{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2MLGVM52OXDCAJN4J7PDMXXXCW","short_pith_number":"pith:2MLGVM52","canonical_record":{"source":{"id":"2605.26070","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T17:37:45Z","cross_cats_sorted":[],"title_canon_sha256":"0e77bbc9e334dab3fce652bd2878d9c52cef581be751f020429bd4e415e70d44","abstract_canon_sha256":"a84bd5bbc9b1e1ca0e518f395c4118c00c915ea75064f6bc326558c5b391b796"},"schema_version":"1.0"},"canonical_sha256":"d3166ab3ba75c62025bc4fde365ef715965dcabdd93b706b61cb4932b65e4ac7","source":{"kind":"arxiv","id":"2605.26070","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26070","created_at":"2026-05-26T02:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26070v1","created_at":"2026-05-26T02:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26070","created_at":"2026-05-26T02:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"2MLGVM52OXDC","created_at":"2026-05-26T02:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"2MLGVM52OXDCAJN4","created_at":"2026-05-26T02:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"2MLGVM52","created_at":"2026-05-26T02:05:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2MLGVM52OXDCAJN4J7PDMXXXCW","target":"record","payload":{"canonical_record":{"source":{"id":"2605.26070","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T17:37:45Z","cross_cats_sorted":[],"title_canon_sha256":"0e77bbc9e334dab3fce652bd2878d9c52cef581be751f020429bd4e415e70d44","abstract_canon_sha256":"a84bd5bbc9b1e1ca0e518f395c4118c00c915ea75064f6bc326558c5b391b796"},"schema_version":"1.0"},"canonical_sha256":"d3166ab3ba75c62025bc4fde365ef715965dcabdd93b706b61cb4932b65e4ac7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:25.747567Z","signature_b64":"sw2BpekQ8uBPSSVnIAwDFIB14g5icIBAFCobur7ZYGnz4lvKCopIf9NXvwBeeYp3FXp7WSzcAdA3aAsjsKWTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3166ab3ba75c62025bc4fde365ef715965dcabdd93b706b61cb4932b65e4ac7","last_reissued_at":"2026-05-26T02:05:25.746829Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:25.746829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.26070","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":"2026-05-26T02:05:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/5cZRAw0sYWuiE6Tz5ltlyqtNwtwJl76aqwx7PSgM1waOntXwwl41c69OPF0oESiN8vOrlg0Y1X96YrhPWUJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T16:17:10.176774Z"},"content_sha256":"02fefe6007fb2bc472bfa369740b54572e015eaf7e31be37bc432c42577c6e09","schema_version":"1.0","event_id":"sha256:02fefe6007fb2bc472bfa369740b54572e015eaf7e31be37bc432c42577c6e09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2MLGVM52OXDCAJN4J7PDMXXXCW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WhoSaidIt: Human-LLM Collaborative Annotation for Text-Based Multilingual Speaker-Attribute Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Smith, Jackie Lee, Lingyu Gao, Meghan Jemison, Will Monroe","submitted_at":"2026-05-25T17:37:45Z","abstract_excerpt":"Annotating speaker attributes from text is inherently ambiguous, particularly in multilingual settings where demographic and social cues are implicit and culturally variable. We propose a human-large language model (LLM) collaborative re-annotation framework for stabilizing multilingual speaker-attribute labels under practical resource constraints. Starting from a noisy corpus, we use LLMs to surface recurring annotation rationales through iterative interaction with experts, and apply disagreement-focused sampling for targeted re-annotation. Using this framework, we construct WhoSaidIt, a mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26070","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/2605.26070/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":"2026-05-26T02:05:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M57e4Dun2hAzBkL22wL7/+3t1XAH9Z/jvshaDCMigBJyBxenwbhgmv9XYJXCFUXpkDUZJT+1hNo9mJaf3Ri2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T16:17:10.177150Z"},"content_sha256":"488a0721dae44fcff9af4cc1c9a804fdb9e219e30a0767661e132181f1f6c943","schema_version":"1.0","event_id":"sha256:488a0721dae44fcff9af4cc1c9a804fdb9e219e30a0767661e132181f1f6c943"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2MLGVM52OXDCAJN4J7PDMXXXCW/bundle.json","state_url":"https://pith.science/pith/2MLGVM52OXDCAJN4J7PDMXXXCW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2MLGVM52OXDCAJN4J7PDMXXXCW/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":"2026-06-05T16:17:10Z","links":{"resolver":"https://pith.science/pith/2MLGVM52OXDCAJN4J7PDMXXXCW","bundle":"https://pith.science/pith/2MLGVM52OXDCAJN4J7PDMXXXCW/bundle.json","state":"https://pith.science/pith/2MLGVM52OXDCAJN4J7PDMXXXCW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2MLGVM52OXDCAJN4J7PDMXXXCW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2MLGVM52OXDCAJN4J7PDMXXXCW","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":"a84bd5bbc9b1e1ca0e518f395c4118c00c915ea75064f6bc326558c5b391b796","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T17:37:45Z","title_canon_sha256":"0e77bbc9e334dab3fce652bd2878d9c52cef581be751f020429bd4e415e70d44"},"schema_version":"1.0","source":{"id":"2605.26070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26070","created_at":"2026-05-26T02:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26070v1","created_at":"2026-05-26T02:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26070","created_at":"2026-05-26T02:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"2MLGVM52OXDC","created_at":"2026-05-26T02:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"2MLGVM52OXDCAJN4","created_at":"2026-05-26T02:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"2MLGVM52","created_at":"2026-05-26T02:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:488a0721dae44fcff9af4cc1c9a804fdb9e219e30a0767661e132181f1f6c943","target":"graph","created_at":"2026-05-26T02:05:25Z","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/2605.26070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Annotating speaker attributes from text is inherently ambiguous, particularly in multilingual settings where demographic and social cues are implicit and culturally variable. We propose a human-large language model (LLM) collaborative re-annotation framework for stabilizing multilingual speaker-attribute labels under practical resource constraints. Starting from a noisy corpus, we use LLMs to surface recurring annotation rationales through iterative interaction with experts, and apply disagreement-focused sampling for targeted re-annotation. Using this framework, we construct WhoSaidIt, a mult","authors_text":"David Smith, Jackie Lee, Lingyu Gao, Meghan Jemison, Will Monroe","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T17:37:45Z","title":"WhoSaidIt: Human-LLM Collaborative Annotation for Text-Based Multilingual Speaker-Attribute Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26070","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":"sha256:02fefe6007fb2bc472bfa369740b54572e015eaf7e31be37bc432c42577c6e09","target":"record","created_at":"2026-05-26T02:05:25Z","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":"a84bd5bbc9b1e1ca0e518f395c4118c00c915ea75064f6bc326558c5b391b796","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T17:37:45Z","title_canon_sha256":"0e77bbc9e334dab3fce652bd2878d9c52cef581be751f020429bd4e415e70d44"},"schema_version":"1.0","source":{"id":"2605.26070","kind":"arxiv","version":1}},"canonical_sha256":"d3166ab3ba75c62025bc4fde365ef715965dcabdd93b706b61cb4932b65e4ac7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3166ab3ba75c62025bc4fde365ef715965dcabdd93b706b61cb4932b65e4ac7","first_computed_at":"2026-05-26T02:05:25.746829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:25.746829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sw2BpekQ8uBPSSVnIAwDFIB14g5icIBAFCobur7ZYGnz4lvKCopIf9NXvwBeeYp3FXp7WSzcAdA3aAsjsKWTDg==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:25.747567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02fefe6007fb2bc472bfa369740b54572e015eaf7e31be37bc432c42577c6e09","sha256:488a0721dae44fcff9af4cc1c9a804fdb9e219e30a0767661e132181f1f6c943"],"state_sha256":"390c3ac82516596ff41aa30d02c689a99889017f07c55257e4fd5540f7c370f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/9tHlvn0OQun3ipvyeHuxgYgLYA37O/jfZUSWjpvfBC+Fb2NLSkXkMJRXO3zIQKKvCrJowjh5YjSVtqGEvKvBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T16:17:10.179481Z","bundle_sha256":"5abf2a0e3be3108bcbe91d092d9733a7fa2b0a7600d3ae9f6131c54ab8bf74c3"}}