{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JJSOY7JE7HLUDF7AESVEQBR7SI","short_pith_number":"pith:JJSOY7JE","canonical_record":{"source":{"id":"2109.04413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T16:53:17Z","cross_cats_sorted":[],"title_canon_sha256":"78d38e8ea6bc3285132d85441129d7f1a1291a3f23cc2e329548a23c602ae09d","abstract_canon_sha256":"7678874af6745761e8f291b803a76c34403b589f069d6dd483f5eb6c6417018b"},"schema_version":"1.0"},"canonical_sha256":"4a64ec7d24f9d74197e024aa48063f920b042653e1858c10530317b518193829","source":{"kind":"arxiv","id":"2109.04413","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04413","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04413v1","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04413","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"JJSOY7JE7HLU","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_16","alias_value":"JJSOY7JE7HLUDF7A","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_8","alias_value":"JJSOY7JE","created_at":"2026-07-05T03:12:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JJSOY7JE7HLUDF7AESVEQBR7SI","target":"record","payload":{"canonical_record":{"source":{"id":"2109.04413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T16:53:17Z","cross_cats_sorted":[],"title_canon_sha256":"78d38e8ea6bc3285132d85441129d7f1a1291a3f23cc2e329548a23c602ae09d","abstract_canon_sha256":"7678874af6745761e8f291b803a76c34403b589f069d6dd483f5eb6c6417018b"},"schema_version":"1.0"},"canonical_sha256":"4a64ec7d24f9d74197e024aa48063f920b042653e1858c10530317b518193829","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:58.235616Z","signature_b64":"c8rwr5Six3QjIIRaEB5S7NFrXEs7q2OPlIDtVhZa7CSgCkrWxyLLlDqETRToxjauviYM+Ix/sYjGNBph2F4iCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a64ec7d24f9d74197e024aa48063f920b042653e1858c10530317b518193829","last_reissued_at":"2026-07-05T03:12:58.235083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:58.235083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.04413","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":"2026-07-05T03:12:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xoaBI1stwHbDzD9im/93ieLIq16NcewSYeNAW5R9XvcY6/dsi9k+anGMb7JzyVnqnwApLwEuJmY7uxqu0R9LDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:10:52.958869Z"},"content_sha256":"a6c4149407e2ee4ba2c55cc1b57cd67e8ba268db7b8be4b7452f4faae7588625","schema_version":"1.0","event_id":"sha256:a6c4149407e2ee4ba2c55cc1b57cd67e8ba268db7b8be4b7452f4faae7588625"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JJSOY7JE7HLUDF7AESVEQBR7SI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aline Villavicencio, Carolina Scarton, Edward Gow-Smith, Harish Tayyar Madabushi","submitted_at":"2021-09-09T16:53:17Z","abstract_excerpt":"Despite their success in a variety of NLP tasks, pre-trained language models, due to their heavy reliance on compositionality, fail in effectively capturing the meanings of multiword expressions (MWEs), especially idioms. Therefore, datasets and methods to improve the representation of MWEs are urgently needed. Existing datasets are limited to providing the degree of idiomaticity of expressions along with the literal and, where applicable, (a single) non-literal interpretation of MWEs. This work presents a novel dataset of naturally occurring sentences containing MWEs manually classified into "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04413","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/2109.04413/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":"2026-07-05T03:12:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xh2qWYUD8lGax20wO0h9ye8+L8NqWIGprCmlqKvjfI/l6/3hvwLEVDdpnCE283BAJvZM+GmTatfI7AuAkEh9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:10:52.959705Z"},"content_sha256":"8f8c660df7ae95e709b22e99639da046efed787480e6565d76d2321655f39647","schema_version":"1.0","event_id":"sha256:8f8c660df7ae95e709b22e99639da046efed787480e6565d76d2321655f39647"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JJSOY7JE7HLUDF7AESVEQBR7SI/bundle.json","state_url":"https://pith.science/pith/JJSOY7JE7HLUDF7AESVEQBR7SI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JJSOY7JE7HLUDF7AESVEQBR7SI/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":"2026-08-19T10:10:52Z","links":{"resolver":"https://pith.science/pith/JJSOY7JE7HLUDF7AESVEQBR7SI","bundle":"https://pith.science/pith/JJSOY7JE7HLUDF7AESVEQBR7SI/bundle.json","state":"https://pith.science/pith/JJSOY7JE7HLUDF7AESVEQBR7SI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JJSOY7JE7HLUDF7AESVEQBR7SI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JJSOY7JE7HLUDF7AESVEQBR7SI","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":"7678874af6745761e8f291b803a76c34403b589f069d6dd483f5eb6c6417018b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T16:53:17Z","title_canon_sha256":"78d38e8ea6bc3285132d85441129d7f1a1291a3f23cc2e329548a23c602ae09d"},"schema_version":"1.0","source":{"id":"2109.04413","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04413","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04413v1","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04413","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"JJSOY7JE7HLU","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_16","alias_value":"JJSOY7JE7HLUDF7A","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_8","alias_value":"JJSOY7JE","created_at":"2026-07-05T03:12:58Z"}],"graph_snapshots":[{"event_id":"sha256:8f8c660df7ae95e709b22e99639da046efed787480e6565d76d2321655f39647","target":"graph","created_at":"2026-07-05T03:12:58Z","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/2109.04413/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite their success in a variety of NLP tasks, pre-trained language models, due to their heavy reliance on compositionality, fail in effectively capturing the meanings of multiword expressions (MWEs), especially idioms. Therefore, datasets and methods to improve the representation of MWEs are urgently needed. Existing datasets are limited to providing the degree of idiomaticity of expressions along with the literal and, where applicable, (a single) non-literal interpretation of MWEs. This work presents a novel dataset of naturally occurring sentences containing MWEs manually classified into ","authors_text":"Aline Villavicencio, Carolina Scarton, Edward Gow-Smith, Harish Tayyar Madabushi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T16:53:17Z","title":"AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04413","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:a6c4149407e2ee4ba2c55cc1b57cd67e8ba268db7b8be4b7452f4faae7588625","target":"record","created_at":"2026-07-05T03:12:58Z","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":"7678874af6745761e8f291b803a76c34403b589f069d6dd483f5eb6c6417018b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T16:53:17Z","title_canon_sha256":"78d38e8ea6bc3285132d85441129d7f1a1291a3f23cc2e329548a23c602ae09d"},"schema_version":"1.0","source":{"id":"2109.04413","kind":"arxiv","version":1}},"canonical_sha256":"4a64ec7d24f9d74197e024aa48063f920b042653e1858c10530317b518193829","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a64ec7d24f9d74197e024aa48063f920b042653e1858c10530317b518193829","first_computed_at":"2026-07-05T03:12:58.235083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:12:58.235083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c8rwr5Six3QjIIRaEB5S7NFrXEs7q2OPlIDtVhZa7CSgCkrWxyLLlDqETRToxjauviYM+Ix/sYjGNBph2F4iCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:12:58.235616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.04413","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6c4149407e2ee4ba2c55cc1b57cd67e8ba268db7b8be4b7452f4faae7588625","sha256:8f8c660df7ae95e709b22e99639da046efed787480e6565d76d2321655f39647"],"state_sha256":"9f59927849c93639d1c1f79dc8fef338121bf2e5a3d2992fd3dddacbc8c11786"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NKqNHPjSD8wAhlJul5z9rnLWrwwmA722fGVkhdF1wI6EbHVtw4oVnzEUe/pmcGoN/hZf9elRp/Q4t02suyftCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T10:10:52.964095Z","bundle_sha256":"a5c740c7ac1703a2ecf90b26ccb1b8fdc0124cddddb750de3c99b6046cefd864"}}