{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5QHGO3NTWWVP4N2UOGCATFHULQ","short_pith_number":"pith:5QHGO3NT","canonical_record":{"source":{"id":"2305.09246","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-16T07:52:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"810de6cb18560f221bcfb811ed5f617d1b7078d29192252ed4fd767948a06b90","abstract_canon_sha256":"47244b136252dceff0ccf293e542e63c771d5c64e2c3d88529752aa6d37f9476"},"schema_version":"1.0"},"canonical_sha256":"ec0e676db3b5aafe375471840994f45c020cb87a429351f79edbad8c2f50d3b0","source":{"kind":"arxiv","id":"2305.09246","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09246","created_at":"2026-07-05T06:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09246v1","created_at":"2026-07-05T06:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09246","created_at":"2026-07-05T06:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"5QHGO3NTWWVP","created_at":"2026-07-05T06:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"5QHGO3NTWWVP4N2U","created_at":"2026-07-05T06:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"5QHGO3NT","created_at":"2026-07-05T06:10:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5QHGO3NTWWVP4N2UOGCATFHULQ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.09246","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-16T07:52:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"810de6cb18560f221bcfb811ed5f617d1b7078d29192252ed4fd767948a06b90","abstract_canon_sha256":"47244b136252dceff0ccf293e542e63c771d5c64e2c3d88529752aa6d37f9476"},"schema_version":"1.0"},"canonical_sha256":"ec0e676db3b5aafe375471840994f45c020cb87a429351f79edbad8c2f50d3b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:45.550360Z","signature_b64":"LKR4isn+O0hh2XgPbA601OKldVFhnleeck/vFrJiHCIBirGnQwCrsa6iuCp43pPjgZNbI1H5mH2BW39lxraCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec0e676db3b5aafe375471840994f45c020cb87a429351f79edbad8c2f50d3b0","last_reissued_at":"2026-07-05T06:10:45.549839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:45.549839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.09246","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":"2026-07-05T06:10:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pu/U2Xarbbqax4YSs0foaZLA7cw5pR10maIc0S22zflxbzD2bbuHgDzckU2PUkpab5Fl608xud73Im9dMM7wDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:25:44.180367Z"},"content_sha256":"974e80e935e78fbe13aaf6cec83a264e27941e8675752192f0220c58940515fb","schema_version":"1.0","event_id":"sha256:974e80e935e78fbe13aaf6cec83a264e27941e8675752192f0220c58940515fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5QHGO3NTWWVP4N2UOGCATFHULQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Hantao Yang, Hao Chen, Junbo Zhao, Qi Zhang, Xiaomeng Hu, Xuetao Ma, Yifan Yanggong, Yiming Zhang","submitted_at":"2023-05-16T07:52:57Z","abstract_excerpt":"Instruction tuning for large language models (LLMs) has gained attention from researchers due to its ability to unlock the potential of LLMs in following instructions. While instruction tuning offers advantages for facilitating the adaptation of large language models (LLMs) to downstream tasks as a fine-tuning approach, training models with tens of millions or even billions of parameters on large amounts of data results in unaffordable computational costs. To address this, we focus on reducing the data used in LLM instruction tuning to decrease training costs and improve data efficiency, dubbe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09246","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/2305.09246/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":"2026-07-05T06:10:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"429IR3PKZQhYpzNt8Jx4Zfh63IreEGjYAEGxI2KbpnXfRhnV2ZNsMcLzyBBYKRzFGFKf//Di9EY01l9/HsN8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:25:44.180889Z"},"content_sha256":"eec1f2330d13cab6dd7850ac735a9208f788b4706c1e79f5aeaeac2e9cd7ebcc","schema_version":"1.0","event_id":"sha256:eec1f2330d13cab6dd7850ac735a9208f788b4706c1e79f5aeaeac2e9cd7ebcc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5QHGO3NTWWVP4N2UOGCATFHULQ/bundle.json","state_url":"https://pith.science/pith/5QHGO3NTWWVP4N2UOGCATFHULQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5QHGO3NTWWVP4N2UOGCATFHULQ/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":"2026-08-07T21:25:44Z","links":{"resolver":"https://pith.science/pith/5QHGO3NTWWVP4N2UOGCATFHULQ","bundle":"https://pith.science/pith/5QHGO3NTWWVP4N2UOGCATFHULQ/bundle.json","state":"https://pith.science/pith/5QHGO3NTWWVP4N2UOGCATFHULQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5QHGO3NTWWVP4N2UOGCATFHULQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5QHGO3NTWWVP4N2UOGCATFHULQ","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":"47244b136252dceff0ccf293e542e63c771d5c64e2c3d88529752aa6d37f9476","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-16T07:52:57Z","title_canon_sha256":"810de6cb18560f221bcfb811ed5f617d1b7078d29192252ed4fd767948a06b90"},"schema_version":"1.0","source":{"id":"2305.09246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09246","created_at":"2026-07-05T06:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09246v1","created_at":"2026-07-05T06:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09246","created_at":"2026-07-05T06:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"5QHGO3NTWWVP","created_at":"2026-07-05T06:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"5QHGO3NTWWVP4N2U","created_at":"2026-07-05T06:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"5QHGO3NT","created_at":"2026-07-05T06:10:45Z"}],"graph_snapshots":[{"event_id":"sha256:eec1f2330d13cab6dd7850ac735a9208f788b4706c1e79f5aeaeac2e9cd7ebcc","target":"graph","created_at":"2026-07-05T06:10:45Z","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/2305.09246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning for large language models (LLMs) has gained attention from researchers due to its ability to unlock the potential of LLMs in following instructions. While instruction tuning offers advantages for facilitating the adaptation of large language models (LLMs) to downstream tasks as a fine-tuning approach, training models with tens of millions or even billions of parameters on large amounts of data results in unaffordable computational costs. To address this, we focus on reducing the data used in LLM instruction tuning to decrease training costs and improve data efficiency, dubbe","authors_text":"Hantao Yang, Hao Chen, Junbo Zhao, Qi Zhang, Xiaomeng Hu, Xuetao Ma, Yifan Yanggong, Yiming Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-16T07:52:57Z","title":"Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09246","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":"sha256:974e80e935e78fbe13aaf6cec83a264e27941e8675752192f0220c58940515fb","target":"record","created_at":"2026-07-05T06:10:45Z","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":"47244b136252dceff0ccf293e542e63c771d5c64e2c3d88529752aa6d37f9476","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-16T07:52:57Z","title_canon_sha256":"810de6cb18560f221bcfb811ed5f617d1b7078d29192252ed4fd767948a06b90"},"schema_version":"1.0","source":{"id":"2305.09246","kind":"arxiv","version":1}},"canonical_sha256":"ec0e676db3b5aafe375471840994f45c020cb87a429351f79edbad8c2f50d3b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec0e676db3b5aafe375471840994f45c020cb87a429351f79edbad8c2f50d3b0","first_computed_at":"2026-07-05T06:10:45.549839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:10:45.549839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LKR4isn+O0hh2XgPbA601OKldVFhnleeck/vFrJiHCIBirGnQwCrsa6iuCp43pPjgZNbI1H5mH2BW39lxraCDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:10:45.550360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.09246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:974e80e935e78fbe13aaf6cec83a264e27941e8675752192f0220c58940515fb","sha256:eec1f2330d13cab6dd7850ac735a9208f788b4706c1e79f5aeaeac2e9cd7ebcc"],"state_sha256":"39f38ad6dbab15438dd86322918477c5cfe9e71f0b9d56c856f0446b29314959"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mVc6raC9Juq6y1v71PHMJGMN52m6kxHsmX3YSO/bEiTjbIQx4bOfCyKZ7yz4jUuYJtfGNNWFbpSOE/ZpfeHgBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:25:44.184564Z","bundle_sha256":"ad2a776a24150ac7d71969988e064957465d7b2c3a6cd759a2e397bcb75505db"}}