{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:EH4FR4CQTPNCP34E5GFF6FMHBN","short_pith_number":"pith:EH4FR4CQ","canonical_record":{"source":{"id":"2004.02105","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T06:22:16Z","cross_cats_sorted":[],"title_canon_sha256":"e4d2d9949bd77551a9d7af7030da3575cc3dc5913ef4c35a149981217629ed91","abstract_canon_sha256":"c175dce968bf028b8993a27f28d455acf94657c9a33579bf4906d0a9a829b3af"},"schema_version":"1.0"},"canonical_sha256":"21f858f0509bda27ef84e98a5f15870b7437d0fa322786025bec91e1c8d4fec3","source":{"kind":"arxiv","id":"2004.02105","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02105","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02105v2","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02105","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"pith_short_12","alias_value":"EH4FR4CQTPNC","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"pith_short_16","alias_value":"EH4FR4CQTPNCP34E","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"pith_short_8","alias_value":"EH4FR4CQ","created_at":"2026-07-05T00:59:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:EH4FR4CQTPNCP34E5GFF6FMHBN","target":"record","payload":{"canonical_record":{"source":{"id":"2004.02105","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T06:22:16Z","cross_cats_sorted":[],"title_canon_sha256":"e4d2d9949bd77551a9d7af7030da3575cc3dc5913ef4c35a149981217629ed91","abstract_canon_sha256":"c175dce968bf028b8993a27f28d455acf94657c9a33579bf4906d0a9a829b3af"},"schema_version":"1.0"},"canonical_sha256":"21f858f0509bda27ef84e98a5f15870b7437d0fa322786025bec91e1c8d4fec3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:36.330471Z","signature_b64":"Jk2AStNm+FBcVoKUoSovTbpjG2QD7bU53eNl+uPryIC0mFrajURTrgYJxc+DiBtpSxr/B5XwVxwR1sAigVWBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21f858f0509bda27ef84e98a5f15870b7437d0fa322786025bec91e1c8d4fec3","last_reissued_at":"2026-07-05T00:59:36.329910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:36.329910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.02105","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":"2026-07-05T00:59:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V5KUY/znhcj5QlmPKWQoqY+d/aaECKZSCL2Hl7cUABm96xrXa2o/4yRTetBJIHVrRPrmr1wWtcJZ+adFpd9HDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:30:37.157072Z"},"content_sha256":"3f365b362d563a3e27e64db161a6380242c7dde759f732c0c352cea82e972040","schema_version":"1.0","event_id":"sha256:3f365b362d563a3e27e64db161a6380242c7dde759f732c0c352cea82e972040"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:EH4FR4CQTPNCP34E5GFF6FMHBN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Domain Clusters in Pretrained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Roee Aharoni, Yoav Goldberg","submitted_at":"2020-04-05T06:22:16Z","abstract_excerpt":"The notion of \"in-domain data\" in NLP is often over-simplistic and vague, as textual data varies in many nuanced linguistic aspects such as topic, style or level of formality. In addition, domain labels are many times unavailable, making it challenging to build domain-specific systems. We show that massive pre-trained language models implicitly learn sentence representations that cluster by domains without supervision -- suggesting a simple data-driven definition of domains in textual data. We harness this property and propose domain data selection methods based on such models, which require o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02105","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/2004.02105/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":"2026-07-05T00:59:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VlH4Q9SAh2Nq5ux2eVBjQPv4y1ElVbLbgORAmPiD3dR3LCAPvNfOdvIya/xFza42P2fCcgx2WSpIJoWfZDY9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:30:37.157441Z"},"content_sha256":"1a9c8a0f6f2692735e08eb0a885cd78dbe02a146c52ef92a3eca8e7db4638dc0","schema_version":"1.0","event_id":"sha256:1a9c8a0f6f2692735e08eb0a885cd78dbe02a146c52ef92a3eca8e7db4638dc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EH4FR4CQTPNCP34E5GFF6FMHBN/bundle.json","state_url":"https://pith.science/pith/EH4FR4CQTPNCP34E5GFF6FMHBN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EH4FR4CQTPNCP34E5GFF6FMHBN/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":"2026-08-19T20:30:37Z","links":{"resolver":"https://pith.science/pith/EH4FR4CQTPNCP34E5GFF6FMHBN","bundle":"https://pith.science/pith/EH4FR4CQTPNCP34E5GFF6FMHBN/bundle.json","state":"https://pith.science/pith/EH4FR4CQTPNCP34E5GFF6FMHBN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EH4FR4CQTPNCP34E5GFF6FMHBN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EH4FR4CQTPNCP34E5GFF6FMHBN","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":"c175dce968bf028b8993a27f28d455acf94657c9a33579bf4906d0a9a829b3af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T06:22:16Z","title_canon_sha256":"e4d2d9949bd77551a9d7af7030da3575cc3dc5913ef4c35a149981217629ed91"},"schema_version":"1.0","source":{"id":"2004.02105","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02105","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02105v2","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02105","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"pith_short_12","alias_value":"EH4FR4CQTPNC","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"pith_short_16","alias_value":"EH4FR4CQTPNCP34E","created_at":"2026-07-05T00:59:36Z"},{"alias_kind":"pith_short_8","alias_value":"EH4FR4CQ","created_at":"2026-07-05T00:59:36Z"}],"graph_snapshots":[{"event_id":"sha256:1a9c8a0f6f2692735e08eb0a885cd78dbe02a146c52ef92a3eca8e7db4638dc0","target":"graph","created_at":"2026-07-05T00:59:36Z","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/2004.02105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The notion of \"in-domain data\" in NLP is often over-simplistic and vague, as textual data varies in many nuanced linguistic aspects such as topic, style or level of formality. In addition, domain labels are many times unavailable, making it challenging to build domain-specific systems. We show that massive pre-trained language models implicitly learn sentence representations that cluster by domains without supervision -- suggesting a simple data-driven definition of domains in textual data. We harness this property and propose domain data selection methods based on such models, which require o","authors_text":"Roee Aharoni, Yoav Goldberg","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T06:22:16Z","title":"Unsupervised Domain Clusters in Pretrained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02105","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":"sha256:3f365b362d563a3e27e64db161a6380242c7dde759f732c0c352cea82e972040","target":"record","created_at":"2026-07-05T00:59:36Z","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":"c175dce968bf028b8993a27f28d455acf94657c9a33579bf4906d0a9a829b3af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T06:22:16Z","title_canon_sha256":"e4d2d9949bd77551a9d7af7030da3575cc3dc5913ef4c35a149981217629ed91"},"schema_version":"1.0","source":{"id":"2004.02105","kind":"arxiv","version":2}},"canonical_sha256":"21f858f0509bda27ef84e98a5f15870b7437d0fa322786025bec91e1c8d4fec3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21f858f0509bda27ef84e98a5f15870b7437d0fa322786025bec91e1c8d4fec3","first_computed_at":"2026-07-05T00:59:36.329910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:36.329910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jk2AStNm+FBcVoKUoSovTbpjG2QD7bU53eNl+uPryIC0mFrajURTrgYJxc+DiBtpSxr/B5XwVxwR1sAigVWBCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:36.330471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.02105","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f365b362d563a3e27e64db161a6380242c7dde759f732c0c352cea82e972040","sha256:1a9c8a0f6f2692735e08eb0a885cd78dbe02a146c52ef92a3eca8e7db4638dc0"],"state_sha256":"bf7a86c8a6defd3c4758f21c708fe05eae914ed8cb0f5d63163e9d7e283efdcd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8rrpveaFopL1v5gRvKnui+0C2ef5huQ32rEpPYZw2PrvmCpnDuOBmJCWpPaq4WPJ7lIxm6xdc0Q3v/DjYNQLAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T20:30:37.159778Z","bundle_sha256":"44a31e4111e10a07b933e1c06be78050c0b5c7c4b22d781c201e6189b318d006"}}