{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W6DPKR4XX43KIRPQBKK3FS5EPX","short_pith_number":"pith:W6DPKR4X","canonical_record":{"source":{"id":"2407.14259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T12:37:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c344ce718cbc17b8c79f55ddb55c51c33391fd164090a51d2aac1c0bcefbafa","abstract_canon_sha256":"a0b7fba4e6521c0b6ba7dd0d9f1f8c3b2dc91530ea342e600551078e549ac6c7"},"schema_version":"1.0"},"canonical_sha256":"b786f54797bf36a445f00a95b2cba47dc1b4168b7b184eea7bc9178e1849cc06","source":{"kind":"arxiv","id":"2407.14259","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14259","created_at":"2026-07-05T08:46:09Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14259v1","created_at":"2026-07-05T08:46:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14259","created_at":"2026-07-05T08:46:09Z"},{"alias_kind":"pith_short_12","alias_value":"W6DPKR4XX43K","created_at":"2026-07-05T08:46:09Z"},{"alias_kind":"pith_short_16","alias_value":"W6DPKR4XX43KIRPQ","created_at":"2026-07-05T08:46:09Z"},{"alias_kind":"pith_short_8","alias_value":"W6DPKR4X","created_at":"2026-07-05T08:46:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W6DPKR4XX43KIRPQBKK3FS5EPX","target":"record","payload":{"canonical_record":{"source":{"id":"2407.14259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T12:37:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c344ce718cbc17b8c79f55ddb55c51c33391fd164090a51d2aac1c0bcefbafa","abstract_canon_sha256":"a0b7fba4e6521c0b6ba7dd0d9f1f8c3b2dc91530ea342e600551078e549ac6c7"},"schema_version":"1.0"},"canonical_sha256":"b786f54797bf36a445f00a95b2cba47dc1b4168b7b184eea7bc9178e1849cc06","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:09.543433Z","signature_b64":"AVSxn4yC7l57ljh5+hCKst9F1tyHg7mF7j5L79+7HMgY+z9v8QKRwO1PlBnF9BuzXz4CHzr9GxFltXU3eFEmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b786f54797bf36a445f00a95b2cba47dc1b4168b7b184eea7bc9178e1849cc06","last_reissued_at":"2026-07-05T08:46:09.542976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:09.542976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.14259","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":"2026-07-05T08:46:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hSBZY6Lmw/zlOs+MG8xF7CswRwE7NDIUeoWuUcDFkuBfYtbqhzTkEj/HHuoA8QGqXxtBtydIXZpM8mIBuaPvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:29:10.916292Z"},"content_sha256":"fb1a3b8a37d587b7052679a8931c58e7bcc1e27bb5c30522ba96f6b9ef8d384b","schema_version":"1.0","event_id":"sha256:fb1a3b8a37d587b7052679a8931c58e7bcc1e27bb5c30522ba96f6b9ef8d384b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W6DPKR4XX43KIRPQBKK3FS5EPX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Voices in a Crowd: Searching for Clusters of Unique Perspectives","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Amit Parekh, Ioannis Konstas, Nikolas Vitsakis","submitted_at":"2024-07-19T12:37:15Z","abstract_excerpt":"Language models have been shown to reproduce underlying biases existing in their training data, which is the majority perspective by default. Proposed solutions aim to capture minority perspectives by either modelling annotator disagreements or grouping annotators based on shared metadata, both of which face significant challenges. We propose a framework that trains models without encoding annotator metadata, extracts latent embeddings informed by annotator behaviour, and creates clusters of similar opinions, that we refer to as voices. Resulting clusters are validated post-hoc via internal an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14259","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/2407.14259/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":"2026-07-05T08:46:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/qpnEssqVFJvyJTCic3LiluaVEtlnH9KlZ3lw+ksQphHBRCaRlMQMolKUzsdQXrKFTPnsK/aK9o4Vpb9aKZZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:29:10.916825Z"},"content_sha256":"ff48a0536c9ab6e5e552eeb4858015ee4ca04e4e8e57bed3403a84a1912fc408","schema_version":"1.0","event_id":"sha256:ff48a0536c9ab6e5e552eeb4858015ee4ca04e4e8e57bed3403a84a1912fc408"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W6DPKR4XX43KIRPQBKK3FS5EPX/bundle.json","state_url":"https://pith.science/pith/W6DPKR4XX43KIRPQBKK3FS5EPX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W6DPKR4XX43KIRPQBKK3FS5EPX/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":"2026-08-09T06:29:10Z","links":{"resolver":"https://pith.science/pith/W6DPKR4XX43KIRPQBKK3FS5EPX","bundle":"https://pith.science/pith/W6DPKR4XX43KIRPQBKK3FS5EPX/bundle.json","state":"https://pith.science/pith/W6DPKR4XX43KIRPQBKK3FS5EPX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W6DPKR4XX43KIRPQBKK3FS5EPX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W6DPKR4XX43KIRPQBKK3FS5EPX","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":"a0b7fba4e6521c0b6ba7dd0d9f1f8c3b2dc91530ea342e600551078e549ac6c7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T12:37:15Z","title_canon_sha256":"1c344ce718cbc17b8c79f55ddb55c51c33391fd164090a51d2aac1c0bcefbafa"},"schema_version":"1.0","source":{"id":"2407.14259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14259","created_at":"2026-07-05T08:46:09Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14259v1","created_at":"2026-07-05T08:46:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14259","created_at":"2026-07-05T08:46:09Z"},{"alias_kind":"pith_short_12","alias_value":"W6DPKR4XX43K","created_at":"2026-07-05T08:46:09Z"},{"alias_kind":"pith_short_16","alias_value":"W6DPKR4XX43KIRPQ","created_at":"2026-07-05T08:46:09Z"},{"alias_kind":"pith_short_8","alias_value":"W6DPKR4X","created_at":"2026-07-05T08:46:09Z"}],"graph_snapshots":[{"event_id":"sha256:ff48a0536c9ab6e5e552eeb4858015ee4ca04e4e8e57bed3403a84a1912fc408","target":"graph","created_at":"2026-07-05T08:46:09Z","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/2407.14259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models have been shown to reproduce underlying biases existing in their training data, which is the majority perspective by default. Proposed solutions aim to capture minority perspectives by either modelling annotator disagreements or grouping annotators based on shared metadata, both of which face significant challenges. We propose a framework that trains models without encoding annotator metadata, extracts latent embeddings informed by annotator behaviour, and creates clusters of similar opinions, that we refer to as voices. Resulting clusters are validated post-hoc via internal an","authors_text":"Amit Parekh, Ioannis Konstas, Nikolas Vitsakis","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T12:37:15Z","title":"Voices in a Crowd: Searching for Clusters of Unique Perspectives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14259","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:fb1a3b8a37d587b7052679a8931c58e7bcc1e27bb5c30522ba96f6b9ef8d384b","target":"record","created_at":"2026-07-05T08:46:09Z","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":"a0b7fba4e6521c0b6ba7dd0d9f1f8c3b2dc91530ea342e600551078e549ac6c7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T12:37:15Z","title_canon_sha256":"1c344ce718cbc17b8c79f55ddb55c51c33391fd164090a51d2aac1c0bcefbafa"},"schema_version":"1.0","source":{"id":"2407.14259","kind":"arxiv","version":1}},"canonical_sha256":"b786f54797bf36a445f00a95b2cba47dc1b4168b7b184eea7bc9178e1849cc06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b786f54797bf36a445f00a95b2cba47dc1b4168b7b184eea7bc9178e1849cc06","first_computed_at":"2026-07-05T08:46:09.542976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:09.542976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AVSxn4yC7l57ljh5+hCKst9F1tyHg7mF7j5L79+7HMgY+z9v8QKRwO1PlBnF9BuzXz4CHzr9GxFltXU3eFEmDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:09.543433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.14259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb1a3b8a37d587b7052679a8931c58e7bcc1e27bb5c30522ba96f6b9ef8d384b","sha256:ff48a0536c9ab6e5e552eeb4858015ee4ca04e4e8e57bed3403a84a1912fc408"],"state_sha256":"11ca8f36fcbdef4733e80eb341f2d9f1be106330ce90dfa3df2b95b75d0e3410"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"reW+iVPCq/ePRZyphu34VpmT/LH23dCP7UjOB9RmEiik3z34ahYfMfCWkfVfWs0QHdTlGtnLWjqaHDgs4z5yBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:29:10.920833Z","bundle_sha256":"31840d9409a65dfbfe535a9d154d51ecd735b0c44b4fb2df48cc1e7288b2a417"}}