{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BW4PYTEKM4SMQPJ5URAGQSNP2F","short_pith_number":"pith:BW4PYTEK","canonical_record":{"source":{"id":"2405.11290","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-18T13:31:12Z","cross_cats_sorted":[],"title_canon_sha256":"31a16589d7a45bbc57476214eed6512c7728883742510fd044ffd04600bed033","abstract_canon_sha256":"2597f3fdd940cf4e9e39ad912b86522d0052f6a61863b6b23dc7a81a75ac6a1f"},"schema_version":"1.0"},"canonical_sha256":"0db8fc4c8a6724c83d3da4406849afd14c1d2790a6683d38d820b8e455d10ed2","source":{"kind":"arxiv","id":"2405.11290","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11290","created_at":"2026-07-05T08:37:52Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11290v3","created_at":"2026-07-05T08:37:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11290","created_at":"2026-07-05T08:37:52Z"},{"alias_kind":"pith_short_12","alias_value":"BW4PYTEKM4SM","created_at":"2026-07-05T08:37:52Z"},{"alias_kind":"pith_short_16","alias_value":"BW4PYTEKM4SMQPJ5","created_at":"2026-07-05T08:37:52Z"},{"alias_kind":"pith_short_8","alias_value":"BW4PYTEK","created_at":"2026-07-05T08:37:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BW4PYTEKM4SMQPJ5URAGQSNP2F","target":"record","payload":{"canonical_record":{"source":{"id":"2405.11290","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-18T13:31:12Z","cross_cats_sorted":[],"title_canon_sha256":"31a16589d7a45bbc57476214eed6512c7728883742510fd044ffd04600bed033","abstract_canon_sha256":"2597f3fdd940cf4e9e39ad912b86522d0052f6a61863b6b23dc7a81a75ac6a1f"},"schema_version":"1.0"},"canonical_sha256":"0db8fc4c8a6724c83d3da4406849afd14c1d2790a6683d38d820b8e455d10ed2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:52.883028Z","signature_b64":"Z6XXXc7jGepH/6MzIa0XxcYA0nB3cy3ElNV9rjJzVyomz9DPnRDdJv3wdzzupDzqy06QV0MlWPB/mc0iqvLgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0db8fc4c8a6724c83d3da4406849afd14c1d2790a6683d38d820b8e455d10ed2","last_reissued_at":"2026-07-05T08:37:52.882509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:52.882509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.11290","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:37:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SlUktl1dn/MwxcwPY2Iz0D4duocysIvD4wAAJrzBsxYIkg3wSL+3yg3jV9Pbe6L0B1ePWdgm2JotCsozmqcHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T07:50:47.400046Z"},"content_sha256":"34e46ae2eed2a6cb9847a14fa0dd3d7f50ac3774722370f783bf51025f868668","schema_version":"1.0","event_id":"sha256:34e46ae2eed2a6cb9847a14fa0dd3d7f50ac3774722370f783bf51025f868668"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BW4PYTEKM4SMQPJ5URAGQSNP2F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MBIAS: Mitigating Bias in Large Language Models While Retaining Context","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananya Raval, Shaina Raza, Veronica Chatrath","submitted_at":"2024-05-18T13:31:12Z","abstract_excerpt":"The deployment of Large Language Models (LLMs) in diverse applications necessitates an assurance of safety without compromising the contextual integrity of the generated content. Traditional approaches, including safety-specific fine-tuning or adversarial testing, often yield safe outputs at the expense of contextual meaning. This can result in a diminished capacity to handle nuanced aspects of bias and toxicity, such as underrepresentation or negative portrayals across various demographics. To address these challenges, we introduce MBIAS, an LLM framework carefully instruction fine-tuned on a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11290","kind":"arxiv","version":3},"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/2405.11290/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":"2026-07-05T08:37:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/m+Y1Eomxi+mpJQ+RmBymeYCv2tQxwOLpn4P7oIlpB8nx1m8Fh/yW3vHyTMi/dO+mznQmabfjue/aUA1gLpcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T07:50:47.400431Z"},"content_sha256":"0a128bda2a7c7a1710baffd0b890c368f77255282a6a31aff7c623334884373f","schema_version":"1.0","event_id":"sha256:0a128bda2a7c7a1710baffd0b890c368f77255282a6a31aff7c623334884373f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BW4PYTEKM4SMQPJ5URAGQSNP2F/bundle.json","state_url":"https://pith.science/pith/BW4PYTEKM4SMQPJ5URAGQSNP2F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BW4PYTEKM4SMQPJ5URAGQSNP2F/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":"2026-07-06T07:50:47Z","links":{"resolver":"https://pith.science/pith/BW4PYTEKM4SMQPJ5URAGQSNP2F","bundle":"https://pith.science/pith/BW4PYTEKM4SMQPJ5URAGQSNP2F/bundle.json","state":"https://pith.science/pith/BW4PYTEKM4SMQPJ5URAGQSNP2F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BW4PYTEKM4SMQPJ5URAGQSNP2F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BW4PYTEKM4SMQPJ5URAGQSNP2F","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":"2597f3fdd940cf4e9e39ad912b86522d0052f6a61863b6b23dc7a81a75ac6a1f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-18T13:31:12Z","title_canon_sha256":"31a16589d7a45bbc57476214eed6512c7728883742510fd044ffd04600bed033"},"schema_version":"1.0","source":{"id":"2405.11290","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11290","created_at":"2026-07-05T08:37:52Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11290v3","created_at":"2026-07-05T08:37:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11290","created_at":"2026-07-05T08:37:52Z"},{"alias_kind":"pith_short_12","alias_value":"BW4PYTEKM4SM","created_at":"2026-07-05T08:37:52Z"},{"alias_kind":"pith_short_16","alias_value":"BW4PYTEKM4SMQPJ5","created_at":"2026-07-05T08:37:52Z"},{"alias_kind":"pith_short_8","alias_value":"BW4PYTEK","created_at":"2026-07-05T08:37:52Z"}],"graph_snapshots":[{"event_id":"sha256:0a128bda2a7c7a1710baffd0b890c368f77255282a6a31aff7c623334884373f","target":"graph","created_at":"2026-07-05T08:37:52Z","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/2405.11290/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The deployment of Large Language Models (LLMs) in diverse applications necessitates an assurance of safety without compromising the contextual integrity of the generated content. Traditional approaches, including safety-specific fine-tuning or adversarial testing, often yield safe outputs at the expense of contextual meaning. This can result in a diminished capacity to handle nuanced aspects of bias and toxicity, such as underrepresentation or negative portrayals across various demographics. To address these challenges, we introduce MBIAS, an LLM framework carefully instruction fine-tuned on a","authors_text":"Ananya Raval, Shaina Raza, Veronica Chatrath","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-18T13:31:12Z","title":"MBIAS: Mitigating Bias in Large Language Models While Retaining Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11290","kind":"arxiv","version":3},"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":"sha256:34e46ae2eed2a6cb9847a14fa0dd3d7f50ac3774722370f783bf51025f868668","target":"record","created_at":"2026-07-05T08:37:52Z","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":"2597f3fdd940cf4e9e39ad912b86522d0052f6a61863b6b23dc7a81a75ac6a1f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-18T13:31:12Z","title_canon_sha256":"31a16589d7a45bbc57476214eed6512c7728883742510fd044ffd04600bed033"},"schema_version":"1.0","source":{"id":"2405.11290","kind":"arxiv","version":3}},"canonical_sha256":"0db8fc4c8a6724c83d3da4406849afd14c1d2790a6683d38d820b8e455d10ed2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0db8fc4c8a6724c83d3da4406849afd14c1d2790a6683d38d820b8e455d10ed2","first_computed_at":"2026-07-05T08:37:52.882509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:52.882509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z6XXXc7jGepH/6MzIa0XxcYA0nB3cy3ElNV9rjJzVyomz9DPnRDdJv3wdzzupDzqy06QV0MlWPB/mc0iqvLgAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:52.883028Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11290","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34e46ae2eed2a6cb9847a14fa0dd3d7f50ac3774722370f783bf51025f868668","sha256:0a128bda2a7c7a1710baffd0b890c368f77255282a6a31aff7c623334884373f"],"state_sha256":"1c7d35a2fa2a47f893445fc9b28a67c3095c42f40a5e6e61d1e07ce243e5c64e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yCLy2hKNAwgCq1CWejuBhjWk9wtlk9R8kWOS+27R+2g1zOaK1zz9sXz+8k0L7Dty6TyVTjqBMcC5+JXNmIMwDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T07:50:47.402423Z","bundle_sha256":"ac8a7a05d843d116e9862e609f4572593fb07bebb9a059f01a82e3edda2e56dd"}}