{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XTTW42LBJMC4F3QS3AZBXSYC3G","short_pith_number":"pith:XTTW42LB","canonical_record":{"source":{"id":"2205.15301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-30T17:59:32Z","cross_cats_sorted":[],"title_canon_sha256":"8c6273cbac7408d0d8defc1fde82d2d5e70d2d94cf250dbfa47b235fa2cd2c12","abstract_canon_sha256":"5aadc7766784fdba879ef4f8caace62ce6d7c4fd61bccd3d33ad637542f59dbb"},"schema_version":"1.0"},"canonical_sha256":"bce76e69614b05c2ee12d8321bcb02d991d6a51896146687480043b3b975b769","source":{"kind":"arxiv","id":"2205.15301","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15301","created_at":"2026-07-05T04:27:26Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15301v1","created_at":"2026-07-05T04:27:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15301","created_at":"2026-07-05T04:27:26Z"},{"alias_kind":"pith_short_12","alias_value":"XTTW42LBJMC4","created_at":"2026-07-05T04:27:26Z"},{"alias_kind":"pith_short_16","alias_value":"XTTW42LBJMC4F3QS","created_at":"2026-07-05T04:27:26Z"},{"alias_kind":"pith_short_8","alias_value":"XTTW42LB","created_at":"2026-07-05T04:27:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XTTW42LBJMC4F3QS3AZBXSYC3G","target":"record","payload":{"canonical_record":{"source":{"id":"2205.15301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-30T17:59:32Z","cross_cats_sorted":[],"title_canon_sha256":"8c6273cbac7408d0d8defc1fde82d2d5e70d2d94cf250dbfa47b235fa2cd2c12","abstract_canon_sha256":"5aadc7766784fdba879ef4f8caace62ce6d7c4fd61bccd3d33ad637542f59dbb"},"schema_version":"1.0"},"canonical_sha256":"bce76e69614b05c2ee12d8321bcb02d991d6a51896146687480043b3b975b769","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:26.435585Z","signature_b64":"PGb5wBfudf+6/FMX1ZJNuW4SVxaTWn0rj5pD3SbfYZMJY/DSS0MV8EtNSMfTJ3zC+8iCkhf8LlKOwP1lomwRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bce76e69614b05c2ee12d8321bcb02d991d6a51896146687480043b3b975b769","last_reissued_at":"2026-07-05T04:27:26.435079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:26.435079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.15301","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":"2026-07-05T04:27:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TyZ/R22InCEg5nHBzIKm7MWNqTrYDFBXBCwHwJ92jBZWcyIPOZ3mWCCQNHB1uF7W5zYFMRk+GOlAtGY0WYY7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:07.272855Z"},"content_sha256":"687fb1aaeb74e08a6c17afa5991b4e56b72eb8a3da71b7919c5cc18523d296bb","schema_version":"1.0","event_id":"sha256:687fb1aaeb74e08a6c17afa5991b4e56b72eb8a3da71b7919c5cc18523d296bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XTTW42LBJMC4F3QS3AZBXSYC3G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christopher G. Lucas, Ivan Titov, Verna Dankers","submitted_at":"2022-05-30T17:59:32Z","abstract_excerpt":"Unlike literal expressions, idioms' meanings do not directly follow from their parts, posing a challenge for neural machine translation (NMT). NMT models are often unable to translate idioms accurately and over-generate compositional, literal translations. In this work, we investigate whether the non-compositionality of idioms is reflected in the mechanics of the dominant NMT model, Transformer, by analysing the hidden states and attention patterns for models with English as source language and one of seven European languages as target language. When Transformer emits a non-literal translation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15301","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/2205.15301/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":"2026-07-05T04:27:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hwgG3Oo5H9RImsQlAm2/BLWFshZ0f+1mDDHQpIwOOnrHVP4X3ofIEnI2BuybYg1SWSH3/u5hqzmOouIk7tO3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:07.273893Z"},"content_sha256":"c7aac2284dd17c820b60eb2484bbe4194933ad3c0852c25fb0d67b5308d3be3d","schema_version":"1.0","event_id":"sha256:c7aac2284dd17c820b60eb2484bbe4194933ad3c0852c25fb0d67b5308d3be3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XTTW42LBJMC4F3QS3AZBXSYC3G/bundle.json","state_url":"https://pith.science/pith/XTTW42LBJMC4F3QS3AZBXSYC3G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XTTW42LBJMC4F3QS3AZBXSYC3G/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":"2026-08-08T13:15:07Z","links":{"resolver":"https://pith.science/pith/XTTW42LBJMC4F3QS3AZBXSYC3G","bundle":"https://pith.science/pith/XTTW42LBJMC4F3QS3AZBXSYC3G/bundle.json","state":"https://pith.science/pith/XTTW42LBJMC4F3QS3AZBXSYC3G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XTTW42LBJMC4F3QS3AZBXSYC3G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XTTW42LBJMC4F3QS3AZBXSYC3G","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":"5aadc7766784fdba879ef4f8caace62ce6d7c4fd61bccd3d33ad637542f59dbb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-30T17:59:32Z","title_canon_sha256":"8c6273cbac7408d0d8defc1fde82d2d5e70d2d94cf250dbfa47b235fa2cd2c12"},"schema_version":"1.0","source":{"id":"2205.15301","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15301","created_at":"2026-07-05T04:27:26Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15301v1","created_at":"2026-07-05T04:27:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15301","created_at":"2026-07-05T04:27:26Z"},{"alias_kind":"pith_short_12","alias_value":"XTTW42LBJMC4","created_at":"2026-07-05T04:27:26Z"},{"alias_kind":"pith_short_16","alias_value":"XTTW42LBJMC4F3QS","created_at":"2026-07-05T04:27:26Z"},{"alias_kind":"pith_short_8","alias_value":"XTTW42LB","created_at":"2026-07-05T04:27:26Z"}],"graph_snapshots":[{"event_id":"sha256:c7aac2284dd17c820b60eb2484bbe4194933ad3c0852c25fb0d67b5308d3be3d","target":"graph","created_at":"2026-07-05T04:27:26Z","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/2205.15301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unlike literal expressions, idioms' meanings do not directly follow from their parts, posing a challenge for neural machine translation (NMT). NMT models are often unable to translate idioms accurately and over-generate compositional, literal translations. In this work, we investigate whether the non-compositionality of idioms is reflected in the mechanics of the dominant NMT model, Transformer, by analysing the hidden states and attention patterns for models with English as source language and one of seven European languages as target language. When Transformer emits a non-literal translation","authors_text":"Christopher G. Lucas, Ivan Titov, Verna Dankers","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-30T17:59:32Z","title":"Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15301","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":"sha256:687fb1aaeb74e08a6c17afa5991b4e56b72eb8a3da71b7919c5cc18523d296bb","target":"record","created_at":"2026-07-05T04:27:26Z","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":"5aadc7766784fdba879ef4f8caace62ce6d7c4fd61bccd3d33ad637542f59dbb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-30T17:59:32Z","title_canon_sha256":"8c6273cbac7408d0d8defc1fde82d2d5e70d2d94cf250dbfa47b235fa2cd2c12"},"schema_version":"1.0","source":{"id":"2205.15301","kind":"arxiv","version":1}},"canonical_sha256":"bce76e69614b05c2ee12d8321bcb02d991d6a51896146687480043b3b975b769","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bce76e69614b05c2ee12d8321bcb02d991d6a51896146687480043b3b975b769","first_computed_at":"2026-07-05T04:27:26.435079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:26.435079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PGb5wBfudf+6/FMX1ZJNuW4SVxaTWn0rj5pD3SbfYZMJY/DSS0MV8EtNSMfTJ3zC+8iCkhf8LlKOwP1lomwRAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:26.435585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15301","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:687fb1aaeb74e08a6c17afa5991b4e56b72eb8a3da71b7919c5cc18523d296bb","sha256:c7aac2284dd17c820b60eb2484bbe4194933ad3c0852c25fb0d67b5308d3be3d"],"state_sha256":"567f15b2f50e8400457279aa9c1ccbcbe93cec4017905fc422f944251223ba2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2JM6rabcrocQQl+M1JivIeH3C4UksZWr1B3PdeCKpr6uNPKNb0SCUQkgRhrjjlmSoKn1G8ICQNNjLmlVy/gLDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:15:07.279870Z","bundle_sha256":"c35f7813066dac65e4c1e2deb1c9a9db0701578ed2882d07598e01967a5bbf6a"}}