{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4HHVDS4VNYODZTMOW4G2BCT6TD","short_pith_number":"pith:4HHVDS4V","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"},"canonical_sha256":"e1cf51cb956e1c3ccd8eb70da08a7e98d72fb0192c6b671d3125eae9d1d0e766","source":{"kind":"arxiv","id":"2105.13466","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.13466","created_at":"2026-07-05T02:44:08Z"},{"alias_kind":"arxiv_version","alias_value":"2105.13466v1","created_at":"2026-07-05T02:44:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13466","created_at":"2026-07-05T02:44:08Z"},{"alias_kind":"pith_short_12","alias_value":"4HHVDS4VNYOD","created_at":"2026-07-05T02:44:08Z"},{"alias_kind":"pith_short_16","alias_value":"4HHVDS4VNYODZTMO","created_at":"2026-07-05T02:44:08Z"},{"alias_kind":"pith_short_8","alias_value":"4HHVDS4V","created_at":"2026-07-05T02:44:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4HHVDS4VNYODZTMOW4G2BCT6TD","target":"record","payload":{"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"},"canonical_sha256":"e1cf51cb956e1c3ccd8eb70da08a7e98d72fb0192c6b671d3125eae9d1d0e766","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"},"source_kind":"arxiv","source_id":"2105.13466","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":"2026-07-05T02:44:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tJZfMFc4DcZlWDhDDyDWG8SSg4cCDOwJG0jfRzFbt0LCOdmNBgKWK9jIc+J97cYYRVFF8QsdMFKEoUzclQRRDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T06:46:00.209977Z"},"content_sha256":"0f5077414fb56d75ba353e4e9192078876f843f12054d146b9298b28b9089b5c","schema_version":"1.0","event_id":"sha256:0f5077414fb56d75ba353e4e9192078876f843f12054d146b9298b28b9089b5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4HHVDS4VNYODZTMOW4G2BCT6TD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:44:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/2ouF7et1DdDKn5nLxw94QHD8/igOAh+EvkL22mKxLmKg93bcYYhXm2Hg9YkaPfKnpw0M6y3jLh2iCQvwuCUDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T06:46:00.210355Z"},"content_sha256":"5bee899d45cb5dccca2d10f1d2bf1f31f2436e71bf35f429af4e191e5ddebb52","schema_version":"1.0","event_id":"sha256:5bee899d45cb5dccca2d10f1d2bf1f31f2436e71bf35f429af4e191e5ddebb52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD/bundle.json","state_url":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4HHVDS4VNYODZTMOW4G2BCT6TD/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":"2026-07-19T06:46:00Z","links":{"resolver":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD","bundle":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD/bundle.json","state":"https://pith.science/pith/4HHVDS4VNYODZTMOW4G2BCT6TD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4HHVDS4VNYODZTMOW4G2BCT6TD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4HHVDS4VNYODZTMOW4G2BCT6TD","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":"7e1875239392e0217be6b3d166c7b89f3639b72a809e48b524e07aa814b5cfd2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-27T22:00:33Z","title_canon_sha256":"078431cbe323347be8fd29d2835da611ccdf633bd85afbbac4868f9cf6f10055"},"schema_version":"1.0","source":{"id":"2105.13466","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.13466","created_at":"2026-07-05T02:44:08Z"},{"alias_kind":"arxiv_version","alias_value":"2105.13466v1","created_at":"2026-07-05T02:44:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13466","created_at":"2026-07-05T02:44:08Z"},{"alias_kind":"pith_short_12","alias_value":"4HHVDS4VNYOD","created_at":"2026-07-05T02:44:08Z"},{"alias_kind":"pith_short_16","alias_value":"4HHVDS4VNYODZTMO","created_at":"2026-07-05T02:44:08Z"},{"alias_kind":"pith_short_8","alias_value":"4HHVDS4V","created_at":"2026-07-05T02:44:08Z"}],"graph_snapshots":[{"event_id":"sha256:5bee899d45cb5dccca2d10f1d2bf1f31f2436e71bf35f429af4e191e5ddebb52","target":"graph","created_at":"2026-07-05T02:44:08Z","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/2105.13466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Koichi Takeda, Kosuke Yamada, Ryohei Sasano","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-27T22:00:33Z","title":"Semantic Frame Induction using Masked Word Embeddings and Two-Step Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13466","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":"sha256:0f5077414fb56d75ba353e4e9192078876f843f12054d146b9298b28b9089b5c","target":"record","created_at":"2026-07-05T02:44:08Z","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":"7e1875239392e0217be6b3d166c7b89f3639b72a809e48b524e07aa814b5cfd2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-27T22:00:33Z","title_canon_sha256":"078431cbe323347be8fd29d2835da611ccdf633bd85afbbac4868f9cf6f10055"},"schema_version":"1.0","source":{"id":"2105.13466","kind":"arxiv","version":1}},"canonical_sha256":"e1cf51cb956e1c3ccd8eb70da08a7e98d72fb0192c6b671d3125eae9d1d0e766","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1cf51cb956e1c3ccd8eb70da08a7e98d72fb0192c6b671d3125eae9d1d0e766","first_computed_at":"2026-07-05T02:44:08.303368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:08.303368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mqwPZaDKgMy55MBMoNeV670eKiyud/fmMOYGdh1XRnSSZfDfNECkRfxuMAsWDppHbu4nAbmVfakBf9IKqkM1Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:08.303787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.13466","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f5077414fb56d75ba353e4e9192078876f843f12054d146b9298b28b9089b5c","sha256:5bee899d45cb5dccca2d10f1d2bf1f31f2436e71bf35f429af4e191e5ddebb52"],"state_sha256":"6b9d8e7ecfacc8501808347d38e7123cc0f1bab556c0ae6ff685ce9508d9e9bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yRkN4Klsh0c3yfjmAMu+MGA6XOQcX6q36M8QAkI/2nDOUUsQ6O36d+rDtn/wjlVpHLMR8Er/o1L+ANl4POmlCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T06:46:00.213597Z","bundle_sha256":"f43ac0e4f3beaca0ac8131a1f5e77f24748ec89a5e706ba44a9f9db010b5db08"}}