{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4HHVDS4VNYODZTMOW4G2BCT6TD","short_pith_number":"pith:4HHVDS4V","schema_version":"1.0","canonical_sha256":"e1cf51cb956e1c3ccd8eb70da08a7e98d72fb0192c6b671d3125eae9d1d0e766","source":{"kind":"arxiv","id":"2105.13466","version":1},"attestation_state":"computed","paper":{"title":"Semantic Frame Induction using Masked Word Embeddings and Two-Step Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Koichi Takeda, Kosuke Yamada, Ryohei Sasano","submitted_at":"2021-05-27T22:00:33Z","abstract_excerpt":"Recent studies on semantic frame induction show that relatively high performance has been achieved by using clustering-based methods with contextualized word embeddings. However, there are two potential drawbacks to these methods: one is that they focus too much on the superficial information of the frame-evoking verb and the other is that they tend to divide the instances of the same verb into too many different frame clusters. To overcome these drawbacks, we propose a semantic frame induction method using masked word embeddings and two-step clustering. Through experiments on the English Fram"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2105.13466","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-27T22:00:33Z","cross_cats_sorted":[],"title_canon_sha256":"078431cbe323347be8fd29d2835da611ccdf633bd85afbbac4868f9cf6f10055","abstract_canon_sha256":"7e1875239392e0217be6b3d166c7b89f3639b72a809e48b524e07aa814b5cfd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:08.303787Z","signature_b64":"mqwPZaDKgMy55MBMoNeV670eKiyud/fmMOYGdh1XRnSSZfDfNECkRfxuMAsWDppHbu4nAbmVfakBf9IKqkM1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1cf51cb956e1c3ccd8eb70da08a7e98d72fb0192c6b671d3125eae9d1d0e766","last_reissued_at":"2026-07-05T02:44:08.303368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:08.303368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Frame Induction using Masked Word Embeddings and Two-Step Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Koichi Takeda, Kosuke Yamada, Ryohei Sasano","submitted_at":"2021-05-27T22:00:33Z","abstract_excerpt":"Recent studies on semantic frame induction show that relatively high performance has been achieved by using clustering-based methods with contextualized word embeddings. However, there are two potential drawbacks to these methods: one is that they focus too much on the superficial information of the frame-evoking verb and the other is that they tend to divide the instances of the same verb into too many different frame clusters. To overcome these drawbacks, we propose a semantic frame induction method using masked word embeddings and two-step clustering. Through experiments on the English Fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13466","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/2105.13466/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2105.13466","created_at":"2026-07-05T02:44:08.303432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.13466v1","created_at":"2026-07-05T02:44:08.303432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13466","created_at":"2026-07-05T02:44:08.303432+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HHVDS4VNYOD","created_at":"2026-07-05T02:44:08.303432+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HHVDS4VNYODZTMO","created_at":"2026-07-05T02:44:08.303432+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HHVDS4V","created_at":"2026-07-05T02:44:08.303432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD","json":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD.json","graph_json":"https://pith.science/api/pith-number/4HHVDS4VNYODZTMOW4G2BCT6TD/graph.json","events_json":"https://pith.science/api/pith-number/4HHVDS4VNYODZTMOW4G2BCT6TD/events.json","paper":"https://pith.science/paper/4HHVDS4V"},"agent_actions":{"view_html":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD","download_json":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD.json","view_paper":"https://pith.science/paper/4HHVDS4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.13466&json=true","fetch_graph":"https://pith.science/api/pith-number/4HHVDS4VNYODZTMOW4G2BCT6TD/graph.json","fetch_events":"https://pith.science/api/pith-number/4HHVDS4VNYODZTMOW4G2BCT6TD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD/action/storage_attestation","attest_author":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD/action/author_attestation","sign_citation":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD/action/citation_signature","submit_replication":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD/action/replication_record"}},"created_at":"2026-07-05T02:44:08.303432+00:00","updated_at":"2026-07-05T02:44:08.303432+00:00"}