{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NDSY4JGODVCHVPF7IYVQQIEWQJ","short_pith_number":"pith:NDSY4JGO","canonical_record":{"source":{"id":"2505.12212","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T03:10:00Z","cross_cats_sorted":[],"title_canon_sha256":"d4b021ad3b4e288ef5874181a779316d011d28ad5c307c00a9d0fd9b4f15208a","abstract_canon_sha256":"983aa97b220d5505baec71096e8a423124354a307fda90fb7ca875d0ed128a9b"},"schema_version":"1.0"},"canonical_sha256":"68e58e24ce1d447abcbf462b082096825571a14609c18291fbf3110cc86c576d","source":{"kind":"arxiv","id":"2505.12212","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12212","created_at":"2026-07-05T11:13:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12212v3","created_at":"2026-07-05T11:13:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12212","created_at":"2026-07-05T11:13:25Z"},{"alias_kind":"pith_short_12","alias_value":"NDSY4JGODVCH","created_at":"2026-07-05T11:13:25Z"},{"alias_kind":"pith_short_16","alias_value":"NDSY4JGODVCHVPF7","created_at":"2026-07-05T11:13:25Z"},{"alias_kind":"pith_short_8","alias_value":"NDSY4JGO","created_at":"2026-07-05T11:13:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NDSY4JGODVCHVPF7IYVQQIEWQJ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12212","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T03:10:00Z","cross_cats_sorted":[],"title_canon_sha256":"d4b021ad3b4e288ef5874181a779316d011d28ad5c307c00a9d0fd9b4f15208a","abstract_canon_sha256":"983aa97b220d5505baec71096e8a423124354a307fda90fb7ca875d0ed128a9b"},"schema_version":"1.0"},"canonical_sha256":"68e58e24ce1d447abcbf462b082096825571a14609c18291fbf3110cc86c576d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:25.630132Z","signature_b64":"rPXCf6sTYDCitPk4kro8u/LNRCYwxbm3Arwe6xWceSlXhM3d74F2+Lp1v7orZ7Q8UmoFXQXR6izaOlMRQrq2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68e58e24ce1d447abcbf462b082096825571a14609c18291fbf3110cc86c576d","last_reissued_at":"2026-07-05T11:13:25.629641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:25.629641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12212","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":"2026-07-05T11:13:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"82uvoZeEoBgCLXLCG2e4jsI6PII7DQTymdrGT0Udc+Ji6XesL/eAzIuquiHixosrIDDBUndvxJR1s0HP+NmgCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:29:05.382890Z"},"content_sha256":"8ab11ce3cee7e3f728a925073c6fbe525e015c2c3af79a925b1b631a5043bcef","schema_version":"1.0","event_id":"sha256:8ab11ce3cee7e3f728a925073c6fbe525e015c2c3af79a925b1b631a5043bcef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NDSY4JGODVCHVPF7IYVQQIEWQJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Conghui He, Jiajun Zhang, Jize Wang, Kaixin Li, Linfeng Zhang, Shaobo Wang, Xiangqi Jin, Xuming Hu, Zhong Li, Zichen Wen, Ziming Wang","submitted_at":"2025-05-18T03:10:00Z","abstract_excerpt":"Fine-tuning large language models (LLMs) on task-specific data is essential for their effective deployment. As dataset sizes grow, efficiently selecting optimal subsets for training becomes crucial to balancing performance and computational costs. Traditional data selection methods often require fine-tuning a scoring model on the target dataset, which is time-consuming and resource-intensive, or rely on heuristics that fail to fully leverage the model's predictive capabilities. To address these challenges, we propose Data Whisperer, an efficient, training-free, attention-based method that leve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12212","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/2505.12212/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":"2026-07-05T11:13:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MUZMC9ndzm5m+DOSMXf6dzXSshrHd0m4GS1aHRwAUIKIwFY+/m7xpIaj2JHLI4kQAqqda+GJCdwBeiQh51A6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:29:05.383413Z"},"content_sha256":"573e4d7c71369c933abc06b071d0670de8cb5d56d8c4961f112f387bf742c783","schema_version":"1.0","event_id":"sha256:573e4d7c71369c933abc06b071d0670de8cb5d56d8c4961f112f387bf742c783"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDSY4JGODVCHVPF7IYVQQIEWQJ/bundle.json","state_url":"https://pith.science/pith/NDSY4JGODVCHVPF7IYVQQIEWQJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDSY4JGODVCHVPF7IYVQQIEWQJ/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":"2026-08-06T19:29:05Z","links":{"resolver":"https://pith.science/pith/NDSY4JGODVCHVPF7IYVQQIEWQJ","bundle":"https://pith.science/pith/NDSY4JGODVCHVPF7IYVQQIEWQJ/bundle.json","state":"https://pith.science/pith/NDSY4JGODVCHVPF7IYVQQIEWQJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDSY4JGODVCHVPF7IYVQQIEWQJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NDSY4JGODVCHVPF7IYVQQIEWQJ","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":"983aa97b220d5505baec71096e8a423124354a307fda90fb7ca875d0ed128a9b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T03:10:00Z","title_canon_sha256":"d4b021ad3b4e288ef5874181a779316d011d28ad5c307c00a9d0fd9b4f15208a"},"schema_version":"1.0","source":{"id":"2505.12212","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12212","created_at":"2026-07-05T11:13:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12212v3","created_at":"2026-07-05T11:13:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12212","created_at":"2026-07-05T11:13:25Z"},{"alias_kind":"pith_short_12","alias_value":"NDSY4JGODVCH","created_at":"2026-07-05T11:13:25Z"},{"alias_kind":"pith_short_16","alias_value":"NDSY4JGODVCHVPF7","created_at":"2026-07-05T11:13:25Z"},{"alias_kind":"pith_short_8","alias_value":"NDSY4JGO","created_at":"2026-07-05T11:13:25Z"}],"graph_snapshots":[{"event_id":"sha256:573e4d7c71369c933abc06b071d0670de8cb5d56d8c4961f112f387bf742c783","target":"graph","created_at":"2026-07-05T11:13:25Z","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/2505.12212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning large language models (LLMs) on task-specific data is essential for their effective deployment. As dataset sizes grow, efficiently selecting optimal subsets for training becomes crucial to balancing performance and computational costs. Traditional data selection methods often require fine-tuning a scoring model on the target dataset, which is time-consuming and resource-intensive, or rely on heuristics that fail to fully leverage the model's predictive capabilities. To address these challenges, we propose Data Whisperer, an efficient, training-free, attention-based method that leve","authors_text":"Conghui He, Jiajun Zhang, Jize Wang, Kaixin Li, Linfeng Zhang, Shaobo Wang, Xiangqi Jin, Xuming Hu, Zhong Li, Zichen Wen, Ziming Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T03:10:00Z","title":"Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12212","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":"sha256:8ab11ce3cee7e3f728a925073c6fbe525e015c2c3af79a925b1b631a5043bcef","target":"record","created_at":"2026-07-05T11:13:25Z","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":"983aa97b220d5505baec71096e8a423124354a307fda90fb7ca875d0ed128a9b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T03:10:00Z","title_canon_sha256":"d4b021ad3b4e288ef5874181a779316d011d28ad5c307c00a9d0fd9b4f15208a"},"schema_version":"1.0","source":{"id":"2505.12212","kind":"arxiv","version":3}},"canonical_sha256":"68e58e24ce1d447abcbf462b082096825571a14609c18291fbf3110cc86c576d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68e58e24ce1d447abcbf462b082096825571a14609c18291fbf3110cc86c576d","first_computed_at":"2026-07-05T11:13:25.629641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:25.629641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rPXCf6sTYDCitPk4kro8u/LNRCYwxbm3Arwe6xWceSlXhM3d74F2+Lp1v7orZ7Q8UmoFXQXR6izaOlMRQrq2Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:25.630132Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12212","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ab11ce3cee7e3f728a925073c6fbe525e015c2c3af79a925b1b631a5043bcef","sha256:573e4d7c71369c933abc06b071d0670de8cb5d56d8c4961f112f387bf742c783"],"state_sha256":"5383492a06c37b99217884dac7b46ebac495678fa4633886a7eb80829788e441"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3826C/91WGsXfvgxnEaugrNNbUa3I9uTOWHrX8ABMFB2N9PoCTzC7NRTEFfAefqBeFSn4VScAn8+xHy0FpYlCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:29:05.390179Z","bundle_sha256":"2bb8cecec3e81fd145c4717f0ac1763ae7f3eb0f1ac3fc5a420636fd1e55f7b7"}}