{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WK7JW3OSKW7VC7H3OIDYTIG6R3","short_pith_number":"pith:WK7JW3OS","canonical_record":{"source":{"id":"2105.03280","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-25T13:05:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"343ea9190ec76368fb65bb5a3f89f8ec536f96320f723980001a4c8911b5298a","abstract_canon_sha256":"4c3c073bdfe343c091a0d7f6a8be33345951c4e6c531fd12237282d1610784d2"},"schema_version":"1.0"},"canonical_sha256":"b2be9b6dd255bf517cfb720789a0de8ee772d5d1979c0d467559c37c67c1c9a3","source":{"kind":"arxiv","id":"2105.03280","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.03280","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"arxiv_version","alias_value":"2105.03280v2","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03280","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"pith_short_12","alias_value":"WK7JW3OSKW7V","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"pith_short_16","alias_value":"WK7JW3OSKW7VC7H3","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"pith_short_8","alias_value":"WK7JW3OS","created_at":"2026-07-05T04:17:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WK7JW3OSKW7VC7H3OIDYTIG6R3","target":"record","payload":{"canonical_record":{"source":{"id":"2105.03280","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-25T13:05:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"343ea9190ec76368fb65bb5a3f89f8ec536f96320f723980001a4c8911b5298a","abstract_canon_sha256":"4c3c073bdfe343c091a0d7f6a8be33345951c4e6c531fd12237282d1610784d2"},"schema_version":"1.0"},"canonical_sha256":"b2be9b6dd255bf517cfb720789a0de8ee772d5d1979c0d467559c37c67c1c9a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:02.816328Z","signature_b64":"Zc9eXUns7hekJWGKNFxc1r7akBTuMxRUOte8nIoSd3HyNu4AN+Z6QZLSLedIfBq9c6f0DDFCvLYxkyorIkHTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2be9b6dd255bf517cfb720789a0de8ee772d5d1979c0d467559c37c67c1c9a3","last_reissued_at":"2026-07-05T04:17:02.815952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:02.815952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.03280","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":"2026-07-05T04:17:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lEE4KS2MZZjVYs7y1y7Eb22NA6Dcdz4Bsqcax9TmfsMG/V3tEdWQMgby87XjjVvEzzRE9NteBoSMPc0/NrQvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:06:53.267718Z"},"content_sha256":"c731c34dcf6c7f050c502620bd83980fb0917a505101f97bb29261111060851a","schema_version":"1.0","event_id":"sha256:c731c34dcf6c7f050c502620bd83980fb0917a505101f97bb29261111060851a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WK7JW3OSKW7VC7H3OIDYTIG6R3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idioms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aparajita Tripathy, Foteini Liwicki, Konstantina Nikolaidou, Marcus Liwicki, Roshanak Vadoodi, Tosin P. Adewumi","submitted_at":"2021-04-25T13:05:29Z","abstract_excerpt":"We present a fairly large, Potential Idiomatic Expression (PIE) dataset for Natural Language Processing (NLP) in English. The challenges with NLP systems with regards to tasks such as Machine Translation (MT), word sense disambiguation (WSD) and information retrieval make it imperative to have a labelled idioms dataset with classes such as it is in this work. To the best of the authors' knowledge, this is the first idioms corpus with classes of idioms beyond the literal and the general idioms classification. In particular, the following classes are labelled in the dataset: metaphor, simile, eu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03280","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/2105.03280/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":"2026-07-05T04:17:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eRQ5kW9cqowBq8IyDODknPGx6/Ea9rMFMUa6sQCCWRD+bdlH8vVBWi2DrTsuf4su6ta573D2dRTIQXEhTqORAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:06:53.268267Z"},"content_sha256":"a38900614c57a388ef9b32b773407c34ddf6ed929290eb5046e624e49459b6f0","schema_version":"1.0","event_id":"sha256:a38900614c57a388ef9b32b773407c34ddf6ed929290eb5046e624e49459b6f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WK7JW3OSKW7VC7H3OIDYTIG6R3/bundle.json","state_url":"https://pith.science/pith/WK7JW3OSKW7VC7H3OIDYTIG6R3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WK7JW3OSKW7VC7H3OIDYTIG6R3/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":"2026-08-13T16:06:53Z","links":{"resolver":"https://pith.science/pith/WK7JW3OSKW7VC7H3OIDYTIG6R3","bundle":"https://pith.science/pith/WK7JW3OSKW7VC7H3OIDYTIG6R3/bundle.json","state":"https://pith.science/pith/WK7JW3OSKW7VC7H3OIDYTIG6R3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WK7JW3OSKW7VC7H3OIDYTIG6R3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WK7JW3OSKW7VC7H3OIDYTIG6R3","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":"4c3c073bdfe343c091a0d7f6a8be33345951c4e6c531fd12237282d1610784d2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-25T13:05:29Z","title_canon_sha256":"343ea9190ec76368fb65bb5a3f89f8ec536f96320f723980001a4c8911b5298a"},"schema_version":"1.0","source":{"id":"2105.03280","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.03280","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"arxiv_version","alias_value":"2105.03280v2","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03280","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"pith_short_12","alias_value":"WK7JW3OSKW7V","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"pith_short_16","alias_value":"WK7JW3OSKW7VC7H3","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"pith_short_8","alias_value":"WK7JW3OS","created_at":"2026-07-05T04:17:02Z"}],"graph_snapshots":[{"event_id":"sha256:a38900614c57a388ef9b32b773407c34ddf6ed929290eb5046e624e49459b6f0","target":"graph","created_at":"2026-07-05T04:17:02Z","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/2105.03280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a fairly large, Potential Idiomatic Expression (PIE) dataset for Natural Language Processing (NLP) in English. The challenges with NLP systems with regards to tasks such as Machine Translation (MT), word sense disambiguation (WSD) and information retrieval make it imperative to have a labelled idioms dataset with classes such as it is in this work. To the best of the authors' knowledge, this is the first idioms corpus with classes of idioms beyond the literal and the general idioms classification. In particular, the following classes are labelled in the dataset: metaphor, simile, eu","authors_text":"Aparajita Tripathy, Foteini Liwicki, Konstantina Nikolaidou, Marcus Liwicki, Roshanak Vadoodi, Tosin P. Adewumi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-25T13:05:29Z","title":"Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idioms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03280","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:c731c34dcf6c7f050c502620bd83980fb0917a505101f97bb29261111060851a","target":"record","created_at":"2026-07-05T04:17:02Z","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":"4c3c073bdfe343c091a0d7f6a8be33345951c4e6c531fd12237282d1610784d2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-25T13:05:29Z","title_canon_sha256":"343ea9190ec76368fb65bb5a3f89f8ec536f96320f723980001a4c8911b5298a"},"schema_version":"1.0","source":{"id":"2105.03280","kind":"arxiv","version":2}},"canonical_sha256":"b2be9b6dd255bf517cfb720789a0de8ee772d5d1979c0d467559c37c67c1c9a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2be9b6dd255bf517cfb720789a0de8ee772d5d1979c0d467559c37c67c1c9a3","first_computed_at":"2026-07-05T04:17:02.815952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:02.815952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zc9eXUns7hekJWGKNFxc1r7akBTuMxRUOte8nIoSd3HyNu4AN+Z6QZLSLedIfBq9c6f0DDFCvLYxkyorIkHTCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:02.816328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.03280","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c731c34dcf6c7f050c502620bd83980fb0917a505101f97bb29261111060851a","sha256:a38900614c57a388ef9b32b773407c34ddf6ed929290eb5046e624e49459b6f0"],"state_sha256":"620990322d10e9152514f983811b15037695ef463e0cd3f298614c3167dc8825"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kobZyyiYrs4N52qj6E+O0gYhTg+kkZRW/pXBU+k9HPX1k7tB3BUpieCVFmjD24q95a1S3Ap1jbY17qC9Yo1uBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T16:06:53.272814Z","bundle_sha256":"0f634792cd34194d482e1efc827cd933d165911b46d9882090301b703bac86cd"}}