{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EDEZE32ZEZOCYFWHLDWJ6GAERQ","short_pith_number":"pith:EDEZE32Z","canonical_record":{"source":{"id":"2411.04425","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T04:38:29Z","cross_cats_sorted":[],"title_canon_sha256":"7c31cce64d3fd2853361b1b6e9026527ae15cae401c5308df3749f79829f2a62","abstract_canon_sha256":"323ff22c65a4fb85e53c1b1cb929d6d0d28e3e4b046697e638d276163503c58d"},"schema_version":"1.0"},"canonical_sha256":"20c9926f59265c2c16c758ec9f18048c02dd37bfdc1f07be9f3ba0da8589fa21","source":{"kind":"arxiv","id":"2411.04425","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04425","created_at":"2026-07-05T10:35:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04425v3","created_at":"2026-07-05T10:35:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04425","created_at":"2026-07-05T10:35:40Z"},{"alias_kind":"pith_short_12","alias_value":"EDEZE32ZEZOC","created_at":"2026-07-05T10:35:40Z"},{"alias_kind":"pith_short_16","alias_value":"EDEZE32ZEZOCYFWH","created_at":"2026-07-05T10:35:40Z"},{"alias_kind":"pith_short_8","alias_value":"EDEZE32Z","created_at":"2026-07-05T10:35:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EDEZE32ZEZOCYFWHLDWJ6GAERQ","target":"record","payload":{"canonical_record":{"source":{"id":"2411.04425","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T04:38:29Z","cross_cats_sorted":[],"title_canon_sha256":"7c31cce64d3fd2853361b1b6e9026527ae15cae401c5308df3749f79829f2a62","abstract_canon_sha256":"323ff22c65a4fb85e53c1b1cb929d6d0d28e3e4b046697e638d276163503c58d"},"schema_version":"1.0"},"canonical_sha256":"20c9926f59265c2c16c758ec9f18048c02dd37bfdc1f07be9f3ba0da8589fa21","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:40.387795Z","signature_b64":"Eu2gVd2DzMNAHCdw+dkC6kVf63GV2yPV71NvjIVOItx2XjKYPa0c4tjWMdEqdJXZbEDQzdV51l6V8G3Dj0tEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20c9926f59265c2c16c758ec9f18048c02dd37bfdc1f07be9f3ba0da8589fa21","last_reissued_at":"2026-07-05T10:35:40.386830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:40.386830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.04425","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":"2026-07-05T10:35:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+emodiS7Snl2bIqCxxaYtCH7qw0kRn4ypvfumbA7hxPi5Apkk6gwBdC/gu5A7XBdl70+WN6h6SZH7umk18PvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:57:18.930810Z"},"content_sha256":"b8dcc46725d956b1a9bbc26cb81edfe50a4419dce09cef49dc940b082878bd45","schema_version":"1.0","event_id":"sha256:b8dcc46725d956b1a9bbc26cb81edfe50a4419dce09cef49dc940b082878bd45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EDEZE32ZEZOCYFWHLDWJ6GAERQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DELIFT: Data Efficient Language model Instruction Fine Tuning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ishika Agarwal, Krishnateja Killamsetty, Lucian Popa, Marina Danilevksy","submitted_at":"2024-11-07T04:38:29Z","abstract_excerpt":"Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To address this inefficiency, we introduce DELIFT (Data Efficient Language model Instruction Fine-Tuning), a novel algorithm that systematically optimizes data selection across the three key stages of fine-tuning: (1) instruction tuning, (2) task-specific fine-tuning (e.g., reasoning, question-answering), and (3) continual fine-tuning (e.g., incorporating new data versions). Unlike existing methods that focus on single-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04425","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/2411.04425/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":"2026-07-05T10:35:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z9ntPJk6TFjYyzxW/fZ66YSfXThxANNQ3d0jIuPuyTdMbPIP/cR3kHkCzZ4KHwoJW+103+M4CfzLJZSeY0maAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:57:18.931718Z"},"content_sha256":"b8d825963cb76d49ea98dfd64ebbef3cd9549b66773dfdcad9b65ca88afc232f","schema_version":"1.0","event_id":"sha256:b8d825963cb76d49ea98dfd64ebbef3cd9549b66773dfdcad9b65ca88afc232f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EDEZE32ZEZOCYFWHLDWJ6GAERQ/bundle.json","state_url":"https://pith.science/pith/EDEZE32ZEZOCYFWHLDWJ6GAERQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EDEZE32ZEZOCYFWHLDWJ6GAERQ/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":"2026-08-10T10:57:18Z","links":{"resolver":"https://pith.science/pith/EDEZE32ZEZOCYFWHLDWJ6GAERQ","bundle":"https://pith.science/pith/EDEZE32ZEZOCYFWHLDWJ6GAERQ/bundle.json","state":"https://pith.science/pith/EDEZE32ZEZOCYFWHLDWJ6GAERQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EDEZE32ZEZOCYFWHLDWJ6GAERQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EDEZE32ZEZOCYFWHLDWJ6GAERQ","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":"323ff22c65a4fb85e53c1b1cb929d6d0d28e3e4b046697e638d276163503c58d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T04:38:29Z","title_canon_sha256":"7c31cce64d3fd2853361b1b6e9026527ae15cae401c5308df3749f79829f2a62"},"schema_version":"1.0","source":{"id":"2411.04425","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04425","created_at":"2026-07-05T10:35:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04425v3","created_at":"2026-07-05T10:35:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04425","created_at":"2026-07-05T10:35:40Z"},{"alias_kind":"pith_short_12","alias_value":"EDEZE32ZEZOC","created_at":"2026-07-05T10:35:40Z"},{"alias_kind":"pith_short_16","alias_value":"EDEZE32ZEZOCYFWH","created_at":"2026-07-05T10:35:40Z"},{"alias_kind":"pith_short_8","alias_value":"EDEZE32Z","created_at":"2026-07-05T10:35:40Z"}],"graph_snapshots":[{"event_id":"sha256:b8d825963cb76d49ea98dfd64ebbef3cd9549b66773dfdcad9b65ca88afc232f","target":"graph","created_at":"2026-07-05T10:35:40Z","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/2411.04425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To address this inefficiency, we introduce DELIFT (Data Efficient Language model Instruction Fine-Tuning), a novel algorithm that systematically optimizes data selection across the three key stages of fine-tuning: (1) instruction tuning, (2) task-specific fine-tuning (e.g., reasoning, question-answering), and (3) continual fine-tuning (e.g., incorporating new data versions). Unlike existing methods that focus on single-s","authors_text":"Ishika Agarwal, Krishnateja Killamsetty, Lucian Popa, Marina Danilevksy","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T04:38:29Z","title":"DELIFT: Data Efficient Language model Instruction Fine Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04425","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:b8dcc46725d956b1a9bbc26cb81edfe50a4419dce09cef49dc940b082878bd45","target":"record","created_at":"2026-07-05T10:35:40Z","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":"323ff22c65a4fb85e53c1b1cb929d6d0d28e3e4b046697e638d276163503c58d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T04:38:29Z","title_canon_sha256":"7c31cce64d3fd2853361b1b6e9026527ae15cae401c5308df3749f79829f2a62"},"schema_version":"1.0","source":{"id":"2411.04425","kind":"arxiv","version":3}},"canonical_sha256":"20c9926f59265c2c16c758ec9f18048c02dd37bfdc1f07be9f3ba0da8589fa21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20c9926f59265c2c16c758ec9f18048c02dd37bfdc1f07be9f3ba0da8589fa21","first_computed_at":"2026-07-05T10:35:40.386830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:40.386830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Eu2gVd2DzMNAHCdw+dkC6kVf63GV2yPV71NvjIVOItx2XjKYPa0c4tjWMdEqdJXZbEDQzdV51l6V8G3Dj0tEDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:40.387795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04425","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8dcc46725d956b1a9bbc26cb81edfe50a4419dce09cef49dc940b082878bd45","sha256:b8d825963cb76d49ea98dfd64ebbef3cd9549b66773dfdcad9b65ca88afc232f"],"state_sha256":"fa050084bb228d4bfefe48c0da4acfbd03ab0063f995d5e43ad5b66e1bdb2e34"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z6t3T5tVxabwnWCXH1tiWLb13ZsvziA7ufl5od8noHPFcGegWh/dn4LdUNZ4OzJXZVjGhWPWuJCNn3fHwX/ADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:57:18.938986Z","bundle_sha256":"423982d853f7e605586308a5d909a9f571250e87597827e645d24b8c1e4aa3a6"}}