{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AKDGQ3MKQZ2HU4CJNMD4A7TBTN","short_pith_number":"pith:AKDGQ3MK","canonical_record":{"source":{"id":"2109.06304","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T20:31:57Z","cross_cats_sorted":[],"title_canon_sha256":"031d276ce0d8679e0c310700c453cf77a5533e4cc0e61dc02964d96e452d8e8c","abstract_canon_sha256":"ba1dba178e6f2808f793f94ea2fb13784adab90436a22343042d34a338c26bf2"},"schema_version":"1.0"},"canonical_sha256":"0286686d8a86747a70496b07c07e619b5fa608dfe523fa93b000cf87b439facb","source":{"kind":"arxiv","id":"2109.06304","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06304","created_at":"2026-07-05T03:22:36Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06304v2","created_at":"2026-07-05T03:22:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06304","created_at":"2026-07-05T03:22:36Z"},{"alias_kind":"pith_short_12","alias_value":"AKDGQ3MKQZ2H","created_at":"2026-07-05T03:22:36Z"},{"alias_kind":"pith_short_16","alias_value":"AKDGQ3MKQZ2HU4CJ","created_at":"2026-07-05T03:22:36Z"},{"alias_kind":"pith_short_8","alias_value":"AKDGQ3MK","created_at":"2026-07-05T03:22:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AKDGQ3MKQZ2HU4CJNMD4A7TBTN","target":"record","payload":{"canonical_record":{"source":{"id":"2109.06304","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T20:31:57Z","cross_cats_sorted":[],"title_canon_sha256":"031d276ce0d8679e0c310700c453cf77a5533e4cc0e61dc02964d96e452d8e8c","abstract_canon_sha256":"ba1dba178e6f2808f793f94ea2fb13784adab90436a22343042d34a338c26bf2"},"schema_version":"1.0"},"canonical_sha256":"0286686d8a86747a70496b07c07e619b5fa608dfe523fa93b000cf87b439facb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:36.831364Z","signature_b64":"OXhCGkn5NqePvOwfBMnrsL/ju5cgoYVL1vEXs1lwHbytRwhRcj6v7RSY/9/IhgKwQ6VZC3XuFYilz/mKuKrYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0286686d8a86747a70496b07c07e619b5fa608dfe523fa93b000cf87b439facb","last_reissued_at":"2026-07-05T03:22:36.830940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:36.830940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.06304","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":"2026-07-05T03:22:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZJVCsC/7Xl6C5qmjLUzbyHEugomVHwgUYkDh38IgrON8sRMwJ6An9zIbwlf6tMN6H2Anoc7dhZlVdYscd7BrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:42:35.280776Z"},"content_sha256":"8e3c33e91dd339eb03da5788915d711c2bc9b2be4395d4674f92d610cc9c7c5c","schema_version":"1.0","event_id":"sha256:8e3c33e91dd339eb03da5788915d711c2bc9b2be4395d4674f92d610cc9c7c5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AKDGQ3MKQZ2HU4CJNMD4A7TBTN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Laure Thompson, Mohit Iyyer, Shufan Wang","submitted_at":"2021-09-13T20:31:57Z","abstract_excerpt":"Phrase representations derived from BERT often do not exhibit complex phrasal compositionality, as the model relies instead on lexical similarity to determine semantic relatedness. In this paper, we propose a contrastive fine-tuning objective that enables BERT to produce more powerful phrase embeddings. Our approach (Phrase-BERT) relies on a dataset of diverse phrasal paraphrases, which is automatically generated using a paraphrase generation model, as well as a large-scale dataset of phrases in context mined from the Books3 corpus. Phrase-BERT outperforms baselines across a variety of phrase-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06304","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/2109.06304/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":"2026-07-05T03:22:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BC4kBFS/Y0S3hkhMuOpXMGd56Cmk6LSU5UvsgXmo5woghdcmN6WkmDEK/hTgQjOYVxIuJ49uFLEKmgi4IvVcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:42:35.281335Z"},"content_sha256":"0be1515eb63c36a1ab9b91c7844d4ef03b1808707138c767da012aba0c2808db","schema_version":"1.0","event_id":"sha256:0be1515eb63c36a1ab9b91c7844d4ef03b1808707138c767da012aba0c2808db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AKDGQ3MKQZ2HU4CJNMD4A7TBTN/bundle.json","state_url":"https://pith.science/pith/AKDGQ3MKQZ2HU4CJNMD4A7TBTN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AKDGQ3MKQZ2HU4CJNMD4A7TBTN/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":"2026-08-20T22:42:35Z","links":{"resolver":"https://pith.science/pith/AKDGQ3MKQZ2HU4CJNMD4A7TBTN","bundle":"https://pith.science/pith/AKDGQ3MKQZ2HU4CJNMD4A7TBTN/bundle.json","state":"https://pith.science/pith/AKDGQ3MKQZ2HU4CJNMD4A7TBTN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AKDGQ3MKQZ2HU4CJNMD4A7TBTN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AKDGQ3MKQZ2HU4CJNMD4A7TBTN","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":"ba1dba178e6f2808f793f94ea2fb13784adab90436a22343042d34a338c26bf2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T20:31:57Z","title_canon_sha256":"031d276ce0d8679e0c310700c453cf77a5533e4cc0e61dc02964d96e452d8e8c"},"schema_version":"1.0","source":{"id":"2109.06304","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06304","created_at":"2026-07-05T03:22:36Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06304v2","created_at":"2026-07-05T03:22:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06304","created_at":"2026-07-05T03:22:36Z"},{"alias_kind":"pith_short_12","alias_value":"AKDGQ3MKQZ2H","created_at":"2026-07-05T03:22:36Z"},{"alias_kind":"pith_short_16","alias_value":"AKDGQ3MKQZ2HU4CJ","created_at":"2026-07-05T03:22:36Z"},{"alias_kind":"pith_short_8","alias_value":"AKDGQ3MK","created_at":"2026-07-05T03:22:36Z"}],"graph_snapshots":[{"event_id":"sha256:0be1515eb63c36a1ab9b91c7844d4ef03b1808707138c767da012aba0c2808db","target":"graph","created_at":"2026-07-05T03:22:36Z","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/2109.06304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Phrase representations derived from BERT often do not exhibit complex phrasal compositionality, as the model relies instead on lexical similarity to determine semantic relatedness. In this paper, we propose a contrastive fine-tuning objective that enables BERT to produce more powerful phrase embeddings. Our approach (Phrase-BERT) relies on a dataset of diverse phrasal paraphrases, which is automatically generated using a paraphrase generation model, as well as a large-scale dataset of phrases in context mined from the Books3 corpus. Phrase-BERT outperforms baselines across a variety of phrase-","authors_text":"Laure Thompson, Mohit Iyyer, Shufan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T20:31:57Z","title":"Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06304","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":"sha256:8e3c33e91dd339eb03da5788915d711c2bc9b2be4395d4674f92d610cc9c7c5c","target":"record","created_at":"2026-07-05T03:22:36Z","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":"ba1dba178e6f2808f793f94ea2fb13784adab90436a22343042d34a338c26bf2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T20:31:57Z","title_canon_sha256":"031d276ce0d8679e0c310700c453cf77a5533e4cc0e61dc02964d96e452d8e8c"},"schema_version":"1.0","source":{"id":"2109.06304","kind":"arxiv","version":2}},"canonical_sha256":"0286686d8a86747a70496b07c07e619b5fa608dfe523fa93b000cf87b439facb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0286686d8a86747a70496b07c07e619b5fa608dfe523fa93b000cf87b439facb","first_computed_at":"2026-07-05T03:22:36.830940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:36.830940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OXhCGkn5NqePvOwfBMnrsL/ju5cgoYVL1vEXs1lwHbytRwhRcj6v7RSY/9/IhgKwQ6VZC3XuFYilz/mKuKrYCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:36.831364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.06304","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e3c33e91dd339eb03da5788915d711c2bc9b2be4395d4674f92d610cc9c7c5c","sha256:0be1515eb63c36a1ab9b91c7844d4ef03b1808707138c767da012aba0c2808db"],"state_sha256":"58a9416cde4646f8ea966e6eb00b4a67b99f1181a2f8b874fc2ede31fb133346"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j/HM8j+lvOd6Nem9C9vEdIYPHSno9rzSUirGU0xyNpScn2fGxqponbDtF2jwxEM23BhGvIKbeOrTVsx+fMo5BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T22:42:35.286628Z","bundle_sha256":"13fe3cb947024d3fbc4aba843c573157f5ea88fe76fea5c50c917504da9a1e96"}}