{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:J5LRM4BUFC5RQFH7URBDPSQ7NS","short_pith_number":"pith:J5LRM4BU","canonical_record":{"source":{"id":"2203.10581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T15:29:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d8866b745d4a2b120d468f4cddd5dd40a4e2fb665f3f9cbba1c608fef3ad5d2f","abstract_canon_sha256":"a54b2e564b24677e84361fa31a0798e3c27be3fbe06402bd93a055a9daba8e6b"},"schema_version":"1.0"},"canonical_sha256":"4f5716703428bb1814ffa44237ca1f6cad5c606bafe587cc6b8ea47ad24ade76","source":{"kind":"arxiv","id":"2203.10581","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10581","created_at":"2026-07-05T04:06:54Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10581v1","created_at":"2026-07-05T04:06:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10581","created_at":"2026-07-05T04:06:54Z"},{"alias_kind":"pith_short_12","alias_value":"J5LRM4BUFC5R","created_at":"2026-07-05T04:06:54Z"},{"alias_kind":"pith_short_16","alias_value":"J5LRM4BUFC5RQFH7","created_at":"2026-07-05T04:06:54Z"},{"alias_kind":"pith_short_8","alias_value":"J5LRM4BU","created_at":"2026-07-05T04:06:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:J5LRM4BUFC5RQFH7URBDPSQ7NS","target":"record","payload":{"canonical_record":{"source":{"id":"2203.10581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T15:29:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d8866b745d4a2b120d468f4cddd5dd40a4e2fb665f3f9cbba1c608fef3ad5d2f","abstract_canon_sha256":"a54b2e564b24677e84361fa31a0798e3c27be3fbe06402bd93a055a9daba8e6b"},"schema_version":"1.0"},"canonical_sha256":"4f5716703428bb1814ffa44237ca1f6cad5c606bafe587cc6b8ea47ad24ade76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:54.627901Z","signature_b64":"4WVtR4n34luSxNLjulkmDuXTmwOFG8u+zrl30M4uY/x1xfTsqTBNclFhYjRLBdAqKLG+AwxFL6ZoQHnkRhgKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f5716703428bb1814ffa44237ca1f6cad5c606bafe587cc6b8ea47ad24ade76","last_reissued_at":"2026-07-05T04:06:54.627481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:54.627481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.10581","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":"2026-07-05T04:06:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6wAIMboCax0ROhVZRUcixnb18RXNBKNTxEI+SrPBIWH2MBb/jSkA+m6XBjXwfeMiX3GtyUp+mmXQEcYZCcuLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:19:42.899661Z"},"content_sha256":"bde5bb1a91c51d79fbafce25259fa99b7d2136d5dbb66c2b3fa23fb574c2fd44","schema_version":"1.0","event_id":"sha256:bde5bb1a91c51d79fbafce25259fa99b7d2136d5dbb66c2b3fa23fb574c2fd44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:J5LRM4BUFC5RQFH7URBDPSQ7NS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cluster & Tune: Boost Cold Start Performance in Text Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alon Halfon, Ariel Gera, Eyal Shnarch, Lena Dankin, Leshem Choshen, Noam Slonim, Ranit Aharonov","submitted_at":"2022-03-20T15:29:34Z","abstract_excerpt":"In real-world scenarios, a text classification task often begins with a cold start, when labeled data is scarce. In such cases, the common practice of fine-tuning pre-trained models, such as BERT, for a target classification task, is prone to produce poor performance. We suggest a method to boost the performance of such models by adding an intermediate unsupervised classification task, between the pre-training and fine-tuning phases. As such an intermediate task, we perform clustering and train the pre-trained model on predicting the cluster labels. We test this hypothesis on various data sets"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10581","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/2203.10581/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":"2026-07-05T04:06:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OC1Rrk3hARJUk3GGI0VGjl60+lXF/vj1AgbNNiW6dqmYA158r5tRh/T4io+LEzyWT6tj5TrtLVhy8JiWr9kbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:19:42.900280Z"},"content_sha256":"f62150534fc22b01e6e3860bd83682189fecdabf2d4cd119e6fe63526f4087f7","schema_version":"1.0","event_id":"sha256:f62150534fc22b01e6e3860bd83682189fecdabf2d4cd119e6fe63526f4087f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J5LRM4BUFC5RQFH7URBDPSQ7NS/bundle.json","state_url":"https://pith.science/pith/J5LRM4BUFC5RQFH7URBDPSQ7NS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J5LRM4BUFC5RQFH7URBDPSQ7NS/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":"2026-08-05T11:19:42Z","links":{"resolver":"https://pith.science/pith/J5LRM4BUFC5RQFH7URBDPSQ7NS","bundle":"https://pith.science/pith/J5LRM4BUFC5RQFH7URBDPSQ7NS/bundle.json","state":"https://pith.science/pith/J5LRM4BUFC5RQFH7URBDPSQ7NS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J5LRM4BUFC5RQFH7URBDPSQ7NS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:J5LRM4BUFC5RQFH7URBDPSQ7NS","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":"a54b2e564b24677e84361fa31a0798e3c27be3fbe06402bd93a055a9daba8e6b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T15:29:34Z","title_canon_sha256":"d8866b745d4a2b120d468f4cddd5dd40a4e2fb665f3f9cbba1c608fef3ad5d2f"},"schema_version":"1.0","source":{"id":"2203.10581","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10581","created_at":"2026-07-05T04:06:54Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10581v1","created_at":"2026-07-05T04:06:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10581","created_at":"2026-07-05T04:06:54Z"},{"alias_kind":"pith_short_12","alias_value":"J5LRM4BUFC5R","created_at":"2026-07-05T04:06:54Z"},{"alias_kind":"pith_short_16","alias_value":"J5LRM4BUFC5RQFH7","created_at":"2026-07-05T04:06:54Z"},{"alias_kind":"pith_short_8","alias_value":"J5LRM4BU","created_at":"2026-07-05T04:06:54Z"}],"graph_snapshots":[{"event_id":"sha256:f62150534fc22b01e6e3860bd83682189fecdabf2d4cd119e6fe63526f4087f7","target":"graph","created_at":"2026-07-05T04:06:54Z","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/2203.10581/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In real-world scenarios, a text classification task often begins with a cold start, when labeled data is scarce. In such cases, the common practice of fine-tuning pre-trained models, such as BERT, for a target classification task, is prone to produce poor performance. We suggest a method to boost the performance of such models by adding an intermediate unsupervised classification task, between the pre-training and fine-tuning phases. As such an intermediate task, we perform clustering and train the pre-trained model on predicting the cluster labels. We test this hypothesis on various data sets","authors_text":"Alon Halfon, Ariel Gera, Eyal Shnarch, Lena Dankin, Leshem Choshen, Noam Slonim, Ranit Aharonov","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T15:29:34Z","title":"Cluster & Tune: Boost Cold Start Performance in Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10581","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:bde5bb1a91c51d79fbafce25259fa99b7d2136d5dbb66c2b3fa23fb574c2fd44","target":"record","created_at":"2026-07-05T04:06:54Z","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":"a54b2e564b24677e84361fa31a0798e3c27be3fbe06402bd93a055a9daba8e6b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-20T15:29:34Z","title_canon_sha256":"d8866b745d4a2b120d468f4cddd5dd40a4e2fb665f3f9cbba1c608fef3ad5d2f"},"schema_version":"1.0","source":{"id":"2203.10581","kind":"arxiv","version":1}},"canonical_sha256":"4f5716703428bb1814ffa44237ca1f6cad5c606bafe587cc6b8ea47ad24ade76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f5716703428bb1814ffa44237ca1f6cad5c606bafe587cc6b8ea47ad24ade76","first_computed_at":"2026-07-05T04:06:54.627481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:54.627481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4WVtR4n34luSxNLjulkmDuXTmwOFG8u+zrl30M4uY/x1xfTsqTBNclFhYjRLBdAqKLG+AwxFL6ZoQHnkRhgKDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:54.627901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.10581","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bde5bb1a91c51d79fbafce25259fa99b7d2136d5dbb66c2b3fa23fb574c2fd44","sha256:f62150534fc22b01e6e3860bd83682189fecdabf2d4cd119e6fe63526f4087f7"],"state_sha256":"930d97ca0b172a1f10bed942287cf77d5f05251797f35ec6a1c5d653732e9b3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D7QGIS1yX55O3VrFUmMU+QrSD62aCAHzirc5cuBucB8HsAle3UkLsp7NEZ/COGVqx+m+50dS5QLU0ZUPjSszDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:19:42.907035Z","bundle_sha256":"9977ecbc715203270c385664e8ab2f41d83bcb31e3cda7e394164757dd3e957f"}}