{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YBT6LXP774A2CITI4RCW23TK6A","short_pith_number":"pith:YBT6LXP7","canonical_record":{"source":{"id":"2110.02523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T06:17:05Z","cross_cats_sorted":[],"title_canon_sha256":"03f5bd721a269dc6d020e2a0f95dfc403e7afb5bbb9b7b19b5b6a8a0857068bf","abstract_canon_sha256":"baae2584a0a675e1f2457e4d028c6090f5cb2838513e022f90c9867925667b7c"},"schema_version":"1.0"},"canonical_sha256":"c067e5ddffff01a12268e4456d6e6af01b02219422689f749f1ea6a587eff31a","source":{"kind":"arxiv","id":"2110.02523","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02523","created_at":"2026-07-05T03:20:27Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02523v1","created_at":"2026-07-05T03:20:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02523","created_at":"2026-07-05T03:20:27Z"},{"alias_kind":"pith_short_12","alias_value":"YBT6LXP774A2","created_at":"2026-07-05T03:20:27Z"},{"alias_kind":"pith_short_16","alias_value":"YBT6LXP774A2CITI","created_at":"2026-07-05T03:20:27Z"},{"alias_kind":"pith_short_8","alias_value":"YBT6LXP7","created_at":"2026-07-05T03:20:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YBT6LXP774A2CITI4RCW23TK6A","target":"record","payload":{"canonical_record":{"source":{"id":"2110.02523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T06:17:05Z","cross_cats_sorted":[],"title_canon_sha256":"03f5bd721a269dc6d020e2a0f95dfc403e7afb5bbb9b7b19b5b6a8a0857068bf","abstract_canon_sha256":"baae2584a0a675e1f2457e4d028c6090f5cb2838513e022f90c9867925667b7c"},"schema_version":"1.0"},"canonical_sha256":"c067e5ddffff01a12268e4456d6e6af01b02219422689f749f1ea6a587eff31a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:27.371404Z","signature_b64":"2AJFSVxHU8TaxA1OKxPx0n9bzWcFoBfD0H7+cRdemBDDsFMXosim/Hm0nN8c31ElOCakvshQufEpWIB4X8LNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c067e5ddffff01a12268e4456d6e6af01b02219422689f749f1ea6a587eff31a","last_reissued_at":"2026-07-05T03:20:27.370814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:27.370814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.02523","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":"2026-07-05T03:20:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kk+hiGuirV+wYo0pfn1Tkrz+6yDRYVO+sV1wkbdv7uaVxgw1e0glhJNwnBuCW06jLRUxGXFNAJe9eDymgdWqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:13:57.794212Z"},"content_sha256":"2a1a94c45199ac06709004f7cb975fd210d72f0e1b6b965992fb50ad4bc7985d","schema_version":"1.0","event_id":"sha256:2a1a94c45199ac06709004f7cb975fd210d72f0e1b6b965992fb50ad4bc7985d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YBT6LXP774A2CITI4RCW23TK6A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Demin Song, Linyang Li, Ruotian Ma, Xipeng Qiu, Xuanjing Huang","submitted_at":"2021-10-06T06:17:05Z","abstract_excerpt":"Pre-trained models are widely used in fine-tuning downstream tasks with linear classifiers optimized by the cross-entropy loss, which might face robustness and stability problems. These problems can be improved by learning representations that focus on similarities in the same class and contradictions in different classes when making predictions. In this paper, we utilize the K-Nearest Neighbors Classifier in pre-trained model fine-tuning. For this KNN classifier, we introduce a supervised momentum contrastive learning framework to learn the clustered representations of the supervised downstre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02523","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/2110.02523/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":"2026-07-05T03:20:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3XS4BX6YdIEdG4XR2IvQbvuXj+ufBl+JpDZpQi/sDmLf5m43klt4BcEn04/bzBe+VuEVNUGeqO8RzQoIXXz6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:13:57.794677Z"},"content_sha256":"e8d6b59e6f60391fd3ae5e2f3cf687cbb8f5af97baeff51dff0914c6c2351b93","schema_version":"1.0","event_id":"sha256:e8d6b59e6f60391fd3ae5e2f3cf687cbb8f5af97baeff51dff0914c6c2351b93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBT6LXP774A2CITI4RCW23TK6A/bundle.json","state_url":"https://pith.science/pith/YBT6LXP774A2CITI4RCW23TK6A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBT6LXP774A2CITI4RCW23TK6A/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":"2026-08-06T02:13:57Z","links":{"resolver":"https://pith.science/pith/YBT6LXP774A2CITI4RCW23TK6A","bundle":"https://pith.science/pith/YBT6LXP774A2CITI4RCW23TK6A/bundle.json","state":"https://pith.science/pith/YBT6LXP774A2CITI4RCW23TK6A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBT6LXP774A2CITI4RCW23TK6A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YBT6LXP774A2CITI4RCW23TK6A","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":"baae2584a0a675e1f2457e4d028c6090f5cb2838513e022f90c9867925667b7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T06:17:05Z","title_canon_sha256":"03f5bd721a269dc6d020e2a0f95dfc403e7afb5bbb9b7b19b5b6a8a0857068bf"},"schema_version":"1.0","source":{"id":"2110.02523","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02523","created_at":"2026-07-05T03:20:27Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02523v1","created_at":"2026-07-05T03:20:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02523","created_at":"2026-07-05T03:20:27Z"},{"alias_kind":"pith_short_12","alias_value":"YBT6LXP774A2","created_at":"2026-07-05T03:20:27Z"},{"alias_kind":"pith_short_16","alias_value":"YBT6LXP774A2CITI","created_at":"2026-07-05T03:20:27Z"},{"alias_kind":"pith_short_8","alias_value":"YBT6LXP7","created_at":"2026-07-05T03:20:27Z"}],"graph_snapshots":[{"event_id":"sha256:e8d6b59e6f60391fd3ae5e2f3cf687cbb8f5af97baeff51dff0914c6c2351b93","target":"graph","created_at":"2026-07-05T03:20:27Z","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/2110.02523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained models are widely used in fine-tuning downstream tasks with linear classifiers optimized by the cross-entropy loss, which might face robustness and stability problems. These problems can be improved by learning representations that focus on similarities in the same class and contradictions in different classes when making predictions. In this paper, we utilize the K-Nearest Neighbors Classifier in pre-trained model fine-tuning. For this KNN classifier, we introduce a supervised momentum contrastive learning framework to learn the clustered representations of the supervised downstre","authors_text":"Demin Song, Linyang Li, Ruotian Ma, Xipeng Qiu, Xuanjing Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T06:17:05Z","title":"KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02523","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":"sha256:2a1a94c45199ac06709004f7cb975fd210d72f0e1b6b965992fb50ad4bc7985d","target":"record","created_at":"2026-07-05T03:20:27Z","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":"baae2584a0a675e1f2457e4d028c6090f5cb2838513e022f90c9867925667b7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T06:17:05Z","title_canon_sha256":"03f5bd721a269dc6d020e2a0f95dfc403e7afb5bbb9b7b19b5b6a8a0857068bf"},"schema_version":"1.0","source":{"id":"2110.02523","kind":"arxiv","version":1}},"canonical_sha256":"c067e5ddffff01a12268e4456d6e6af01b02219422689f749f1ea6a587eff31a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c067e5ddffff01a12268e4456d6e6af01b02219422689f749f1ea6a587eff31a","first_computed_at":"2026-07-05T03:20:27.370814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:27.370814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2AJFSVxHU8TaxA1OKxPx0n9bzWcFoBfD0H7+cRdemBDDsFMXosim/Hm0nN8c31ElOCakvshQufEpWIB4X8LNCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:27.371404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.02523","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a1a94c45199ac06709004f7cb975fd210d72f0e1b6b965992fb50ad4bc7985d","sha256:e8d6b59e6f60391fd3ae5e2f3cf687cbb8f5af97baeff51dff0914c6c2351b93"],"state_sha256":"6a9bc042fe7e240616754095deba72e7604e388986f2ef43c70133539f0d1c40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUJXt8AIrh3n7dmD8jCGauvjpqmFotr497xEesTuJAHqh/Q4gmyvk5dxeN500nSmeRNZlpydk/1qRNlovRo6Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:13:57.797976Z","bundle_sha256":"6b1fb9b7b43cf529df309f8bf3c4516d2f6f84b17d1289e6c2ecf768f4cb95f2"}}