{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KTJYRP6OZYF7LX35VW3DASKGKI","short_pith_number":"pith:KTJYRP6O","canonical_record":{"source":{"id":"2211.13376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-24T02:05:47Z","cross_cats_sorted":[],"title_canon_sha256":"90b42836b521a696581d17572f00ff4680102ba478ccdbfbb04c9c43b5676297","abstract_canon_sha256":"9ff2aff6e36c6e817774d8ec340e6ae795adad72ba278b7a622f25dd94486011"},"schema_version":"1.0"},"canonical_sha256":"54d388bfcece0bf5df7dadb6304946522cd993cb2b10ea4d7311e3b8d254a6f8","source":{"kind":"arxiv","id":"2211.13376","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.13376","created_at":"2026-07-05T05:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"2211.13376v1","created_at":"2026-07-05T05:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13376","created_at":"2026-07-05T05:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"KTJYRP6OZYF7","created_at":"2026-07-05T05:19:02Z"},{"alias_kind":"pith_short_16","alias_value":"KTJYRP6OZYF7LX35","created_at":"2026-07-05T05:19:02Z"},{"alias_kind":"pith_short_8","alias_value":"KTJYRP6O","created_at":"2026-07-05T05:19:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KTJYRP6OZYF7LX35VW3DASKGKI","target":"record","payload":{"canonical_record":{"source":{"id":"2211.13376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-24T02:05:47Z","cross_cats_sorted":[],"title_canon_sha256":"90b42836b521a696581d17572f00ff4680102ba478ccdbfbb04c9c43b5676297","abstract_canon_sha256":"9ff2aff6e36c6e817774d8ec340e6ae795adad72ba278b7a622f25dd94486011"},"schema_version":"1.0"},"canonical_sha256":"54d388bfcece0bf5df7dadb6304946522cd993cb2b10ea4d7311e3b8d254a6f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:02.935196Z","signature_b64":"zeIeEgxs21dZkXpUSwvw2cPPPUnowRfo6QYl/s+6zXLo3UmZwa+bc/RdEbrQcN5+Gm3ajsfwRJrIUN8Xdo9NBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d388bfcece0bf5df7dadb6304946522cd993cb2b10ea4d7311e3b8d254a6f8","last_reissued_at":"2026-07-05T05:19:02.934797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:02.934797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.13376","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":"2026-07-05T05:19:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2843BKMrDIcmWwB4/+wnGN2s5oNYWPXDRAR+4PqHOfV0s5S3X71sLmdf/LB+BzgOOHDmHSnWHzQ78nH0golLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:28:18.863120Z"},"content_sha256":"bc48573f42916727270e7e03a9e77377380a10fb4c9fca3fbe9f3aa0826d0646","schema_version":"1.0","event_id":"sha256:bc48573f42916727270e7e03a9e77377380a10fb4c9fca3fbe9f3aa0826d0646"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KTJYRP6OZYF7LX35VW3DASKGKI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InDEX: Indonesian Idiom and Expression Dataset for Cloze Test","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guofeng Shi, Xinying Qiu","submitted_at":"2022-11-24T02:05:47Z","abstract_excerpt":"We propose InDEX, an Indonesian Idiom and Expression dataset for cloze test. The dataset contains 10438 unique sentences for 289 idioms and expressions for which we generate 15 different types of distractors, resulting in a large cloze-style corpus. Many baseline models of cloze test reading comprehension apply BERT with random initialization to learn embedding representation. But idioms and fixed expressions are different such that the literal meaning of the phrases may or may not be consistent with their contextual meaning. Therefore, we explore different ways to combine static and contextua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13376","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/2211.13376/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":"2026-07-05T05:19:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PFtwMVGXc8/IcCrltu0jfTP9exYW+RMDqvZj9Ky812HK2rCg+HmjyEqfDfBvwJ7MHUgT5Hfezh1HynrJ8LqKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:28:18.863983Z"},"content_sha256":"a085e71994aa13bf72793bd8e3ea1880f64f42dd75d714d03d40f4fffb9eef6d","schema_version":"1.0","event_id":"sha256:a085e71994aa13bf72793bd8e3ea1880f64f42dd75d714d03d40f4fffb9eef6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KTJYRP6OZYF7LX35VW3DASKGKI/bundle.json","state_url":"https://pith.science/pith/KTJYRP6OZYF7LX35VW3DASKGKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KTJYRP6OZYF7LX35VW3DASKGKI/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":"2026-08-03T19:28:18Z","links":{"resolver":"https://pith.science/pith/KTJYRP6OZYF7LX35VW3DASKGKI","bundle":"https://pith.science/pith/KTJYRP6OZYF7LX35VW3DASKGKI/bundle.json","state":"https://pith.science/pith/KTJYRP6OZYF7LX35VW3DASKGKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KTJYRP6OZYF7LX35VW3DASKGKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KTJYRP6OZYF7LX35VW3DASKGKI","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":"9ff2aff6e36c6e817774d8ec340e6ae795adad72ba278b7a622f25dd94486011","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-24T02:05:47Z","title_canon_sha256":"90b42836b521a696581d17572f00ff4680102ba478ccdbfbb04c9c43b5676297"},"schema_version":"1.0","source":{"id":"2211.13376","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.13376","created_at":"2026-07-05T05:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"2211.13376v1","created_at":"2026-07-05T05:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13376","created_at":"2026-07-05T05:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"KTJYRP6OZYF7","created_at":"2026-07-05T05:19:02Z"},{"alias_kind":"pith_short_16","alias_value":"KTJYRP6OZYF7LX35","created_at":"2026-07-05T05:19:02Z"},{"alias_kind":"pith_short_8","alias_value":"KTJYRP6O","created_at":"2026-07-05T05:19:02Z"}],"graph_snapshots":[{"event_id":"sha256:a085e71994aa13bf72793bd8e3ea1880f64f42dd75d714d03d40f4fffb9eef6d","target":"graph","created_at":"2026-07-05T05:19:02Z","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/2211.13376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose InDEX, an Indonesian Idiom and Expression dataset for cloze test. The dataset contains 10438 unique sentences for 289 idioms and expressions for which we generate 15 different types of distractors, resulting in a large cloze-style corpus. Many baseline models of cloze test reading comprehension apply BERT with random initialization to learn embedding representation. But idioms and fixed expressions are different such that the literal meaning of the phrases may or may not be consistent with their contextual meaning. Therefore, we explore different ways to combine static and contextua","authors_text":"Guofeng Shi, Xinying Qiu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-24T02:05:47Z","title":"InDEX: Indonesian Idiom and Expression Dataset for Cloze Test"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13376","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:bc48573f42916727270e7e03a9e77377380a10fb4c9fca3fbe9f3aa0826d0646","target":"record","created_at":"2026-07-05T05:19:02Z","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":"9ff2aff6e36c6e817774d8ec340e6ae795adad72ba278b7a622f25dd94486011","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-24T02:05:47Z","title_canon_sha256":"90b42836b521a696581d17572f00ff4680102ba478ccdbfbb04c9c43b5676297"},"schema_version":"1.0","source":{"id":"2211.13376","kind":"arxiv","version":1}},"canonical_sha256":"54d388bfcece0bf5df7dadb6304946522cd993cb2b10ea4d7311e3b8d254a6f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54d388bfcece0bf5df7dadb6304946522cd993cb2b10ea4d7311e3b8d254a6f8","first_computed_at":"2026-07-05T05:19:02.934797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:02.934797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zeIeEgxs21dZkXpUSwvw2cPPPUnowRfo6QYl/s+6zXLo3UmZwa+bc/RdEbrQcN5+Gm3ajsfwRJrIUN8Xdo9NBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:02.935196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.13376","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc48573f42916727270e7e03a9e77377380a10fb4c9fca3fbe9f3aa0826d0646","sha256:a085e71994aa13bf72793bd8e3ea1880f64f42dd75d714d03d40f4fffb9eef6d"],"state_sha256":"295261de5e5a0b6ae0cbb74eb145dc64d8049c0bc57073e5f542d7c0c9bb01c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ECDsJGcLusZGxC+0fkC9lfEXpa1cs/aY7liJVD3d3PYLpbLIn72U7KF5BLrUFGl88e/h83EwfcmB1t3VMWM2Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:28:18.871161Z","bundle_sha256":"b5594ac9238b5942406603fef64347a64a24b4670330411ba78237a8ee5de84b"}}