{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DNOM5APULQ34ZRFS5MSVE6QN3R","short_pith_number":"pith:DNOM5APU","canonical_record":{"source":{"id":"2401.06692","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T16:56:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"02540d4d68c92453db806701426ff4e3144c1331acfcf8f8bd98c0d7803fdf9a","abstract_canon_sha256":"0bc314f3a098bdcd2f96b9acd805de6a9c4272f08dcd663a1c3c6851adf1a77f"},"schema_version":"1.0"},"canonical_sha256":"1b5cce81f45c37ccc4b2eb25527a0ddc544f02742c69a1ec5f9ac672788a4c3b","source":{"kind":"arxiv","id":"2401.06692","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06692","created_at":"2026-07-05T08:40:58Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06692v3","created_at":"2026-07-05T08:40:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06692","created_at":"2026-07-05T08:40:58Z"},{"alias_kind":"pith_short_12","alias_value":"DNOM5APULQ34","created_at":"2026-07-05T08:40:58Z"},{"alias_kind":"pith_short_16","alias_value":"DNOM5APULQ34ZRFS","created_at":"2026-07-05T08:40:58Z"},{"alias_kind":"pith_short_8","alias_value":"DNOM5APU","created_at":"2026-07-05T08:40:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DNOM5APULQ34ZRFS5MSVE6QN3R","target":"record","payload":{"canonical_record":{"source":{"id":"2401.06692","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T16:56:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"02540d4d68c92453db806701426ff4e3144c1331acfcf8f8bd98c0d7803fdf9a","abstract_canon_sha256":"0bc314f3a098bdcd2f96b9acd805de6a9c4272f08dcd663a1c3c6851adf1a77f"},"schema_version":"1.0"},"canonical_sha256":"1b5cce81f45c37ccc4b2eb25527a0ddc544f02742c69a1ec5f9ac672788a4c3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:58.440657Z","signature_b64":"qFNgw2n75sVYoFB4YPa4WT5HMeKmpoiiEoogEHW9pojLqnpw5KD/1m7ph4WQx9OHqQ07iLWJgflXJkJFu7deAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b5cce81f45c37ccc4b2eb25527a0ddc544f02742c69a1ec5f9ac672788a4c3b","last_reissued_at":"2026-07-05T08:40:58.440176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:58.440176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.06692","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":"2026-07-05T08:40:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PO36yj4K7IAQHJQrZklqb9DL6ksDKpeeGEOv98KupNGNDhOiYLl2KsHj+S/8k9UA8zjhN/KPpD/J/u2qrahjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:39:10.794468Z"},"content_sha256":"1618f9dbdb884a4306477a2bec184c923535d76231ff8270c8b4ca5d61ef1557","schema_version":"1.0","event_id":"sha256:1618f9dbdb884a4306477a2bec184c923535d76231ff8270c8b4ca5d61ef1557"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DNOM5APULQ34ZRFS5MSVE6QN3R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arnav M. Das, Gantavya Bhatt, Jeffrey Bilmes, Jifan Zhang, Jordan T. Ash, Kevin Jamieson, Robert D. Nowak, Sang T. Truong, Simon S. Du, Stephen Mussmann, Yifang Chen, Yinglun Zhu","submitted_at":"2024-01-12T16:56:54Z","abstract_excerpt":"Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to produce high quality responses for instructions are becoming prohibitively expensive, especially as the number of tasks spanned by instruction datasets continues to increase. Active learning is effective in identifying useful subsets of samples to annotate from an unlabeled pool, but its high computational cost remains a barrier to its widespread applicability "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06692","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/2401.06692/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":"2026-07-05T08:40:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gaPXYPrFvwYwhtzjuAUzyuidfSAOmc+xWEZVxq16SZVIT5nH/UgkjYG3IBh7/BSzqkczTP4UdjS48CSFEs/OCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:39:10.794991Z"},"content_sha256":"c353c86ac5ba7d8a4d31f9f879e7ff88f3d8f52efe6ccd02f752d218046c7552","schema_version":"1.0","event_id":"sha256:c353c86ac5ba7d8a4d31f9f879e7ff88f3d8f52efe6ccd02f752d218046c7552"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DNOM5APULQ34ZRFS5MSVE6QN3R/bundle.json","state_url":"https://pith.science/pith/DNOM5APULQ34ZRFS5MSVE6QN3R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DNOM5APULQ34ZRFS5MSVE6QN3R/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":"2026-08-07T17:39:10Z","links":{"resolver":"https://pith.science/pith/DNOM5APULQ34ZRFS5MSVE6QN3R","bundle":"https://pith.science/pith/DNOM5APULQ34ZRFS5MSVE6QN3R/bundle.json","state":"https://pith.science/pith/DNOM5APULQ34ZRFS5MSVE6QN3R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DNOM5APULQ34ZRFS5MSVE6QN3R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DNOM5APULQ34ZRFS5MSVE6QN3R","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":"0bc314f3a098bdcd2f96b9acd805de6a9c4272f08dcd663a1c3c6851adf1a77f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T16:56:54Z","title_canon_sha256":"02540d4d68c92453db806701426ff4e3144c1331acfcf8f8bd98c0d7803fdf9a"},"schema_version":"1.0","source":{"id":"2401.06692","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06692","created_at":"2026-07-05T08:40:58Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06692v3","created_at":"2026-07-05T08:40:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06692","created_at":"2026-07-05T08:40:58Z"},{"alias_kind":"pith_short_12","alias_value":"DNOM5APULQ34","created_at":"2026-07-05T08:40:58Z"},{"alias_kind":"pith_short_16","alias_value":"DNOM5APULQ34ZRFS","created_at":"2026-07-05T08:40:58Z"},{"alias_kind":"pith_short_8","alias_value":"DNOM5APU","created_at":"2026-07-05T08:40:58Z"}],"graph_snapshots":[{"event_id":"sha256:c353c86ac5ba7d8a4d31f9f879e7ff88f3d8f52efe6ccd02f752d218046c7552","target":"graph","created_at":"2026-07-05T08:40:58Z","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/2401.06692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to produce high quality responses for instructions are becoming prohibitively expensive, especially as the number of tasks spanned by instruction datasets continues to increase. Active learning is effective in identifying useful subsets of samples to annotate from an unlabeled pool, but its high computational cost remains a barrier to its widespread applicability ","authors_text":"Arnav M. Das, Gantavya Bhatt, Jeffrey Bilmes, Jifan Zhang, Jordan T. Ash, Kevin Jamieson, Robert D. Nowak, Sang T. Truong, Simon S. Du, Stephen Mussmann, Yifang Chen, Yinglun Zhu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T16:56:54Z","title":"An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06692","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":"sha256:1618f9dbdb884a4306477a2bec184c923535d76231ff8270c8b4ca5d61ef1557","target":"record","created_at":"2026-07-05T08:40:58Z","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":"0bc314f3a098bdcd2f96b9acd805de6a9c4272f08dcd663a1c3c6851adf1a77f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T16:56:54Z","title_canon_sha256":"02540d4d68c92453db806701426ff4e3144c1331acfcf8f8bd98c0d7803fdf9a"},"schema_version":"1.0","source":{"id":"2401.06692","kind":"arxiv","version":3}},"canonical_sha256":"1b5cce81f45c37ccc4b2eb25527a0ddc544f02742c69a1ec5f9ac672788a4c3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b5cce81f45c37ccc4b2eb25527a0ddc544f02742c69a1ec5f9ac672788a4c3b","first_computed_at":"2026-07-05T08:40:58.440176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:58.440176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qFNgw2n75sVYoFB4YPa4WT5HMeKmpoiiEoogEHW9pojLqnpw5KD/1m7ph4WQx9OHqQ07iLWJgflXJkJFu7deAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:58.440657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06692","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1618f9dbdb884a4306477a2bec184c923535d76231ff8270c8b4ca5d61ef1557","sha256:c353c86ac5ba7d8a4d31f9f879e7ff88f3d8f52efe6ccd02f752d218046c7552"],"state_sha256":"e69b6a016419da3cabf3c06b6e187295d3ee6fc992eee96ebc809d851b455a6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XUiRtFFzCoD+IEuAIPZsYVskopDKWkY1RVYL9AHaEs7Vti/k0VQBPdE6QS/hyqVXtv+ySwvhyGwapDdLawk6Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:39:10.801966Z","bundle_sha256":"06dd6e12a42e1d339186d29183c61f55d4742dcf5e10a7ae794ab0263a9f5eef"}}