{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SRDZJWDYEFZEHOVYX7ON54C5YJ","short_pith_number":"pith:SRDZJWDY","canonical_record":{"source":{"id":"2305.13862","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T09:35:37Z","cross_cats_sorted":[],"title_canon_sha256":"f7b5e3b63321779616326fa6943800031ecda8888cf160d5a9e0f48733c31bcb","abstract_canon_sha256":"288da635bfe668cd1e535617a5a4dfbf91c582b005ffb80f23edaf8f7847b29f"},"schema_version":"1.0"},"canonical_sha256":"944794d878217243bab8bfdcdef05dc264a007b4b0518dc4041ef7dfe42cfc07","source":{"kind":"arxiv","id":"2305.13862","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13862","created_at":"2026-07-05T09:33:07Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13862v2","created_at":"2026-07-05T09:33:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13862","created_at":"2026-07-05T09:33:07Z"},{"alias_kind":"pith_short_12","alias_value":"SRDZJWDYEFZE","created_at":"2026-07-05T09:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"SRDZJWDYEFZEHOVY","created_at":"2026-07-05T09:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"SRDZJWDY","created_at":"2026-07-05T09:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SRDZJWDYEFZEHOVYX7ON54C5YJ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13862","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T09:35:37Z","cross_cats_sorted":[],"title_canon_sha256":"f7b5e3b63321779616326fa6943800031ecda8888cf160d5a9e0f48733c31bcb","abstract_canon_sha256":"288da635bfe668cd1e535617a5a4dfbf91c582b005ffb80f23edaf8f7847b29f"},"schema_version":"1.0"},"canonical_sha256":"944794d878217243bab8bfdcdef05dc264a007b4b0518dc4041ef7dfe42cfc07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:07.442336Z","signature_b64":"Tdhqtt4EIQxOiCUFfqqVFmEEF+FSszPTBR6hlirqq5qzHEn0CO3a8r65U2ghMsHCAlvX3zxdupdCGz2i5Es+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"944794d878217243bab8bfdcdef05dc264a007b4b0518dc4041ef7dfe42cfc07","last_reissued_at":"2026-07-05T09:33:07.441462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:07.441462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13862","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":"2026-07-05T09:33:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zoptQ+M+H414kFBiUuSiJCYQZUpBVCt35RLu2fA8t98qUWfCM6s1OPkSp4JYqb3W9gyOGN8tJZOZ18Ib7fiuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:04:39.478579Z"},"content_sha256":"c100cb407431491d9cd9a44abb5701836dfa2e1e0b611982261469ea3f4af451","schema_version":"1.0","event_id":"sha256:c100cb407431491d9cd9a44abb5701836dfa2e1e0b611982261469ea3f4af451"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SRDZJWDYEFZEHOVYX7ON54C5YJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Trip Towards Fairness: Bias and De-Biasing in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dario Onorati, Davide Venditti, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto, Leonardo Ranaldi","submitted_at":"2023-05-23T09:35:37Z","abstract_excerpt":"Cheap-to-Build Very Large-Language Models (CtB-LLMs) with affordable training are emerging as the next big revolution in natural language processing and understanding. These CtB-LLMs are democratizing access to trainable Very Large-Language Models (VLLMs) and, thus, may represent the building blocks of many NLP systems solving downstream tasks. Hence, a little or a large bias in CtB-LLMs may cause huge harm. In this paper, we performed a large investigation of the bias of three families of CtB-LLMs, and we showed that debiasing techniques are effective and usable. Indeed, according to current "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13862","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/2305.13862/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":"2026-07-05T09:33:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vBpfdjYS96gP4xIKZTqiOeQABHR9EcOE23YI2YtIHdjhFetz707+Jt60JDP0kJWPbmljrGLf84Q8AacHK904DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:04:39.479105Z"},"content_sha256":"303cf925e57842a67af5969bfaf237dfecaf40aeafc750b26f4ca66111cbb1e7","schema_version":"1.0","event_id":"sha256:303cf925e57842a67af5969bfaf237dfecaf40aeafc750b26f4ca66111cbb1e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRDZJWDYEFZEHOVYX7ON54C5YJ/bundle.json","state_url":"https://pith.science/pith/SRDZJWDYEFZEHOVYX7ON54C5YJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRDZJWDYEFZEHOVYX7ON54C5YJ/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":"2026-08-10T11:04:39Z","links":{"resolver":"https://pith.science/pith/SRDZJWDYEFZEHOVYX7ON54C5YJ","bundle":"https://pith.science/pith/SRDZJWDYEFZEHOVYX7ON54C5YJ/bundle.json","state":"https://pith.science/pith/SRDZJWDYEFZEHOVYX7ON54C5YJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRDZJWDYEFZEHOVYX7ON54C5YJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SRDZJWDYEFZEHOVYX7ON54C5YJ","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":"288da635bfe668cd1e535617a5a4dfbf91c582b005ffb80f23edaf8f7847b29f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T09:35:37Z","title_canon_sha256":"f7b5e3b63321779616326fa6943800031ecda8888cf160d5a9e0f48733c31bcb"},"schema_version":"1.0","source":{"id":"2305.13862","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13862","created_at":"2026-07-05T09:33:07Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13862v2","created_at":"2026-07-05T09:33:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13862","created_at":"2026-07-05T09:33:07Z"},{"alias_kind":"pith_short_12","alias_value":"SRDZJWDYEFZE","created_at":"2026-07-05T09:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"SRDZJWDYEFZEHOVY","created_at":"2026-07-05T09:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"SRDZJWDY","created_at":"2026-07-05T09:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:303cf925e57842a67af5969bfaf237dfecaf40aeafc750b26f4ca66111cbb1e7","target":"graph","created_at":"2026-07-05T09:33:07Z","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/2305.13862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cheap-to-Build Very Large-Language Models (CtB-LLMs) with affordable training are emerging as the next big revolution in natural language processing and understanding. These CtB-LLMs are democratizing access to trainable Very Large-Language Models (VLLMs) and, thus, may represent the building blocks of many NLP systems solving downstream tasks. Hence, a little or a large bias in CtB-LLMs may cause huge harm. In this paper, we performed a large investigation of the bias of three families of CtB-LLMs, and we showed that debiasing techniques are effective and usable. Indeed, according to current ","authors_text":"Dario Onorati, Davide Venditti, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto, Leonardo Ranaldi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T09:35:37Z","title":"A Trip Towards Fairness: Bias and De-Biasing in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13862","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:c100cb407431491d9cd9a44abb5701836dfa2e1e0b611982261469ea3f4af451","target":"record","created_at":"2026-07-05T09:33:07Z","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":"288da635bfe668cd1e535617a5a4dfbf91c582b005ffb80f23edaf8f7847b29f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T09:35:37Z","title_canon_sha256":"f7b5e3b63321779616326fa6943800031ecda8888cf160d5a9e0f48733c31bcb"},"schema_version":"1.0","source":{"id":"2305.13862","kind":"arxiv","version":2}},"canonical_sha256":"944794d878217243bab8bfdcdef05dc264a007b4b0518dc4041ef7dfe42cfc07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"944794d878217243bab8bfdcdef05dc264a007b4b0518dc4041ef7dfe42cfc07","first_computed_at":"2026-07-05T09:33:07.441462Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:07.441462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tdhqtt4EIQxOiCUFfqqVFmEEF+FSszPTBR6hlirqq5qzHEn0CO3a8r65U2ghMsHCAlvX3zxdupdCGz2i5Es+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:07.442336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13862","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c100cb407431491d9cd9a44abb5701836dfa2e1e0b611982261469ea3f4af451","sha256:303cf925e57842a67af5969bfaf237dfecaf40aeafc750b26f4ca66111cbb1e7"],"state_sha256":"87ef6bb6a2bc2af750e7a9670c2b25ead67fdd0d5e550d8169545ee4c585f585"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AiTjKe8NwWglh8THlYwxOTHo0t7/mL4F3jAlmKXYOK6wK/Gz3p7N/Upy2GA731XJvDb0g+pCzgl+3BXQml9NCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:04:39.484393Z","bundle_sha256":"17ffb8aa6e4b46392a595057c4ccf9c8936119d854b85ea3abaff6508a89408b"}}