{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:J6SZRR6EGGFVKNKTLAE5ZZFW3I","short_pith_number":"pith:J6SZRR6E","canonical_record":{"source":{"id":"2007.06162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-13T02:53:03Z","cross_cats_sorted":[],"title_canon_sha256":"cdd3bc9e9957f310461ac899d277eeabd2567cc4ec7162c9743847c601dae93f","abstract_canon_sha256":"14f01cb748db5f81adf7d99c3dcd3974347a54c39d398d0d6036bc3781d52f2f"},"schema_version":"1.0"},"canonical_sha256":"4fa598c7c4318b5535535809dce4b6da3c6f155413991ce645ef86e236550949","source":{"kind":"arxiv","id":"2007.06162","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.06162","created_at":"2026-07-05T01:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"2007.06162v1","created_at":"2026-07-05T01:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06162","created_at":"2026-07-05T01:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"J6SZRR6EGGFV","created_at":"2026-07-05T01:18:10Z"},{"alias_kind":"pith_short_16","alias_value":"J6SZRR6EGGFVKNKT","created_at":"2026-07-05T01:18:10Z"},{"alias_kind":"pith_short_8","alias_value":"J6SZRR6E","created_at":"2026-07-05T01:18:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:J6SZRR6EGGFVKNKTLAE5ZZFW3I","target":"record","payload":{"canonical_record":{"source":{"id":"2007.06162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-13T02:53:03Z","cross_cats_sorted":[],"title_canon_sha256":"cdd3bc9e9957f310461ac899d277eeabd2567cc4ec7162c9743847c601dae93f","abstract_canon_sha256":"14f01cb748db5f81adf7d99c3dcd3974347a54c39d398d0d6036bc3781d52f2f"},"schema_version":"1.0"},"canonical_sha256":"4fa598c7c4318b5535535809dce4b6da3c6f155413991ce645ef86e236550949","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:10.521610Z","signature_b64":"mVSCsb5yHt+ePh3ooO/znBKfmxEFA2Ic0Rfc7yPNhiimE6ohS6v1wygU3r9ipHClc2havy+sauNOij+yCS/ABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fa598c7c4318b5535535809dce4b6da3c6f155413991ce645ef86e236550949","last_reissued_at":"2026-07-05T01:18:10.521194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:10.521194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.06162","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":"2026-07-05T01:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3uQJ3xNshHJgy3hLn3ywePhebpxjozQXoKo0fxx79cOvhg0IlACLDWyCzoiGZdl6YZm1zJtNOarwMzk83OheAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:08:23.210864Z"},"content_sha256":"3a467988f2b08ee9ef22c692098c1d7d59838e612a478f9d154f3919c48c5b77","schema_version":"1.0","event_id":"sha256:3a467988f2b08ee9ef22c692098c1d7d59838e612a478f9d154f3919c48c5b77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:J6SZRR6EGGFVKNKTLAE5ZZFW3I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do You Have the Right Scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Zhou, Lei Li, Ning Miao, Yuxuan Song","submitted_at":"2020-07-13T02:53:03Z","abstract_excerpt":"It has been a common approach to pre-train a language model on a large corpus and fine-tune it on task-specific data. In practice, we observe that fine-tuning a pre-trained model on a small dataset may lead to over- and/or under-estimation problem. In this paper, we propose MC-Tailor, a novel method to alleviate the above issue in text generation tasks by truncating and transferring the probability mass from over-estimated regions to under-estimated ones. Experiments on a variety of text generation datasets show that MC-Tailor consistently and significantly outperforms the fine-tuning approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06162","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/2007.06162/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":"2026-07-05T01:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ylG+oEqEyT1qtByeR4p7lmM5dP/EuyYpuwMiuBstgEru/7M8TgJyJR3lPntCD9acaprccUw/SOuVju01jZSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:08:23.211357Z"},"content_sha256":"729dc91dfde6389bc7b5e9e4d93a71bbd87e1775d33bdd5a158132c0e5824fee","schema_version":"1.0","event_id":"sha256:729dc91dfde6389bc7b5e9e4d93a71bbd87e1775d33bdd5a158132c0e5824fee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J6SZRR6EGGFVKNKTLAE5ZZFW3I/bundle.json","state_url":"https://pith.science/pith/J6SZRR6EGGFVKNKTLAE5ZZFW3I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J6SZRR6EGGFVKNKTLAE5ZZFW3I/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":"2026-08-22T15:08:23Z","links":{"resolver":"https://pith.science/pith/J6SZRR6EGGFVKNKTLAE5ZZFW3I","bundle":"https://pith.science/pith/J6SZRR6EGGFVKNKTLAE5ZZFW3I/bundle.json","state":"https://pith.science/pith/J6SZRR6EGGFVKNKTLAE5ZZFW3I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J6SZRR6EGGFVKNKTLAE5ZZFW3I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:J6SZRR6EGGFVKNKTLAE5ZZFW3I","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":"14f01cb748db5f81adf7d99c3dcd3974347a54c39d398d0d6036bc3781d52f2f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-13T02:53:03Z","title_canon_sha256":"cdd3bc9e9957f310461ac899d277eeabd2567cc4ec7162c9743847c601dae93f"},"schema_version":"1.0","source":{"id":"2007.06162","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.06162","created_at":"2026-07-05T01:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"2007.06162v1","created_at":"2026-07-05T01:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06162","created_at":"2026-07-05T01:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"J6SZRR6EGGFV","created_at":"2026-07-05T01:18:10Z"},{"alias_kind":"pith_short_16","alias_value":"J6SZRR6EGGFVKNKT","created_at":"2026-07-05T01:18:10Z"},{"alias_kind":"pith_short_8","alias_value":"J6SZRR6E","created_at":"2026-07-05T01:18:10Z"}],"graph_snapshots":[{"event_id":"sha256:729dc91dfde6389bc7b5e9e4d93a71bbd87e1775d33bdd5a158132c0e5824fee","target":"graph","created_at":"2026-07-05T01:18:10Z","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/2007.06162/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It has been a common approach to pre-train a language model on a large corpus and fine-tune it on task-specific data. In practice, we observe that fine-tuning a pre-trained model on a small dataset may lead to over- and/or under-estimation problem. In this paper, we propose MC-Tailor, a novel method to alleviate the above issue in text generation tasks by truncating and transferring the probability mass from over-estimated regions to under-estimated ones. Experiments on a variety of text generation datasets show that MC-Tailor consistently and significantly outperforms the fine-tuning approach","authors_text":"Hao Zhou, Lei Li, Ning Miao, Yuxuan Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-13T02:53:03Z","title":"Do You Have the Right Scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06162","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":"sha256:3a467988f2b08ee9ef22c692098c1d7d59838e612a478f9d154f3919c48c5b77","target":"record","created_at":"2026-07-05T01:18:10Z","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":"14f01cb748db5f81adf7d99c3dcd3974347a54c39d398d0d6036bc3781d52f2f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-13T02:53:03Z","title_canon_sha256":"cdd3bc9e9957f310461ac899d277eeabd2567cc4ec7162c9743847c601dae93f"},"schema_version":"1.0","source":{"id":"2007.06162","kind":"arxiv","version":1}},"canonical_sha256":"4fa598c7c4318b5535535809dce4b6da3c6f155413991ce645ef86e236550949","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fa598c7c4318b5535535809dce4b6da3c6f155413991ce645ef86e236550949","first_computed_at":"2026-07-05T01:18:10.521194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:18:10.521194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mVSCsb5yHt+ePh3ooO/znBKfmxEFA2Ic0Rfc7yPNhiimE6ohS6v1wygU3r9ipHClc2havy+sauNOij+yCS/ABA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:18:10.521610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.06162","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a467988f2b08ee9ef22c692098c1d7d59838e612a478f9d154f3919c48c5b77","sha256:729dc91dfde6389bc7b5e9e4d93a71bbd87e1775d33bdd5a158132c0e5824fee"],"state_sha256":"037344ded4f12fa1d65b11768f14640a110a0779dcaf91a0580d7d16901848b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2jt51y/hjHZqNOpCe7j56M67NgV0+suAJV6MT2cp1ulelHXt1LbV9v5ewDs9HK3QBxxqOQoomImKfzUvuC4UDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T15:08:23.215075Z","bundle_sha256":"b375b9c02bb68eed93d6c2e745d573482705fcad299fe8abc4064f97691a15f0"}}