{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LMFZDEU2JBJPN53JVRAIIWWDJR","short_pith_number":"pith:LMFZDEU2","canonical_record":{"source":{"id":"2012.15197","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-30T15:38:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"062c91e61fffbc5c8f26d3fe950de745d7f0953e8df81f2178c13c3420c2ed6e","abstract_canon_sha256":"f1b6f6b25bc4a46264322974a74bdcf27f7ec79897552fb1c311cef9163df136"},"schema_version":"1.0"},"canonical_sha256":"5b0b91929a4852f6f769ac40845ac34c5a03b380ed23ac80c9f3c1ecda0375a3","source":{"kind":"arxiv","id":"2012.15197","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15197","created_at":"2026-07-05T03:34:42Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15197v2","created_at":"2026-07-05T03:34:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15197","created_at":"2026-07-05T03:34:42Z"},{"alias_kind":"pith_short_12","alias_value":"LMFZDEU2JBJP","created_at":"2026-07-05T03:34:42Z"},{"alias_kind":"pith_short_16","alias_value":"LMFZDEU2JBJPN53J","created_at":"2026-07-05T03:34:42Z"},{"alias_kind":"pith_short_8","alias_value":"LMFZDEU2","created_at":"2026-07-05T03:34:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LMFZDEU2JBJPN53JVRAIIWWDJR","target":"record","payload":{"canonical_record":{"source":{"id":"2012.15197","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-30T15:38:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"062c91e61fffbc5c8f26d3fe950de745d7f0953e8df81f2178c13c3420c2ed6e","abstract_canon_sha256":"f1b6f6b25bc4a46264322974a74bdcf27f7ec79897552fb1c311cef9163df136"},"schema_version":"1.0"},"canonical_sha256":"5b0b91929a4852f6f769ac40845ac34c5a03b380ed23ac80c9f3c1ecda0375a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:42.633448Z","signature_b64":"P/yXXCB62W+zhzWoLYM7pBahllJluQnmOzkuSRKUctzjnH+Hnm3Qf0n7gUJhVIsWrDq/3t5tZ5w0uEQhhz5yAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b0b91929a4852f6f769ac40845ac34c5a03b380ed23ac80c9f3c1ecda0375a3","last_reissued_at":"2026-07-05T03:34:42.633034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:42.633034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.15197","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":"2026-07-05T03:34:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3QVuSlnXa8Hz1LJ0y2s5RCZxqtK3SwIs0XGrnAhm0bElJNmxf3iGdbJTG3zBzDmm1RWFNP4SSmMdD/c7gxgIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:15:34.918404Z"},"content_sha256":"b5bbcc68b2b6f3682e8b96b64ce8d4f031322f51f1fe3f211665c78591ea8436","schema_version":"1.0","event_id":"sha256:b5bbcc68b2b6f3682e8b96b64ce8d4f031322f51f1fe3f211665c78591ea8436"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LMFZDEU2JBJPN53JVRAIIWWDJR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SemGloVe: Semantic Co-occurrences for GloVe from BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fei Wu, Leilei Gan, Linchao Zhu, Yi Yang, Yue Zhang, Zhiyang Teng","submitted_at":"2020-12-30T15:38:26Z","abstract_excerpt":"GloVe learns word embeddings by leveraging statistical information from word co-occurrence matrices. However, word pairs in the matrices are extracted from a predefined local context window, which might lead to limited word pairs and potentially semantic irrelevant word pairs. In this paper, we propose SemGloVe, which distills semantic co-occurrences from BERT into static GloVe word embeddings. Particularly, we propose two models to extract co-occurrence statistics based on either the masked language model or the multi-head attention weights of BERT. Our methods can extract word pairs without "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15197","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/2012.15197/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":"2026-07-05T03:34:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DBw+5vhdC0wJOd/8YHrlZHhfCtOddW2ZN7KZO0YXQveDBGRXYNEPyb74LHhn83lK/LBfrFWRsoG+1xnIx28yCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:15:34.918935Z"},"content_sha256":"f9374eaa4e4d5afb76343ae2680d67030abdf35806d0c23fc363b8004730d4a1","schema_version":"1.0","event_id":"sha256:f9374eaa4e4d5afb76343ae2680d67030abdf35806d0c23fc363b8004730d4a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LMFZDEU2JBJPN53JVRAIIWWDJR/bundle.json","state_url":"https://pith.science/pith/LMFZDEU2JBJPN53JVRAIIWWDJR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LMFZDEU2JBJPN53JVRAIIWWDJR/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":"2026-08-04T04:15:34Z","links":{"resolver":"https://pith.science/pith/LMFZDEU2JBJPN53JVRAIIWWDJR","bundle":"https://pith.science/pith/LMFZDEU2JBJPN53JVRAIIWWDJR/bundle.json","state":"https://pith.science/pith/LMFZDEU2JBJPN53JVRAIIWWDJR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LMFZDEU2JBJPN53JVRAIIWWDJR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LMFZDEU2JBJPN53JVRAIIWWDJR","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":"f1b6f6b25bc4a46264322974a74bdcf27f7ec79897552fb1c311cef9163df136","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-30T15:38:26Z","title_canon_sha256":"062c91e61fffbc5c8f26d3fe950de745d7f0953e8df81f2178c13c3420c2ed6e"},"schema_version":"1.0","source":{"id":"2012.15197","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15197","created_at":"2026-07-05T03:34:42Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15197v2","created_at":"2026-07-05T03:34:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15197","created_at":"2026-07-05T03:34:42Z"},{"alias_kind":"pith_short_12","alias_value":"LMFZDEU2JBJP","created_at":"2026-07-05T03:34:42Z"},{"alias_kind":"pith_short_16","alias_value":"LMFZDEU2JBJPN53J","created_at":"2026-07-05T03:34:42Z"},{"alias_kind":"pith_short_8","alias_value":"LMFZDEU2","created_at":"2026-07-05T03:34:42Z"}],"graph_snapshots":[{"event_id":"sha256:f9374eaa4e4d5afb76343ae2680d67030abdf35806d0c23fc363b8004730d4a1","target":"graph","created_at":"2026-07-05T03:34:42Z","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/2012.15197/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"GloVe learns word embeddings by leveraging statistical information from word co-occurrence matrices. However, word pairs in the matrices are extracted from a predefined local context window, which might lead to limited word pairs and potentially semantic irrelevant word pairs. In this paper, we propose SemGloVe, which distills semantic co-occurrences from BERT into static GloVe word embeddings. Particularly, we propose two models to extract co-occurrence statistics based on either the masked language model or the multi-head attention weights of BERT. Our methods can extract word pairs without ","authors_text":"Fei Wu, Leilei Gan, Linchao Zhu, Yi Yang, Yue Zhang, Zhiyang Teng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-30T15:38:26Z","title":"SemGloVe: Semantic Co-occurrences for GloVe from BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15197","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:b5bbcc68b2b6f3682e8b96b64ce8d4f031322f51f1fe3f211665c78591ea8436","target":"record","created_at":"2026-07-05T03:34:42Z","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":"f1b6f6b25bc4a46264322974a74bdcf27f7ec79897552fb1c311cef9163df136","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-30T15:38:26Z","title_canon_sha256":"062c91e61fffbc5c8f26d3fe950de745d7f0953e8df81f2178c13c3420c2ed6e"},"schema_version":"1.0","source":{"id":"2012.15197","kind":"arxiv","version":2}},"canonical_sha256":"5b0b91929a4852f6f769ac40845ac34c5a03b380ed23ac80c9f3c1ecda0375a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b0b91929a4852f6f769ac40845ac34c5a03b380ed23ac80c9f3c1ecda0375a3","first_computed_at":"2026-07-05T03:34:42.633034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:34:42.633034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P/yXXCB62W+zhzWoLYM7pBahllJluQnmOzkuSRKUctzjnH+Hnm3Qf0n7gUJhVIsWrDq/3t5tZ5w0uEQhhz5yAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:34:42.633448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15197","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5bbcc68b2b6f3682e8b96b64ce8d4f031322f51f1fe3f211665c78591ea8436","sha256:f9374eaa4e4d5afb76343ae2680d67030abdf35806d0c23fc363b8004730d4a1"],"state_sha256":"6328e747dd38572489942344f7579be9a609403d39c1c84e7e081ad94ceb0dd8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CBPNfYWzopRPPSvC6FLnLLepncLbs96DvlKskcNEcLqC09TIi9DiMb0yo635h6sc6ZSCBEX1EiV320/COl+7Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:15:34.924067Z","bundle_sha256":"7106786e09fe66e6393ee4b321b03b5ec0a1871f95e777d64c4f8e2e6a6d5e31"}}