{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QG64XKDKJB5Z4KGX4BYWJYYCMN","short_pith_number":"pith:QG64XKDK","canonical_record":{"source":{"id":"2310.03400","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T09:09:44Z","cross_cats_sorted":[],"title_canon_sha256":"72abb2eb059bb9c035f58e38ff73faa27a407935263f7c5610aec81dae6de914","abstract_canon_sha256":"bbdda29d66190929ca158d5fc3d16c2a80b469dbdcc21b6078a4060c54205c6c"},"schema_version":"1.0"},"canonical_sha256":"81bdcba86a487b9e28d7e07164e302637c2dfec28058008ee692dc7654dc093a","source":{"kind":"arxiv","id":"2310.03400","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03400","created_at":"2026-07-05T07:53:11Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03400v2","created_at":"2026-07-05T07:53:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03400","created_at":"2026-07-05T07:53:11Z"},{"alias_kind":"pith_short_12","alias_value":"QG64XKDKJB5Z","created_at":"2026-07-05T07:53:11Z"},{"alias_kind":"pith_short_16","alias_value":"QG64XKDKJB5Z4KGX","created_at":"2026-07-05T07:53:11Z"},{"alias_kind":"pith_short_8","alias_value":"QG64XKDK","created_at":"2026-07-05T07:53:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QG64XKDKJB5Z4KGX4BYWJYYCMN","target":"record","payload":{"canonical_record":{"source":{"id":"2310.03400","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T09:09:44Z","cross_cats_sorted":[],"title_canon_sha256":"72abb2eb059bb9c035f58e38ff73faa27a407935263f7c5610aec81dae6de914","abstract_canon_sha256":"bbdda29d66190929ca158d5fc3d16c2a80b469dbdcc21b6078a4060c54205c6c"},"schema_version":"1.0"},"canonical_sha256":"81bdcba86a487b9e28d7e07164e302637c2dfec28058008ee692dc7654dc093a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:11.374252Z","signature_b64":"cmaSinV1EgJK+sZtz7CQgJv78lsDK0/Bw767HP1cs79tCUK7EzVnkzAE//el5C9RIpg+YbkrdvLMJ7EBa8GGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81bdcba86a487b9e28d7e07164e302637c2dfec28058008ee692dc7654dc093a","last_reissued_at":"2026-07-05T07:53:11.373771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:11.373771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.03400","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":"2026-07-05T07:53:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"brXIVMOuZ84PzD3KL8UFubsusOkmzWEQfAoK9CNdLmtLnMd7dz32m270y3WuO2APjhMhVYCE9kz4SDXuFBCUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:33:10.531742Z"},"content_sha256":"abf56c1cb52a230ec79252dcf3a60bdc180dc217acc496eaabf8f1e516aaabf5","schema_version":"1.0","event_id":"sha256:abf56c1cb52a230ec79252dcf3a60bdc180dc217acc496eaabf8f1e516aaabf5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QG64XKDKJB5Z4KGX4BYWJYYCMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingzhe Wu, Changqing Zhang, Huan Ma, Huazhu Fu, Peilin Zhao","submitted_at":"2023-10-05T09:09:44Z","abstract_excerpt":"Nowadays, billions of people engage in communication and express their opinions on the internet daily. Unfortunately, not all of these expressions are friendly or compliant, making content moderation an indispensable task. A common approach is to use a discriminative model to classify the content, but this method often requires strict data engineering, otherwise it will face unacceptable overfitting. With the successful development of Large Language Models (LLMs) in recent years, LLM-based methods have become a feasible solution for handling tasks in various domains. Thanks to the knowledge of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03400","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/2310.03400/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":"2026-07-05T07:53:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Q2fAE1XXtC2FRKN68idHN3bgCrCWpZtxWrPdG7vMfR3KPcDXJLLY8YsHYVepemnEp+soQ1+7bh/DM+UBDt+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:33:10.532442Z"},"content_sha256":"8cd6fdfdfa80b2d4aa98c05affae6a5e27f2980b6685404e54194a823fbc1f4f","schema_version":"1.0","event_id":"sha256:8cd6fdfdfa80b2d4aa98c05affae6a5e27f2980b6685404e54194a823fbc1f4f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QG64XKDKJB5Z4KGX4BYWJYYCMN/bundle.json","state_url":"https://pith.science/pith/QG64XKDKJB5Z4KGX4BYWJYYCMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QG64XKDKJB5Z4KGX4BYWJYYCMN/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":"2026-08-09T09:33:10Z","links":{"resolver":"https://pith.science/pith/QG64XKDKJB5Z4KGX4BYWJYYCMN","bundle":"https://pith.science/pith/QG64XKDKJB5Z4KGX4BYWJYYCMN/bundle.json","state":"https://pith.science/pith/QG64XKDKJB5Z4KGX4BYWJYYCMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QG64XKDKJB5Z4KGX4BYWJYYCMN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QG64XKDKJB5Z4KGX4BYWJYYCMN","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":"bbdda29d66190929ca158d5fc3d16c2a80b469dbdcc21b6078a4060c54205c6c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T09:09:44Z","title_canon_sha256":"72abb2eb059bb9c035f58e38ff73faa27a407935263f7c5610aec81dae6de914"},"schema_version":"1.0","source":{"id":"2310.03400","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03400","created_at":"2026-07-05T07:53:11Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03400v2","created_at":"2026-07-05T07:53:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03400","created_at":"2026-07-05T07:53:11Z"},{"alias_kind":"pith_short_12","alias_value":"QG64XKDKJB5Z","created_at":"2026-07-05T07:53:11Z"},{"alias_kind":"pith_short_16","alias_value":"QG64XKDKJB5Z4KGX","created_at":"2026-07-05T07:53:11Z"},{"alias_kind":"pith_short_8","alias_value":"QG64XKDK","created_at":"2026-07-05T07:53:11Z"}],"graph_snapshots":[{"event_id":"sha256:8cd6fdfdfa80b2d4aa98c05affae6a5e27f2980b6685404e54194a823fbc1f4f","target":"graph","created_at":"2026-07-05T07:53:11Z","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/2310.03400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Nowadays, billions of people engage in communication and express their opinions on the internet daily. Unfortunately, not all of these expressions are friendly or compliant, making content moderation an indispensable task. A common approach is to use a discriminative model to classify the content, but this method often requires strict data engineering, otherwise it will face unacceptable overfitting. With the successful development of Large Language Models (LLMs) in recent years, LLM-based methods have become a feasible solution for handling tasks in various domains. Thanks to the knowledge of","authors_text":"Bingzhe Wu, Changqing Zhang, Huan Ma, Huazhu Fu, Peilin Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T09:09:44Z","title":"Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03400","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:abf56c1cb52a230ec79252dcf3a60bdc180dc217acc496eaabf8f1e516aaabf5","target":"record","created_at":"2026-07-05T07:53:11Z","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":"bbdda29d66190929ca158d5fc3d16c2a80b469dbdcc21b6078a4060c54205c6c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T09:09:44Z","title_canon_sha256":"72abb2eb059bb9c035f58e38ff73faa27a407935263f7c5610aec81dae6de914"},"schema_version":"1.0","source":{"id":"2310.03400","kind":"arxiv","version":2}},"canonical_sha256":"81bdcba86a487b9e28d7e07164e302637c2dfec28058008ee692dc7654dc093a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81bdcba86a487b9e28d7e07164e302637c2dfec28058008ee692dc7654dc093a","first_computed_at":"2026-07-05T07:53:11.373771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:11.373771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cmaSinV1EgJK+sZtz7CQgJv78lsDK0/Bw767HP1cs79tCUK7EzVnkzAE//el5C9RIpg+YbkrdvLMJ7EBa8GGBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:11.374252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03400","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abf56c1cb52a230ec79252dcf3a60bdc180dc217acc496eaabf8f1e516aaabf5","sha256:8cd6fdfdfa80b2d4aa98c05affae6a5e27f2980b6685404e54194a823fbc1f4f"],"state_sha256":"e8a9dbe4e5fcfe3cd9593e0a861dd9a64b68d0ae2faf06b2cfa2baaf01d6cd0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IGzndbJQR9Rc+54JJlSzavkiD2C5FGfsq8Aw+b/MQc8hhcANi9G8RJYjPFb4gB0Pbj+EGnIQmzlyL+urNweMCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:33:10.537813Z","bundle_sha256":"73afc13ef6b720cf2d130e9cb7f88bea7238ff9872f0f861fa0e27db5863565a"}}