{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OL2FWTJ7HV25Q776KMN5CPNAAG","short_pith_number":"pith:OL2FWTJ7","canonical_record":{"source":{"id":"2505.06062","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T13:57:56Z","cross_cats_sorted":[],"title_canon_sha256":"2cc627be8ba527922c4ea4850534cc37a084fed569d188bcf8b9cfeb4e6abc9c","abstract_canon_sha256":"9d2ae72e2b6df7bcc8275a7bf2ae1a3845663b48eb5653eade4181444a7ee409"},"schema_version":"1.0"},"canonical_sha256":"72f45b4d3f3d75d87ffe531bd13da001baaa41e81cc9320e4a31f7238ca4bd33","source":{"kind":"arxiv","id":"2505.06062","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06062","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06062v1","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06062","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"pith_short_12","alias_value":"OL2FWTJ7HV25","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"pith_short_16","alias_value":"OL2FWTJ7HV25Q776","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"pith_short_8","alias_value":"OL2FWTJ7","created_at":"2026-07-05T11:00:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OL2FWTJ7HV25Q776KMN5CPNAAG","target":"record","payload":{"canonical_record":{"source":{"id":"2505.06062","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T13:57:56Z","cross_cats_sorted":[],"title_canon_sha256":"2cc627be8ba527922c4ea4850534cc37a084fed569d188bcf8b9cfeb4e6abc9c","abstract_canon_sha256":"9d2ae72e2b6df7bcc8275a7bf2ae1a3845663b48eb5653eade4181444a7ee409"},"schema_version":"1.0"},"canonical_sha256":"72f45b4d3f3d75d87ffe531bd13da001baaa41e81cc9320e4a31f7238ca4bd33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:53.298382Z","signature_b64":"XDkG/VNRwJ67+VNhaQDsgS1I8kgjRbjHgnA4dRredKI8+i3GecLNwkXZuXciaIP45QL2ZMj8uyXcpFOCZ3lgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72f45b4d3f3d75d87ffe531bd13da001baaa41e81cc9320e4a31f7238ca4bd33","last_reissued_at":"2026-07-05T11:00:53.297741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:53.297741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.06062","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":"2026-07-05T11:00:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SdqH6TfTJhYo6Cznul4kbjWWGr+B+llPdHaXKDpA4Vq2tMk0U92WrfqlJ74sfO023ZVUM5q2hufwtxjmFEjnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T08:30:31.886727Z"},"content_sha256":"1f7e5e37e76d51a4f2de7bc934155f42d9e844b5e2c25e99e4a91b4ffcf57cd7","schema_version":"1.0","event_id":"sha256:1f7e5e37e76d51a4f2de7bc934155f42d9e844b5e2c25e99e4a91b4ffcf57cd7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OL2FWTJ7HV25Q776KMN5CPNAAG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention on Multiword Expressions: A Multilingual Study of BERT-based Models with Regard to Idiomaticity and Microsyntax","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Badr M. Abdullah, Bernd M\\\"obius, Dietrich Klakow, Iuliia Zaitova, Tania Avgustinova, Vitalii Hirak","submitted_at":"2025-05-09T13:57:56Z","abstract_excerpt":"This study analyzes the attention patterns of fine-tuned encoder-only models based on the BERT architecture (BERT-based models) towards two distinct types of Multiword Expressions (MWEs): idioms and microsyntactic units (MSUs). Idioms present challenges in semantic non-compositionality, whereas MSUs demonstrate unconventional syntactic behavior that does not conform to standard grammatical categorizations. We aim to understand whether fine-tuning BERT-based models on specific tasks influences their attention to MWEs, and how this attention differs between semantic and syntactic tasks. We exami"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06062","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/2505.06062/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":"2026-07-05T11:00:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"plCCzj9Lq3lrzmBenkKDJ6kbXKpSssggDuoeIXwTGFTEJwCuzfnfgoB+qFD8P3kG8GxqJn0/K4Hr4VwFQ+6vBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T08:30:31.887090Z"},"content_sha256":"99c1029beebf1655fb33f75ea40177f415cd5d8b876f81193fdbd6300350b4a7","schema_version":"1.0","event_id":"sha256:99c1029beebf1655fb33f75ea40177f415cd5d8b876f81193fdbd6300350b4a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OL2FWTJ7HV25Q776KMN5CPNAAG/bundle.json","state_url":"https://pith.science/pith/OL2FWTJ7HV25Q776KMN5CPNAAG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OL2FWTJ7HV25Q776KMN5CPNAAG/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":"2026-08-20T08:30:31Z","links":{"resolver":"https://pith.science/pith/OL2FWTJ7HV25Q776KMN5CPNAAG","bundle":"https://pith.science/pith/OL2FWTJ7HV25Q776KMN5CPNAAG/bundle.json","state":"https://pith.science/pith/OL2FWTJ7HV25Q776KMN5CPNAAG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OL2FWTJ7HV25Q776KMN5CPNAAG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OL2FWTJ7HV25Q776KMN5CPNAAG","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":"9d2ae72e2b6df7bcc8275a7bf2ae1a3845663b48eb5653eade4181444a7ee409","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T13:57:56Z","title_canon_sha256":"2cc627be8ba527922c4ea4850534cc37a084fed569d188bcf8b9cfeb4e6abc9c"},"schema_version":"1.0","source":{"id":"2505.06062","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06062","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06062v1","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06062","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"pith_short_12","alias_value":"OL2FWTJ7HV25","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"pith_short_16","alias_value":"OL2FWTJ7HV25Q776","created_at":"2026-07-05T11:00:53Z"},{"alias_kind":"pith_short_8","alias_value":"OL2FWTJ7","created_at":"2026-07-05T11:00:53Z"}],"graph_snapshots":[{"event_id":"sha256:99c1029beebf1655fb33f75ea40177f415cd5d8b876f81193fdbd6300350b4a7","target":"graph","created_at":"2026-07-05T11:00:53Z","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/2505.06062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study analyzes the attention patterns of fine-tuned encoder-only models based on the BERT architecture (BERT-based models) towards two distinct types of Multiword Expressions (MWEs): idioms and microsyntactic units (MSUs). Idioms present challenges in semantic non-compositionality, whereas MSUs demonstrate unconventional syntactic behavior that does not conform to standard grammatical categorizations. We aim to understand whether fine-tuning BERT-based models on specific tasks influences their attention to MWEs, and how this attention differs between semantic and syntactic tasks. We exami","authors_text":"Badr M. Abdullah, Bernd M\\\"obius, Dietrich Klakow, Iuliia Zaitova, Tania Avgustinova, Vitalii Hirak","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T13:57:56Z","title":"Attention on Multiword Expressions: A Multilingual Study of BERT-based Models with Regard to Idiomaticity and Microsyntax"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06062","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":"sha256:1f7e5e37e76d51a4f2de7bc934155f42d9e844b5e2c25e99e4a91b4ffcf57cd7","target":"record","created_at":"2026-07-05T11:00:53Z","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":"9d2ae72e2b6df7bcc8275a7bf2ae1a3845663b48eb5653eade4181444a7ee409","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T13:57:56Z","title_canon_sha256":"2cc627be8ba527922c4ea4850534cc37a084fed569d188bcf8b9cfeb4e6abc9c"},"schema_version":"1.0","source":{"id":"2505.06062","kind":"arxiv","version":1}},"canonical_sha256":"72f45b4d3f3d75d87ffe531bd13da001baaa41e81cc9320e4a31f7238ca4bd33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72f45b4d3f3d75d87ffe531bd13da001baaa41e81cc9320e4a31f7238ca4bd33","first_computed_at":"2026-07-05T11:00:53.297741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:53.297741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XDkG/VNRwJ67+VNhaQDsgS1I8kgjRbjHgnA4dRredKI8+i3GecLNwkXZuXciaIP45QL2ZMj8uyXcpFOCZ3lgBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:53.298382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06062","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f7e5e37e76d51a4f2de7bc934155f42d9e844b5e2c25e99e4a91b4ffcf57cd7","sha256:99c1029beebf1655fb33f75ea40177f415cd5d8b876f81193fdbd6300350b4a7"],"state_sha256":"1c4088aa072440407772804c489ad06e8001c691e1c8d1e6d48309d33763922a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5FvkdM34BDClp1ly75MQz0d6g9rZZAAVFr10R/EtnkpoURi6fPYBspm8uqh60GtG/cAEms+WZmQ3GFKlmiyyAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T08:30:31.890192Z","bundle_sha256":"4f7b37127be1ec1042b855c59df5c88ec8f0d3589bd49c8551817b5b58985675"}}