{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZFCIYYGSPJCME35DYCZ2Q54MCN","short_pith_number":"pith:ZFCIYYGS","canonical_record":{"source":{"id":"2509.09524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T15:04:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0f2c6deb1d0f88d86494ed09a5358e7037a9c4027836d5bc8e4625dee0b681c9","abstract_canon_sha256":"09d7ae8b6701643f20b5ce03ca83c20501ca06fb6da61fbaee11db5ff215167f"},"schema_version":"1.0"},"canonical_sha256":"c9448c60d27a44c26fa3c0b3a8778c136580a00af31b0fcba5ed96d4367ff5c4","source":{"kind":"arxiv","id":"2509.09524","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09524","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09524v1","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09524","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZFCIYYGSPJCM","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZFCIYYGSPJCME35D","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZFCIYYGS","created_at":"2026-07-05T12:09:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZFCIYYGSPJCME35DYCZ2Q54MCN","target":"record","payload":{"canonical_record":{"source":{"id":"2509.09524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T15:04:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0f2c6deb1d0f88d86494ed09a5358e7037a9c4027836d5bc8e4625dee0b681c9","abstract_canon_sha256":"09d7ae8b6701643f20b5ce03ca83c20501ca06fb6da61fbaee11db5ff215167f"},"schema_version":"1.0"},"canonical_sha256":"c9448c60d27a44c26fa3c0b3a8778c136580a00af31b0fcba5ed96d4367ff5c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:37.510322Z","signature_b64":"o0pdSyTQNj4fZl/0MM18wUHTwSAJoDqDCLRRQmDoOcf8w0dbciHeyjgVljlcLYXJqLb7D0sHxSAGbv3BlSMbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9448c60d27a44c26fa3c0b3a8778c136580a00af31b0fcba5ed96d4367ff5c4","last_reissued_at":"2026-07-05T12:09:37.509866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:37.509866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.09524","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":"2026-07-05T12:09:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vCvhhqpQ8pn7A+m3wNtM0dwGQr0t9DZYQUlQDU0vsK+O9nZPkNPFF0vkr9NHreqDDUyx6E1I18yO8NSRXkCCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:00:22.551139Z"},"content_sha256":"73debfeb5139b319b453d355440e2233d5435d7a8d401fbddba5a0bdb964d04b","schema_version":"1.0","event_id":"sha256:73debfeb5139b319b453d355440e2233d5435d7a8d401fbddba5a0bdb964d04b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZFCIYYGSPJCME35DYCZ2Q54MCN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anh Dang, Daniil Ignatev, Hugh Mee Wong, Nan Li, Shane Kaszefski Yaschuk","submitted_at":"2025-09-11T15:04:42Z","abstract_excerpt":"This system paper presents the DeMeVa team's approaches to the third edition of the Learning with Disagreements shared task (LeWiDi 2025; Leonardelli et al., 2025). We explore two directions: in-context learning (ICL) with large language models, where we compare example sampling strategies; and label distribution learning (LDL) methods with RoBERTa (Liu et al., 2019b), where we evaluate several fine-tuning methods. Our contributions are twofold: (1) we show that ICL can effectively predict annotator-specific annotations (perspectivist annotations), and that aggregating these predictions into s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09524","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/2509.09524/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":"2026-07-05T12:09:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HFv+9Xid9QOmpNBKul/vWSchu9hwcVm4YkIt2XlxhqwsJG7NfKBee1dqbUX5LKoOzjTaQo7bpNNSybUniUtRCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:00:22.551641Z"},"content_sha256":"98dd0b97bae8dd18c0c15b061ccd8ab17fd117f3fdd5e9a5409376702e603bb4","schema_version":"1.0","event_id":"sha256:98dd0b97bae8dd18c0c15b061ccd8ab17fd117f3fdd5e9a5409376702e603bb4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZFCIYYGSPJCME35DYCZ2Q54MCN/bundle.json","state_url":"https://pith.science/pith/ZFCIYYGSPJCME35DYCZ2Q54MCN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZFCIYYGSPJCME35DYCZ2Q54MCN/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":"2026-08-05T07:00:22Z","links":{"resolver":"https://pith.science/pith/ZFCIYYGSPJCME35DYCZ2Q54MCN","bundle":"https://pith.science/pith/ZFCIYYGSPJCME35DYCZ2Q54MCN/bundle.json","state":"https://pith.science/pith/ZFCIYYGSPJCME35DYCZ2Q54MCN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZFCIYYGSPJCME35DYCZ2Q54MCN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZFCIYYGSPJCME35DYCZ2Q54MCN","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":"09d7ae8b6701643f20b5ce03ca83c20501ca06fb6da61fbaee11db5ff215167f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T15:04:42Z","title_canon_sha256":"0f2c6deb1d0f88d86494ed09a5358e7037a9c4027836d5bc8e4625dee0b681c9"},"schema_version":"1.0","source":{"id":"2509.09524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09524","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09524v1","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09524","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZFCIYYGSPJCM","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZFCIYYGSPJCME35D","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZFCIYYGS","created_at":"2026-07-05T12:09:37Z"}],"graph_snapshots":[{"event_id":"sha256:98dd0b97bae8dd18c0c15b061ccd8ab17fd117f3fdd5e9a5409376702e603bb4","target":"graph","created_at":"2026-07-05T12:09:37Z","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/2509.09524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This system paper presents the DeMeVa team's approaches to the third edition of the Learning with Disagreements shared task (LeWiDi 2025; Leonardelli et al., 2025). We explore two directions: in-context learning (ICL) with large language models, where we compare example sampling strategies; and label distribution learning (LDL) methods with RoBERTa (Liu et al., 2019b), where we evaluate several fine-tuning methods. Our contributions are twofold: (1) we show that ICL can effectively predict annotator-specific annotations (perspectivist annotations), and that aggregating these predictions into s","authors_text":"Anh Dang, Daniil Ignatev, Hugh Mee Wong, Nan Li, Shane Kaszefski Yaschuk","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T15:04:42Z","title":"DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09524","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":"sha256:73debfeb5139b319b453d355440e2233d5435d7a8d401fbddba5a0bdb964d04b","target":"record","created_at":"2026-07-05T12:09:37Z","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":"09d7ae8b6701643f20b5ce03ca83c20501ca06fb6da61fbaee11db5ff215167f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T15:04:42Z","title_canon_sha256":"0f2c6deb1d0f88d86494ed09a5358e7037a9c4027836d5bc8e4625dee0b681c9"},"schema_version":"1.0","source":{"id":"2509.09524","kind":"arxiv","version":1}},"canonical_sha256":"c9448c60d27a44c26fa3c0b3a8778c136580a00af31b0fcba5ed96d4367ff5c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9448c60d27a44c26fa3c0b3a8778c136580a00af31b0fcba5ed96d4367ff5c4","first_computed_at":"2026-07-05T12:09:37.509866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:37.509866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o0pdSyTQNj4fZl/0MM18wUHTwSAJoDqDCLRRQmDoOcf8w0dbciHeyjgVljlcLYXJqLb7D0sHxSAGbv3BlSMbAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:37.510322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73debfeb5139b319b453d355440e2233d5435d7a8d401fbddba5a0bdb964d04b","sha256:98dd0b97bae8dd18c0c15b061ccd8ab17fd117f3fdd5e9a5409376702e603bb4"],"state_sha256":"ae6b0ae72d93601105c011afb0fbd7d077b2dc91de73eca68644b0339a9bbaa7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q2IudoozEL2QqvTyfeIh7mMTcM8i4GwXecAhh9G4NnuoHK78AwQxOI+O1FpYNbleT3Ggu8AHKXmZlJV8JoxCAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:00:22.556627Z","bundle_sha256":"190d49a5f02bc0944be60bd9277a786f0bf9c0f9ea93ba751d78735057ccac0b"}}