{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2BAMEOZM4CUUKT6NB7WSM6KYES","short_pith_number":"pith:2BAMEOZM","canonical_record":{"source":{"id":"2402.04333","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T19:18:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7383ec9e54b781b4423cddb2fe5fd0a2c0de584a55b0cb5627f19604c7f3d693","abstract_canon_sha256":"082adf0f5eb8a781fda325bdd087ff058287b86c0812986f7b9533587066381f"},"schema_version":"1.0"},"canonical_sha256":"d040c23b2ce0a9454fcd0fed26795824b34f3a16d958b9fc4a61e8c519cbad51","source":{"kind":"arxiv","id":"2402.04333","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04333","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04333v3","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04333","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"pith_short_12","alias_value":"2BAMEOZM4CUU","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"pith_short_16","alias_value":"2BAMEOZM4CUUKT6N","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"pith_short_8","alias_value":"2BAMEOZM","created_at":"2026-07-05T08:31:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2BAMEOZM4CUUKT6NB7WSM6KYES","target":"record","payload":{"canonical_record":{"source":{"id":"2402.04333","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T19:18:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7383ec9e54b781b4423cddb2fe5fd0a2c0de584a55b0cb5627f19604c7f3d693","abstract_canon_sha256":"082adf0f5eb8a781fda325bdd087ff058287b86c0812986f7b9533587066381f"},"schema_version":"1.0"},"canonical_sha256":"d040c23b2ce0a9454fcd0fed26795824b34f3a16d958b9fc4a61e8c519cbad51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:11.353491Z","signature_b64":"/sBKPUjCEW7znuaNkcF7HzOV/E/lhkK0zkNoVC+hw3RMiDjGEH0SwXFdb0OP3VL/Vp33vwXFrC/Yb38grzQNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d040c23b2ce0a9454fcd0fed26795824b34f3a16d958b9fc4a61e8c519cbad51","last_reissued_at":"2026-07-05T08:31:11.352989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:11.352989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.04333","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":"2026-07-05T08:31:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B8S0ibFT31HYkovV+nQuYgyFcEhyWITIWgqCgBX1Vo6MbWeUsVcEtBvdqr2bQPpk8DHnFW/6kEZ0yB2pnWtDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:44:14.255534Z"},"content_sha256":"1439b63d673c78063d85511588586bdccf2c18e4997fc1f011ccf7408c92ffed","schema_version":"1.0","event_id":"sha256:1439b63d673c78063d85511588586bdccf2c18e4997fc1f011ccf7408c92ffed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2BAMEOZM4CUUKT6NB7WSM6KYES","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Danqi Chen, Mengzhou Xia, Sadhika Malladi, Sanjeev Arora, Suchin Gururangan","submitted_at":"2024-02-06T19:18:04Z","abstract_excerpt":"Instruction tuning has unlocked powerful capabilities in large language models (LLMs), effectively using combined datasets to develop generalpurpose chatbots. However, real-world applications often require a specialized suite of skills (e.g., reasoning). The challenge lies in identifying the most relevant data from these extensive datasets to effectively develop specific capabilities, a setting we frame as targeted instruction tuning. We propose LESS, an optimizer-aware and practically efficient algorithm to effectively estimate data influences and perform Low-rank gradiEnt Similarity Search f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04333","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/2402.04333/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":"2026-07-05T08:31:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yc0s5VzFpl4OfJhzbfkWkZFpnCbjdfZnnMZ5bIHYv8xRVnzjfGfLuKHGf0gorq1n4MVlk36uI2MXzznPdcj2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:44:14.256081Z"},"content_sha256":"d95227bfca0b7588fda7238db77103ed1be4af3eb8e45e7cf8aa7f1fcf83bd10","schema_version":"1.0","event_id":"sha256:d95227bfca0b7588fda7238db77103ed1be4af3eb8e45e7cf8aa7f1fcf83bd10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2BAMEOZM4CUUKT6NB7WSM6KYES/bundle.json","state_url":"https://pith.science/pith/2BAMEOZM4CUUKT6NB7WSM6KYES/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2BAMEOZM4CUUKT6NB7WSM6KYES/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":"2026-08-05T16:44:14Z","links":{"resolver":"https://pith.science/pith/2BAMEOZM4CUUKT6NB7WSM6KYES","bundle":"https://pith.science/pith/2BAMEOZM4CUUKT6NB7WSM6KYES/bundle.json","state":"https://pith.science/pith/2BAMEOZM4CUUKT6NB7WSM6KYES/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2BAMEOZM4CUUKT6NB7WSM6KYES/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2BAMEOZM4CUUKT6NB7WSM6KYES","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":"082adf0f5eb8a781fda325bdd087ff058287b86c0812986f7b9533587066381f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T19:18:04Z","title_canon_sha256":"7383ec9e54b781b4423cddb2fe5fd0a2c0de584a55b0cb5627f19604c7f3d693"},"schema_version":"1.0","source":{"id":"2402.04333","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04333","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04333v3","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04333","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"pith_short_12","alias_value":"2BAMEOZM4CUU","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"pith_short_16","alias_value":"2BAMEOZM4CUUKT6N","created_at":"2026-07-05T08:31:11Z"},{"alias_kind":"pith_short_8","alias_value":"2BAMEOZM","created_at":"2026-07-05T08:31:11Z"}],"graph_snapshots":[{"event_id":"sha256:d95227bfca0b7588fda7238db77103ed1be4af3eb8e45e7cf8aa7f1fcf83bd10","target":"graph","created_at":"2026-07-05T08:31:11Z","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/2402.04333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning has unlocked powerful capabilities in large language models (LLMs), effectively using combined datasets to develop generalpurpose chatbots. However, real-world applications often require a specialized suite of skills (e.g., reasoning). The challenge lies in identifying the most relevant data from these extensive datasets to effectively develop specific capabilities, a setting we frame as targeted instruction tuning. We propose LESS, an optimizer-aware and practically efficient algorithm to effectively estimate data influences and perform Low-rank gradiEnt Similarity Search f","authors_text":"Danqi Chen, Mengzhou Xia, Sadhika Malladi, Sanjeev Arora, Suchin Gururangan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T19:18:04Z","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04333","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":"sha256:1439b63d673c78063d85511588586bdccf2c18e4997fc1f011ccf7408c92ffed","target":"record","created_at":"2026-07-05T08:31:11Z","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":"082adf0f5eb8a781fda325bdd087ff058287b86c0812986f7b9533587066381f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T19:18:04Z","title_canon_sha256":"7383ec9e54b781b4423cddb2fe5fd0a2c0de584a55b0cb5627f19604c7f3d693"},"schema_version":"1.0","source":{"id":"2402.04333","kind":"arxiv","version":3}},"canonical_sha256":"d040c23b2ce0a9454fcd0fed26795824b34f3a16d958b9fc4a61e8c519cbad51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d040c23b2ce0a9454fcd0fed26795824b34f3a16d958b9fc4a61e8c519cbad51","first_computed_at":"2026-07-05T08:31:11.352989Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:11.352989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/sBKPUjCEW7znuaNkcF7HzOV/E/lhkK0zkNoVC+hw3RMiDjGEH0SwXFdb0OP3VL/Vp33vwXFrC/Yb38grzQNAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:11.353491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04333","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1439b63d673c78063d85511588586bdccf2c18e4997fc1f011ccf7408c92ffed","sha256:d95227bfca0b7588fda7238db77103ed1be4af3eb8e45e7cf8aa7f1fcf83bd10"],"state_sha256":"6777fc61e24a2c2ecdaca3aea02a2b687371594782cb3a85ba9c01af5a35e4f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0onQUMj+tTCjP5GaLRV4+RPwp0GNC4VJAwNgpivOAB/9xxAesSinwpzVHyUQuEXl4wEDv5KevXcjCsh89HwMDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:44:14.260381Z","bundle_sha256":"93138b96940416a138535b6cdf7409715d0279d84e28a6dad86d00ed6fe9a761"}}