{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OEAZIOSDCCJNR7NT2XZ3VOAAWM","short_pith_number":"pith:OEAZIOSD","canonical_record":{"source":{"id":"2407.15235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-21T17:59:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ffe2bf51a366734f6ddd775fabc2e4dd032d8e6d796e5e16b9fb994dc4c49901","abstract_canon_sha256":"985c7a4b71d8e74e83845ba8733fcfa5dcf8ab2d7f9a187310fb93f51313e995"},"schema_version":"1.0"},"canonical_sha256":"7101943a431092d8fdb3d5f3bab800b304865983fe97e40408134e224324657e","source":{"kind":"arxiv","id":"2407.15235","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15235","created_at":"2026-07-05T08:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15235v1","created_at":"2026-07-05T08:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15235","created_at":"2026-07-05T08:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"OEAZIOSDCCJN","created_at":"2026-07-05T08:46:40Z"},{"alias_kind":"pith_short_16","alias_value":"OEAZIOSDCCJNR7NT","created_at":"2026-07-05T08:46:40Z"},{"alias_kind":"pith_short_8","alias_value":"OEAZIOSD","created_at":"2026-07-05T08:46:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OEAZIOSDCCJNR7NT2XZ3VOAAWM","target":"record","payload":{"canonical_record":{"source":{"id":"2407.15235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-21T17:59:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ffe2bf51a366734f6ddd775fabc2e4dd032d8e6d796e5e16b9fb994dc4c49901","abstract_canon_sha256":"985c7a4b71d8e74e83845ba8733fcfa5dcf8ab2d7f9a187310fb93f51313e995"},"schema_version":"1.0"},"canonical_sha256":"7101943a431092d8fdb3d5f3bab800b304865983fe97e40408134e224324657e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:40.539360Z","signature_b64":"07HUWOc9a+aRvM4G7Z6l33xIk4n7IpWTnS3Jd6/MGY1vTHxBlx38daC50GcxaGN1sEPOsNxRrXjZNRjPs1q1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7101943a431092d8fdb3d5f3bab800b304865983fe97e40408134e224324657e","last_reissued_at":"2026-07-05T08:46:40.538877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:40.538877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.15235","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":"2026-07-05T08:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QZX5SqZJ9QckLCAOxV5GZdFGqH9MNRX2xuS4NlsdwN2eNMW5WuZmhshMS1FI6TERD7n1y8kxzfQ69RL9xYuLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:55:53.678739Z"},"content_sha256":"ef53dc069f0102f02ee27bf734b4117509a45cfb2d4f8b7f41c8fcce2de45e78","schema_version":"1.0","event_id":"sha256:ef53dc069f0102f02ee27bf734b4117509a45cfb2d4f8b7f41c8fcce2de45e78"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OEAZIOSDCCJNR7NT2XZ3VOAAWM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jipeng Zhang, Renjie Pi, Rui Pan, Tong Zhang, Weizhong Zhang, Yaxuan Qin","submitted_at":"2024-07-21T17:59:20Z","abstract_excerpt":"Instruction tuning has achieved unprecedented success in NLP, turning large language models into versatile chatbots. However, the increasing variety and volume of instruction datasets demand significant computational resources. To address this, it is essential to extract a small and highly informative subset (i.e., Coreset) that achieves comparable performance to the full dataset. Achieving this goal poses non-trivial challenges: 1) data selection requires accurate data representations that reflect the training samples' quality, 2) considering the diverse nature of instruction datasets, and 3)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15235","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/2407.15235/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":"2026-07-05T08:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"79pc8UhE14osZjD+TjBMdtgmc8jlfQX9ldkksUGOOg6YojJYCGpDhdmSsQtWVG8OuYX6Wthzp99uqNd6B9cfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:55:53.679258Z"},"content_sha256":"bb98cfa44d1fb4fcdf90d70ca277145eb3c710e51fab89cc236b290f875feb27","schema_version":"1.0","event_id":"sha256:bb98cfa44d1fb4fcdf90d70ca277145eb3c710e51fab89cc236b290f875feb27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OEAZIOSDCCJNR7NT2XZ3VOAAWM/bundle.json","state_url":"https://pith.science/pith/OEAZIOSDCCJNR7NT2XZ3VOAAWM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OEAZIOSDCCJNR7NT2XZ3VOAAWM/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":"2026-08-08T04:55:53Z","links":{"resolver":"https://pith.science/pith/OEAZIOSDCCJNR7NT2XZ3VOAAWM","bundle":"https://pith.science/pith/OEAZIOSDCCJNR7NT2XZ3VOAAWM/bundle.json","state":"https://pith.science/pith/OEAZIOSDCCJNR7NT2XZ3VOAAWM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OEAZIOSDCCJNR7NT2XZ3VOAAWM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OEAZIOSDCCJNR7NT2XZ3VOAAWM","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":"985c7a4b71d8e74e83845ba8733fcfa5dcf8ab2d7f9a187310fb93f51313e995","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-21T17:59:20Z","title_canon_sha256":"ffe2bf51a366734f6ddd775fabc2e4dd032d8e6d796e5e16b9fb994dc4c49901"},"schema_version":"1.0","source":{"id":"2407.15235","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15235","created_at":"2026-07-05T08:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15235v1","created_at":"2026-07-05T08:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15235","created_at":"2026-07-05T08:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"OEAZIOSDCCJN","created_at":"2026-07-05T08:46:40Z"},{"alias_kind":"pith_short_16","alias_value":"OEAZIOSDCCJNR7NT","created_at":"2026-07-05T08:46:40Z"},{"alias_kind":"pith_short_8","alias_value":"OEAZIOSD","created_at":"2026-07-05T08:46:40Z"}],"graph_snapshots":[{"event_id":"sha256:bb98cfa44d1fb4fcdf90d70ca277145eb3c710e51fab89cc236b290f875feb27","target":"graph","created_at":"2026-07-05T08:46:40Z","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/2407.15235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning has achieved unprecedented success in NLP, turning large language models into versatile chatbots. However, the increasing variety and volume of instruction datasets demand significant computational resources. To address this, it is essential to extract a small and highly informative subset (i.e., Coreset) that achieves comparable performance to the full dataset. Achieving this goal poses non-trivial challenges: 1) data selection requires accurate data representations that reflect the training samples' quality, 2) considering the diverse nature of instruction datasets, and 3)","authors_text":"Jipeng Zhang, Renjie Pi, Rui Pan, Tong Zhang, Weizhong Zhang, Yaxuan Qin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-21T17:59:20Z","title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15235","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:ef53dc069f0102f02ee27bf734b4117509a45cfb2d4f8b7f41c8fcce2de45e78","target":"record","created_at":"2026-07-05T08:46:40Z","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":"985c7a4b71d8e74e83845ba8733fcfa5dcf8ab2d7f9a187310fb93f51313e995","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-21T17:59:20Z","title_canon_sha256":"ffe2bf51a366734f6ddd775fabc2e4dd032d8e6d796e5e16b9fb994dc4c49901"},"schema_version":"1.0","source":{"id":"2407.15235","kind":"arxiv","version":1}},"canonical_sha256":"7101943a431092d8fdb3d5f3bab800b304865983fe97e40408134e224324657e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7101943a431092d8fdb3d5f3bab800b304865983fe97e40408134e224324657e","first_computed_at":"2026-07-05T08:46:40.538877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:40.538877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"07HUWOc9a+aRvM4G7Z6l33xIk4n7IpWTnS3Jd6/MGY1vTHxBlx38daC50GcxaGN1sEPOsNxRrXjZNRjPs1q1DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:40.539360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15235","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef53dc069f0102f02ee27bf734b4117509a45cfb2d4f8b7f41c8fcce2de45e78","sha256:bb98cfa44d1fb4fcdf90d70ca277145eb3c710e51fab89cc236b290f875feb27"],"state_sha256":"c557fc2898a09228feb892f808e27656b37a2ea792bdf6e5d1de97908c078f2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LYMMlZLQnnh+oF5UinExY36GiOYILU92SNlxW+Uz4puQFPqQxubiiQKMfY4Hp37dIirTdYY9gdMShSnLkHLZAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:55:53.684416Z","bundle_sha256":"fd97d76b6cde1a0283bbf8e6308bce79b99b3c87e4494e38b99ae8b08265e574"}}