZdFOqahH13NAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T00:23:26.873414Z","bundle_sha256":"1553b1e83e979dddacf1f1ab52e72f7ccb64966b53950733282fe9cf3cf88482"}}