{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RCKS7M3YUG7BA65GLAX5VWD7QM","short_pith_number":"pith:RCKS7M3Y","canonical_record":{"source":{"id":"2306.04735","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T19:11:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8cea84d288b0f41719f541e422d32d734420624814f7cdebf23cca4ea246d83e","abstract_canon_sha256":"d17b50ff51b1c69820e8090b0195516a3254b8abd4cd2b50e9f829ecb9ead361"},"schema_version":"1.0"},"canonical_sha256":"88952fb378a1be107ba6582fdad87f831406eef6b183df7d91e8ad41f1033ea4","source":{"kind":"arxiv","id":"2306.04735","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04735","created_at":"2026-07-05T07:52:10Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04735v2","created_at":"2026-07-05T07:52:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04735","created_at":"2026-07-05T07:52:10Z"},{"alias_kind":"pith_short_12","alias_value":"RCKS7M3YUG7B","created_at":"2026-07-05T07:52:10Z"},{"alias_kind":"pith_short_16","alias_value":"RCKS7M3YUG7BA65G","created_at":"2026-07-05T07:52:10Z"},{"alias_kind":"pith_short_8","alias_value":"RCKS7M3Y","created_at":"2026-07-05T07:52:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RCKS7M3YUG7BA65GLAX5VWD7QM","target":"record","payload":{"canonical_record":{"source":{"id":"2306.04735","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T19:11:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8cea84d288b0f41719f541e422d32d734420624814f7cdebf23cca4ea246d83e","abstract_canon_sha256":"d17b50ff51b1c69820e8090b0195516a3254b8abd4cd2b50e9f829ecb9ead361"},"schema_version":"1.0"},"canonical_sha256":"88952fb378a1be107ba6582fdad87f831406eef6b183df7d91e8ad41f1033ea4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:10.273344Z","signature_b64":"cYnZMne0gLS72RU9k2dU5Tc3F6hp5SV616Ml67PIBzCK4u3G/AKg/nfwvMXV3s0srS83O8SJTcKgUkocvyE2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88952fb378a1be107ba6582fdad87f831406eef6b183df7d91e8ad41f1033ea4","last_reissued_at":"2026-07-05T07:52:10.272879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:10.272879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.04735","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":"2026-07-05T07:52:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gn8Pw9dA/2HV4hwpWIVnAqmyCstXJm/wpL+6aLtBa21KC0h4AZmIJhoK+7ijfmnwrTxQnj+tc7pU4aoehRrQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:11:38.619178Z"},"content_sha256":"f74a5bbd4cf67cb6e3823392da0a838d461591776c43c9677ee09de0aa939b69","schema_version":"1.0","event_id":"sha256:f74a5bbd4cf67cb6e3823392da0a838d461591776c43c9677ee09de0aa939b69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RCKS7M3YUG7BA65GLAX5VWD7QM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Soft-prompt Tuning for Large Language Models to Evaluate Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Emerson, Deval Pandya, Faiza Khan Khattak, Jacob-Junqi Tian, Laleh Seyyed-Kalantari, Sevil Zanjani Miyandoab","submitted_at":"2023-06-07T19:11:25Z","abstract_excerpt":"Prompting large language models has gained immense popularity in recent years due to the advantage of producing good results even without the need for labelled data. However, this requires prompt tuning to get optimal prompts that lead to better model performances. In this paper, we explore the use of soft-prompt tuning on sentiment classification task to quantify the biases of large language models (LLMs) such as Open Pre-trained Transformers (OPT) and Galactica language model. Since these models are trained on real-world data that could be prone to bias toward certain groups of populations, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04735","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/2306.04735/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":"2026-07-05T07:52:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oYVJFZ/GkSnXNhQh1KWd1oy+CeeqO0EArKKALcdtfEETNizdLDqAKD0XVRtc7VyTO3yKbUKRLuqciEmVKGjeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:11:38.619982Z"},"content_sha256":"8928cb793b8952891503f6322cea5b186129e2a4d41ee847a35252d31f3f3eaf","schema_version":"1.0","event_id":"sha256:8928cb793b8952891503f6322cea5b186129e2a4d41ee847a35252d31f3f3eaf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RCKS7M3YUG7BA65GLAX5VWD7QM/bundle.json","state_url":"https://pith.science/pith/RCKS7M3YUG7BA65GLAX5VWD7QM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RCKS7M3YUG7BA65GLAX5VWD7QM/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":"2026-08-17T17:11:38Z","links":{"resolver":"https://pith.science/pith/RCKS7M3YUG7BA65GLAX5VWD7QM","bundle":"https://pith.science/pith/RCKS7M3YUG7BA65GLAX5VWD7QM/bundle.json","state":"https://pith.science/pith/RCKS7M3YUG7BA65GLAX5VWD7QM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RCKS7M3YUG7BA65GLAX5VWD7QM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RCKS7M3YUG7BA65GLAX5VWD7QM","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":"d17b50ff51b1c69820e8090b0195516a3254b8abd4cd2b50e9f829ecb9ead361","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T19:11:25Z","title_canon_sha256":"8cea84d288b0f41719f541e422d32d734420624814f7cdebf23cca4ea246d83e"},"schema_version":"1.0","source":{"id":"2306.04735","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04735","created_at":"2026-07-05T07:52:10Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04735v2","created_at":"2026-07-05T07:52:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04735","created_at":"2026-07-05T07:52:10Z"},{"alias_kind":"pith_short_12","alias_value":"RCKS7M3YUG7B","created_at":"2026-07-05T07:52:10Z"},{"alias_kind":"pith_short_16","alias_value":"RCKS7M3YUG7BA65G","created_at":"2026-07-05T07:52:10Z"},{"alias_kind":"pith_short_8","alias_value":"RCKS7M3Y","created_at":"2026-07-05T07:52:10Z"}],"graph_snapshots":[{"event_id":"sha256:8928cb793b8952891503f6322cea5b186129e2a4d41ee847a35252d31f3f3eaf","target":"graph","created_at":"2026-07-05T07:52:10Z","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/2306.04735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompting large language models has gained immense popularity in recent years due to the advantage of producing good results even without the need for labelled data. However, this requires prompt tuning to get optimal prompts that lead to better model performances. In this paper, we explore the use of soft-prompt tuning on sentiment classification task to quantify the biases of large language models (LLMs) such as Open Pre-trained Transformers (OPT) and Galactica language model. Since these models are trained on real-world data that could be prone to bias toward certain groups of populations, ","authors_text":"David Emerson, Deval Pandya, Faiza Khan Khattak, Jacob-Junqi Tian, Laleh Seyyed-Kalantari, Sevil Zanjani Miyandoab","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T19:11:25Z","title":"Soft-prompt Tuning for Large Language Models to Evaluate Bias"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04735","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:f74a5bbd4cf67cb6e3823392da0a838d461591776c43c9677ee09de0aa939b69","target":"record","created_at":"2026-07-05T07:52:10Z","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":"d17b50ff51b1c69820e8090b0195516a3254b8abd4cd2b50e9f829ecb9ead361","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T19:11:25Z","title_canon_sha256":"8cea84d288b0f41719f541e422d32d734420624814f7cdebf23cca4ea246d83e"},"schema_version":"1.0","source":{"id":"2306.04735","kind":"arxiv","version":2}},"canonical_sha256":"88952fb378a1be107ba6582fdad87f831406eef6b183df7d91e8ad41f1033ea4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88952fb378a1be107ba6582fdad87f831406eef6b183df7d91e8ad41f1033ea4","first_computed_at":"2026-07-05T07:52:10.272879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:10.272879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cYnZMne0gLS72RU9k2dU5Tc3F6hp5SV616Ml67PIBzCK4u3G/AKg/nfwvMXV3s0srS83O8SJTcKgUkocvyE2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:10.273344Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04735","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f74a5bbd4cf67cb6e3823392da0a838d461591776c43c9677ee09de0aa939b69","sha256:8928cb793b8952891503f6322cea5b186129e2a4d41ee847a35252d31f3f3eaf"],"state_sha256":"563ef7037c78e31e7501e146411cb3580828fa865d4e9d919b84b0faca914419"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IQpsvZEJbmcyNZ5UEIBuZvOwA7KOMrWDg6fHOZ3gBB6YcuUsajkV5E7SXTL3ggsA+O6JhzN+oNsaH1cQkoVPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T17:11:38.626067Z","bundle_sha256":"4ffad37516ce695a835d6959b513cf64f252877e893965b0e734e66faa77e38e"}}