{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:WEJBYLHMC6UYG7IP474PUUAZPV","short_pith_number":"pith:WEJBYLHM","canonical_record":{"source":{"id":"2211.08794","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T09:39:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1f682327c3714b0ee729351ac04829da23083b2c0c34f795ce2efb24c3c2ad08","abstract_canon_sha256":"c7e4fa88630892a7bb7bd00ff0007ebf9c535521a16593614ea5f13fd923a989"},"schema_version":"1.0"},"canonical_sha256":"b1121c2cec17a9837d0fe7f8fa50197d7f0281fff1d09dca02c35680bcd25a89","source":{"kind":"arxiv","id":"2211.08794","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.08794","created_at":"2026-07-05T06:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"2211.08794v4","created_at":"2026-07-05T06:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08794","created_at":"2026-07-05T06:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"WEJBYLHMC6UY","created_at":"2026-07-05T06:14:06Z"},{"alias_kind":"pith_short_16","alias_value":"WEJBYLHMC6UYG7IP","created_at":"2026-07-05T06:14:06Z"},{"alias_kind":"pith_short_8","alias_value":"WEJBYLHM","created_at":"2026-07-05T06:14:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:WEJBYLHMC6UYG7IP474PUUAZPV","target":"record","payload":{"canonical_record":{"source":{"id":"2211.08794","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T09:39:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1f682327c3714b0ee729351ac04829da23083b2c0c34f795ce2efb24c3c2ad08","abstract_canon_sha256":"c7e4fa88630892a7bb7bd00ff0007ebf9c535521a16593614ea5f13fd923a989"},"schema_version":"1.0"},"canonical_sha256":"b1121c2cec17a9837d0fe7f8fa50197d7f0281fff1d09dca02c35680bcd25a89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:06.626787Z","signature_b64":"294CtuFKp+fSyzYf3k4u0UCCSHb30neSKwLpv9mUuhwqVa2+M5GnMUXvtJovwejGEV9JerkZRREdWq3VbWryAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1121c2cec17a9837d0fe7f8fa50197d7f0281fff1d09dca02c35680bcd25a89","last_reissued_at":"2026-07-05T06:14:06.626348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:06.626348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.08794","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RZzPwnzW9Kwp15s9dwGFJiGqnj6WriV+Gq11dsgEK8pgjeo+c5Ew7JdGhdwLiz9gtTakPJnn7S3sowh7bmH+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:16:05.170656Z"},"content_sha256":"78d7690da5554bde19f66c053debecd440c27c0d73cdb076015826226f765747","schema_version":"1.0","event_id":"sha256:78d7690da5554bde19f66c053debecd440c27c0d73cdb076015826226f765747"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:WEJBYLHMC6UYG7IP474PUUAZPV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Lidong Bing, Linlin Liu, Luo Si, Megh Thakkar, Shafiq Joty, Xingxuan Li, Xin Li","submitted_at":"2022-11-16T09:39:29Z","abstract_excerpt":"Due to the huge amount of parameters, fine-tuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios. In this work, we present a novel method that operates on the hidden representations of a PLM to reduce overfitting. During fine-tuning, our method inserts random autoencoders between the hidden layers of a PLM, which transform activations from the previous layers into multi-view compressed representations before feeding them into the upper layers. The autoencoders are plugged out after fine-tuning, so our method does not add extra parameters or increase "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08794","kind":"arxiv","version":4},"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/2211.08794/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":"2026-07-05T06:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lVOPXU/qiGYSGIN6IQeWfO4G3boQqIKTKvKaa4VL0JZ2Us7pvIUJrDcCeluP5rWQhtuomkfzjaDApy4PjAcMDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:16:05.171065Z"},"content_sha256":"4a8858fbe2dd4a448e6339d5147e308109996440f4c25710b32dc44b2044c9bf","schema_version":"1.0","event_id":"sha256:4a8858fbe2dd4a448e6339d5147e308109996440f4c25710b32dc44b2044c9bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WEJBYLHMC6UYG7IP474PUUAZPV/bundle.json","state_url":"https://pith.science/pith/WEJBYLHMC6UYG7IP474PUUAZPV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WEJBYLHMC6UYG7IP474PUUAZPV/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":"2026-08-07T17:16:05Z","links":{"resolver":"https://pith.science/pith/WEJBYLHMC6UYG7IP474PUUAZPV","bundle":"https://pith.science/pith/WEJBYLHMC6UYG7IP474PUUAZPV/bundle.json","state":"https://pith.science/pith/WEJBYLHMC6UYG7IP474PUUAZPV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WEJBYLHMC6UYG7IP474PUUAZPV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WEJBYLHMC6UYG7IP474PUUAZPV","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":"c7e4fa88630892a7bb7bd00ff0007ebf9c535521a16593614ea5f13fd923a989","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T09:39:29Z","title_canon_sha256":"1f682327c3714b0ee729351ac04829da23083b2c0c34f795ce2efb24c3c2ad08"},"schema_version":"1.0","source":{"id":"2211.08794","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.08794","created_at":"2026-07-05T06:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"2211.08794v4","created_at":"2026-07-05T06:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08794","created_at":"2026-07-05T06:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"WEJBYLHMC6UY","created_at":"2026-07-05T06:14:06Z"},{"alias_kind":"pith_short_16","alias_value":"WEJBYLHMC6UYG7IP","created_at":"2026-07-05T06:14:06Z"},{"alias_kind":"pith_short_8","alias_value":"WEJBYLHM","created_at":"2026-07-05T06:14:06Z"}],"graph_snapshots":[{"event_id":"sha256:4a8858fbe2dd4a448e6339d5147e308109996440f4c25710b32dc44b2044c9bf","target":"graph","created_at":"2026-07-05T06:14:06Z","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/2211.08794/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Due to the huge amount of parameters, fine-tuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios. In this work, we present a novel method that operates on the hidden representations of a PLM to reduce overfitting. During fine-tuning, our method inserts random autoencoders between the hidden layers of a PLM, which transform activations from the previous layers into multi-view compressed representations before feeding them into the upper layers. The autoencoders are plugged out after fine-tuning, so our method does not add extra parameters or increase ","authors_text":"Lidong Bing, Linlin Liu, Luo Si, Megh Thakkar, Shafiq Joty, Xingxuan Li, Xin Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T09:39:29Z","title":"Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08794","kind":"arxiv","version":4},"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":"sha256:78d7690da5554bde19f66c053debecd440c27c0d73cdb076015826226f765747","target":"record","created_at":"2026-07-05T06:14:06Z","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":"c7e4fa88630892a7bb7bd00ff0007ebf9c535521a16593614ea5f13fd923a989","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T09:39:29Z","title_canon_sha256":"1f682327c3714b0ee729351ac04829da23083b2c0c34f795ce2efb24c3c2ad08"},"schema_version":"1.0","source":{"id":"2211.08794","kind":"arxiv","version":4}},"canonical_sha256":"b1121c2cec17a9837d0fe7f8fa50197d7f0281fff1d09dca02c35680bcd25a89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1121c2cec17a9837d0fe7f8fa50197d7f0281fff1d09dca02c35680bcd25a89","first_computed_at":"2026-07-05T06:14:06.626348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:06.626348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"294CtuFKp+fSyzYf3k4u0UCCSHb30neSKwLpv9mUuhwqVa2+M5GnMUXvtJovwejGEV9JerkZRREdWq3VbWryAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:06.626787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.08794","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78d7690da5554bde19f66c053debecd440c27c0d73cdb076015826226f765747","sha256:4a8858fbe2dd4a448e6339d5147e308109996440f4c25710b32dc44b2044c9bf"],"state_sha256":"2d5b31dce2455ad6a3e36850dcd4d33d428fd6149ae90b7dcde5a1b8eaa9b3bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qRRCLrvS+dGLC9pZoieoGp3A0dwYUdC7NjilVexkNfRBeSBSMliGKoZ8XFYyUR705HwyE4XEE9EphMpZt6snAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:16:05.174061Z","bundle_sha256":"7a062f63273d3ebca2bc3515454ee39e57fad0253cc29887869216d3e33f3b53"}}