{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RWMLBZXWHU5MHFXSBLAPN4LD6Y","short_pith_number":"pith:RWMLBZXW","canonical_record":{"source":{"id":"2008.05759","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-13T08:56:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"def646c322a77e9f301f3ec9acd2e875a423287fd41b5302513bb02f5197fbbf","abstract_canon_sha256":"ba1126153d1ac83f115287cbcea30bd324440b2b370632f81249b3058173a462"},"schema_version":"1.0"},"canonical_sha256":"8d98b0e6f63d3ac396f20ac0f6f163f616a519dc3bc43ef9ebf6bb5793c25945","source":{"kind":"arxiv","id":"2008.05759","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.05759","created_at":"2026-07-05T03:30:37Z"},{"alias_kind":"arxiv_version","alias_value":"2008.05759v2","created_at":"2026-07-05T03:30:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05759","created_at":"2026-07-05T03:30:37Z"},{"alias_kind":"pith_short_12","alias_value":"RWMLBZXWHU5M","created_at":"2026-07-05T03:30:37Z"},{"alias_kind":"pith_short_16","alias_value":"RWMLBZXWHU5MHFXS","created_at":"2026-07-05T03:30:37Z"},{"alias_kind":"pith_short_8","alias_value":"RWMLBZXW","created_at":"2026-07-05T03:30:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RWMLBZXWHU5MHFXSBLAPN4LD6Y","target":"record","payload":{"canonical_record":{"source":{"id":"2008.05759","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-13T08:56:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"def646c322a77e9f301f3ec9acd2e875a423287fd41b5302513bb02f5197fbbf","abstract_canon_sha256":"ba1126153d1ac83f115287cbcea30bd324440b2b370632f81249b3058173a462"},"schema_version":"1.0"},"canonical_sha256":"8d98b0e6f63d3ac396f20ac0f6f163f616a519dc3bc43ef9ebf6bb5793c25945","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:37.375432Z","signature_b64":"lUXvlZuJ5dklm+dFl/+HKBt0OLFZ3N1/2X5hgbzo93b8xjE3bnX7eQ6cg2leaa5QsUjt5SJq84pXnmGxuqAUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d98b0e6f63d3ac396f20ac0f6f163f616a519dc3bc43ef9ebf6bb5793c25945","last_reissued_at":"2026-07-05T03:30:37.374957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:37.374957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.05759","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":"2026-07-05T03:30:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/juKSFKm1IX8rBJSdgvX+GMxUebWmwVqYVnOVGLPTFIfK/2drXyJVypbuMDVj883hvw877ZMaGNV7ntArwQyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:24:00.345796Z"},"content_sha256":"1a0aeeed69daccacceb65c04e50828a60939d2a7786ef4a161b9520ddddb02a0","schema_version":"1.0","event_id":"sha256:1a0aeeed69daccacceb65c04e50828a60939d2a7786ef4a161b9520ddddb02a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RWMLBZXWHU5MHFXSBLAPN4LD6Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MICE: Mining Idioms with Contextual Embeddings","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Marko Robnik-\\v{S}ikonja, Polona Gantar, Tadej \\v{S}kvorc","submitted_at":"2020-08-13T08:56:40Z","abstract_excerpt":"Idiomatic expressions can be problematic for natural language processing applications as their meaning cannot be inferred from their constituting words. A lack of successful methodological approaches and sufficiently large datasets prevents the development of machine learning approaches for detecting idioms, especially for expressions that do not occur in the training set. We present an approach, called MICE, that uses contextual embeddings for that purpose. We present a new dataset of multi-word expressions with literal and idiomatic meanings and use it to train a classifier based on two stat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05759","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/2008.05759/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":"2026-07-05T03:30:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A4K1NIDkZnLjnaVUlEvUsViTO3KRwC6awIHQEuWJH1Xx81HN/9CY83ezh4R/ryIBbiMxK57bh1SfbanARUY/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:24:00.346178Z"},"content_sha256":"c6ed006a7a5b6329d2ede4b279829fbf179feb9b4873b475d75c2dd423ef1d0d","schema_version":"1.0","event_id":"sha256:c6ed006a7a5b6329d2ede4b279829fbf179feb9b4873b475d75c2dd423ef1d0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RWMLBZXWHU5MHFXSBLAPN4LD6Y/bundle.json","state_url":"https://pith.science/pith/RWMLBZXWHU5MHFXSBLAPN4LD6Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RWMLBZXWHU5MHFXSBLAPN4LD6Y/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":"2026-07-06T15:24:00Z","links":{"resolver":"https://pith.science/pith/RWMLBZXWHU5MHFXSBLAPN4LD6Y","bundle":"https://pith.science/pith/RWMLBZXWHU5MHFXSBLAPN4LD6Y/bundle.json","state":"https://pith.science/pith/RWMLBZXWHU5MHFXSBLAPN4LD6Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RWMLBZXWHU5MHFXSBLAPN4LD6Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RWMLBZXWHU5MHFXSBLAPN4LD6Y","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":"ba1126153d1ac83f115287cbcea30bd324440b2b370632f81249b3058173a462","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-13T08:56:40Z","title_canon_sha256":"def646c322a77e9f301f3ec9acd2e875a423287fd41b5302513bb02f5197fbbf"},"schema_version":"1.0","source":{"id":"2008.05759","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.05759","created_at":"2026-07-05T03:30:37Z"},{"alias_kind":"arxiv_version","alias_value":"2008.05759v2","created_at":"2026-07-05T03:30:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05759","created_at":"2026-07-05T03:30:37Z"},{"alias_kind":"pith_short_12","alias_value":"RWMLBZXWHU5M","created_at":"2026-07-05T03:30:37Z"},{"alias_kind":"pith_short_16","alias_value":"RWMLBZXWHU5MHFXS","created_at":"2026-07-05T03:30:37Z"},{"alias_kind":"pith_short_8","alias_value":"RWMLBZXW","created_at":"2026-07-05T03:30:37Z"}],"graph_snapshots":[{"event_id":"sha256:c6ed006a7a5b6329d2ede4b279829fbf179feb9b4873b475d75c2dd423ef1d0d","target":"graph","created_at":"2026-07-05T03:30:37Z","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/2008.05759/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Idiomatic expressions can be problematic for natural language processing applications as their meaning cannot be inferred from their constituting words. A lack of successful methodological approaches and sufficiently large datasets prevents the development of machine learning approaches for detecting idioms, especially for expressions that do not occur in the training set. We present an approach, called MICE, that uses contextual embeddings for that purpose. We present a new dataset of multi-word expressions with literal and idiomatic meanings and use it to train a classifier based on two stat","authors_text":"Marko Robnik-\\v{S}ikonja, Polona Gantar, Tadej \\v{S}kvorc","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-13T08:56:40Z","title":"MICE: Mining Idioms with Contextual Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05759","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":"sha256:1a0aeeed69daccacceb65c04e50828a60939d2a7786ef4a161b9520ddddb02a0","target":"record","created_at":"2026-07-05T03:30:37Z","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":"ba1126153d1ac83f115287cbcea30bd324440b2b370632f81249b3058173a462","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-13T08:56:40Z","title_canon_sha256":"def646c322a77e9f301f3ec9acd2e875a423287fd41b5302513bb02f5197fbbf"},"schema_version":"1.0","source":{"id":"2008.05759","kind":"arxiv","version":2}},"canonical_sha256":"8d98b0e6f63d3ac396f20ac0f6f163f616a519dc3bc43ef9ebf6bb5793c25945","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d98b0e6f63d3ac396f20ac0f6f163f616a519dc3bc43ef9ebf6bb5793c25945","first_computed_at":"2026-07-05T03:30:37.374957Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:30:37.374957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lUXvlZuJ5dklm+dFl/+HKBt0OLFZ3N1/2X5hgbzo93b8xjE3bnX7eQ6cg2leaa5QsUjt5SJq84pXnmGxuqAUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:30:37.375432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.05759","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a0aeeed69daccacceb65c04e50828a60939d2a7786ef4a161b9520ddddb02a0","sha256:c6ed006a7a5b6329d2ede4b279829fbf179feb9b4873b475d75c2dd423ef1d0d"],"state_sha256":"39db905a8fc5e2758bc0c0033500b6f6c6709877b82fc3b264048919f8e42cfe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0kcalvZdj5w2ls0WRfiDLgNi/zA+0lYOrLQa9jVQbx6tn+AD1JDAzRtx462RSz2skvx13Q5SYNEVeCUEGm/lCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:24:00.348125Z","bundle_sha256":"eea153d7b6b32e75e7bcf830a84dd17fa97ec5d3146788299f8fc74f6f0a6897"}}