{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:F3VEUY7RLSWCCH3L5MAFXUJKDM","short_pith_number":"pith:F3VEUY7R","canonical_record":{"source":{"id":"2011.05864","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-02T13:14:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6df1f07e500c4610590b6183498b9cd0cf6b05d6961999bf71ad35982e495dff","abstract_canon_sha256":"6ffb0933a795972851b8d34d02cad8fb682174a33bc8163698ab95016d4fbd20"},"schema_version":"1.0"},"canonical_sha256":"2eea4a63f15cac211f6beb005bd12a1b2077eb7375af6a95f14a0057b64e4efa","source":{"kind":"arxiv","id":"2011.05864","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.05864","created_at":"2026-07-05T01:51:02Z"},{"alias_kind":"arxiv_version","alias_value":"2011.05864v1","created_at":"2026-07-05T01:51:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05864","created_at":"2026-07-05T01:51:02Z"},{"alias_kind":"pith_short_12","alias_value":"F3VEUY7RLSWC","created_at":"2026-07-05T01:51:02Z"},{"alias_kind":"pith_short_16","alias_value":"F3VEUY7RLSWCCH3L","created_at":"2026-07-05T01:51:02Z"},{"alias_kind":"pith_short_8","alias_value":"F3VEUY7R","created_at":"2026-07-05T01:51:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:F3VEUY7RLSWCCH3L5MAFXUJKDM","target":"record","payload":{"canonical_record":{"source":{"id":"2011.05864","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-02T13:14:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6df1f07e500c4610590b6183498b9cd0cf6b05d6961999bf71ad35982e495dff","abstract_canon_sha256":"6ffb0933a795972851b8d34d02cad8fb682174a33bc8163698ab95016d4fbd20"},"schema_version":"1.0"},"canonical_sha256":"2eea4a63f15cac211f6beb005bd12a1b2077eb7375af6a95f14a0057b64e4efa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:02.397550Z","signature_b64":"Ng22cajz68PS3S+eHXPgPYTwy866C6fIpaSW3h/amN3n/h7MuUtGUWffwghQDykIdiawmiJfdyV2tZXJW3OrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eea4a63f15cac211f6beb005bd12a1b2077eb7375af6a95f14a0057b64e4efa","last_reissued_at":"2026-07-05T01:51:02.397106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:02.397106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.05864","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":"2026-07-05T01:51:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3gTnjGpPF6CPx6wFsZfARKurURb84dD0QORoz9p0F+Eb14Qtq/EkcV2QC/gD3IbiT5/EEuFBXH2vBJZ+LnE8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:25:45.999910Z"},"content_sha256":"263d80def83aed23f766a34d0d4ee61e00b07e66db3a3c3b22fd528eab1bf4d2","schema_version":"1.0","event_id":"sha256:263d80def83aed23f766a34d0d4ee61e00b07e66db3a3c3b22fd528eab1bf4d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:F3VEUY7RLSWCCH3L5MAFXUJKDM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Sentence Embeddings from Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bohan Li, Hao Zhou, Junxian He, Lei Li, Mingxuan Wang, Yiming Yang","submitted_at":"2020-11-02T13:14:57Z","abstract_excerpt":"Pre-trained contextual representations like BERT have achieved great success in natural language processing. However, the sentence embeddings from the pre-trained language models without fine-tuning have been found to poorly capture semantic meaning of sentences. In this paper, we argue that the semantic information in the BERT embeddings is not fully exploited. We first reveal the theoretical connection between the masked language model pre-training objective and the semantic similarity task theoretically, and then analyze the BERT sentence embeddings empirically. We find that BERT always ind"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05864","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/2011.05864/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":"2026-07-05T01:51:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U20nk09tDB4OdSQW6eFOV2gbFhjjPE72FaZ6Kc+pjp3JpL3PmiSw/4ypKy0OqW9/b130OeqOaL99D4rWgMA7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:25:46.000357Z"},"content_sha256":"6868e1c18ca12b0044de47bbeadf1bfb3fe953020ab02f7bff3177a4c931f76a","schema_version":"1.0","event_id":"sha256:6868e1c18ca12b0044de47bbeadf1bfb3fe953020ab02f7bff3177a4c931f76a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F3VEUY7RLSWCCH3L5MAFXUJKDM/bundle.json","state_url":"https://pith.science/pith/F3VEUY7RLSWCCH3L5MAFXUJKDM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F3VEUY7RLSWCCH3L5MAFXUJKDM/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":"2026-07-07T13:25:46Z","links":{"resolver":"https://pith.science/pith/F3VEUY7RLSWCCH3L5MAFXUJKDM","bundle":"https://pith.science/pith/F3VEUY7RLSWCCH3L5MAFXUJKDM/bundle.json","state":"https://pith.science/pith/F3VEUY7RLSWCCH3L5MAFXUJKDM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F3VEUY7RLSWCCH3L5MAFXUJKDM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:F3VEUY7RLSWCCH3L5MAFXUJKDM","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":"6ffb0933a795972851b8d34d02cad8fb682174a33bc8163698ab95016d4fbd20","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-02T13:14:57Z","title_canon_sha256":"6df1f07e500c4610590b6183498b9cd0cf6b05d6961999bf71ad35982e495dff"},"schema_version":"1.0","source":{"id":"2011.05864","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.05864","created_at":"2026-07-05T01:51:02Z"},{"alias_kind":"arxiv_version","alias_value":"2011.05864v1","created_at":"2026-07-05T01:51:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05864","created_at":"2026-07-05T01:51:02Z"},{"alias_kind":"pith_short_12","alias_value":"F3VEUY7RLSWC","created_at":"2026-07-05T01:51:02Z"},{"alias_kind":"pith_short_16","alias_value":"F3VEUY7RLSWCCH3L","created_at":"2026-07-05T01:51:02Z"},{"alias_kind":"pith_short_8","alias_value":"F3VEUY7R","created_at":"2026-07-05T01:51:02Z"}],"graph_snapshots":[{"event_id":"sha256:6868e1c18ca12b0044de47bbeadf1bfb3fe953020ab02f7bff3177a4c931f76a","target":"graph","created_at":"2026-07-05T01:51:02Z","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/2011.05864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained contextual representations like BERT have achieved great success in natural language processing. However, the sentence embeddings from the pre-trained language models without fine-tuning have been found to poorly capture semantic meaning of sentences. In this paper, we argue that the semantic information in the BERT embeddings is not fully exploited. We first reveal the theoretical connection between the masked language model pre-training objective and the semantic similarity task theoretically, and then analyze the BERT sentence embeddings empirically. We find that BERT always ind","authors_text":"Bohan Li, Hao Zhou, Junxian He, Lei Li, Mingxuan Wang, Yiming Yang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-02T13:14:57Z","title":"On the Sentence Embeddings from Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05864","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":"sha256:263d80def83aed23f766a34d0d4ee61e00b07e66db3a3c3b22fd528eab1bf4d2","target":"record","created_at":"2026-07-05T01:51:02Z","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":"6ffb0933a795972851b8d34d02cad8fb682174a33bc8163698ab95016d4fbd20","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-02T13:14:57Z","title_canon_sha256":"6df1f07e500c4610590b6183498b9cd0cf6b05d6961999bf71ad35982e495dff"},"schema_version":"1.0","source":{"id":"2011.05864","kind":"arxiv","version":1}},"canonical_sha256":"2eea4a63f15cac211f6beb005bd12a1b2077eb7375af6a95f14a0057b64e4efa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2eea4a63f15cac211f6beb005bd12a1b2077eb7375af6a95f14a0057b64e4efa","first_computed_at":"2026-07-05T01:51:02.397106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:02.397106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ng22cajz68PS3S+eHXPgPYTwy866C6fIpaSW3h/amN3n/h7MuUtGUWffwghQDykIdiawmiJfdyV2tZXJW3OrCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:02.397550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.05864","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:263d80def83aed23f766a34d0d4ee61e00b07e66db3a3c3b22fd528eab1bf4d2","sha256:6868e1c18ca12b0044de47bbeadf1bfb3fe953020ab02f7bff3177a4c931f76a"],"state_sha256":"9d935f9c596b1a3ffd271c73eb92b2de83926307fb904b4419169204157b1cd6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vnxFhIcKWiqD0HFYKd3fH1BtztC7Z6bZEhM0/wecaiNDnpf3d3LDCVgjwr7hz6Pjce6+5eINtzFrqm3ArFH3Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:25:46.002425Z","bundle_sha256":"49213a77310c6b0de49fb694b3a1e9f9677098955e8a5aa05235c499ba3db078"}}