{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZJH6IHH3SEQON7M5AEUZ4MZFJ6","short_pith_number":"pith:ZJH6IHH3","canonical_record":{"source":{"id":"2402.10110","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T17:06:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"28d0383eb954cf263fcd4b4645425d502e1fe249a29774cd72c9cf20c0455013","abstract_canon_sha256":"d78ebe9738f7a7f35f2bd3a2e1581e8913912ce8a96864a7c27298332fdf0bdb"},"schema_version":"1.0"},"canonical_sha256":"ca4fe41cfb9120e6fd9d01299e33254f9cdca906d766fb98698ff450e24cfb46","source":{"kind":"arxiv","id":"2402.10110","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10110","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10110v2","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10110","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"ZJH6IHH3SEQO","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZJH6IHH3SEQON7M5","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZJH6IHH3","created_at":"2026-07-05T08:28:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZJH6IHH3SEQON7M5AEUZ4MZFJ6","target":"record","payload":{"canonical_record":{"source":{"id":"2402.10110","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T17:06:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"28d0383eb954cf263fcd4b4645425d502e1fe249a29774cd72c9cf20c0455013","abstract_canon_sha256":"d78ebe9738f7a7f35f2bd3a2e1581e8913912ce8a96864a7c27298332fdf0bdb"},"schema_version":"1.0"},"canonical_sha256":"ca4fe41cfb9120e6fd9d01299e33254f9cdca906d766fb98698ff450e24cfb46","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:59.521202Z","signature_b64":"1kszs0Mf7B6w9ZMf8zoqD+jU1FXI3IO1P6y7MPSsxVpm09E3GsY1bGhcNO/W95XpfASwriD97PjEwKORuxgJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca4fe41cfb9120e6fd9d01299e33254f9cdca906d766fb98698ff450e24cfb46","last_reissued_at":"2026-07-05T08:28:59.520725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:59.520725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.10110","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u/PuywvKRAWHibpLtGvT52X4g8/CafdOAVZFGYr8GPWeGw/Nxu5ZKeSdVEoyBKz3Hghpy3o4hyfi6lmAhERMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:11:43.559368Z"},"content_sha256":"58c2621c97a9ebfdc969ec446d29b7b1b9fee73c6edecfe7443950615b112315","schema_version":"1.0","event_id":"sha256:58c2621c97a9ebfdc969ec446d29b7b1b9fee73c6edecfe7443950615b112315"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZJH6IHH3SEQON7M5AEUZ4MZFJ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiuhai Chen, Jiuxiang Gu, Lichang Chen, Ming Li, Shwai He, Tianyi Zhou","submitted_at":"2024-02-15T17:06:21Z","abstract_excerpt":"Instruction tuning is critical to large language models (LLMs) for achieving better instruction following and task adaptation capabilities but its success heavily relies on the training data quality. Many recent methods focus on improving the data quality but often overlook the compatibility of the data with the student model being finetuned. This paper introduces Selective Reflection-Tuning, a novel paradigm that synergizes a teacher LLM's reflection and introspection for improving existing data quality with the data selection capability of the student LLM, to automatically refine existing in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10110","kind":"arxiv","version":2},"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/2402.10110/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":"2026-07-05T08:28:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HDcqhpx35gLK7OD8ZY1kacZrcq2trzr/Vns72i2kF0bzZpXoo4/CAuE+qaZy6LoPZij8GmqPyjy8Z1rG65CNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:11:43.559862Z"},"content_sha256":"b4b75dcab385ea32ee08a6d4a1f2f7f7377192dc6b0a2097d508e522bdce755c","schema_version":"1.0","event_id":"sha256:b4b75dcab385ea32ee08a6d4a1f2f7f7377192dc6b0a2097d508e522bdce755c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZJH6IHH3SEQON7M5AEUZ4MZFJ6/bundle.json","state_url":"https://pith.science/pith/ZJH6IHH3SEQON7M5AEUZ4MZFJ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZJH6IHH3SEQON7M5AEUZ4MZFJ6/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":"2026-08-11T00:11:43Z","links":{"resolver":"https://pith.science/pith/ZJH6IHH3SEQON7M5AEUZ4MZFJ6","bundle":"https://pith.science/pith/ZJH6IHH3SEQON7M5AEUZ4MZFJ6/bundle.json","state":"https://pith.science/pith/ZJH6IHH3SEQON7M5AEUZ4MZFJ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZJH6IHH3SEQON7M5AEUZ4MZFJ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZJH6IHH3SEQON7M5AEUZ4MZFJ6","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":"d78ebe9738f7a7f35f2bd3a2e1581e8913912ce8a96864a7c27298332fdf0bdb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T17:06:21Z","title_canon_sha256":"28d0383eb954cf263fcd4b4645425d502e1fe249a29774cd72c9cf20c0455013"},"schema_version":"1.0","source":{"id":"2402.10110","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10110","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10110v2","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10110","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"ZJH6IHH3SEQO","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZJH6IHH3SEQON7M5","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZJH6IHH3","created_at":"2026-07-05T08:28:59Z"}],"graph_snapshots":[{"event_id":"sha256:b4b75dcab385ea32ee08a6d4a1f2f7f7377192dc6b0a2097d508e522bdce755c","target":"graph","created_at":"2026-07-05T08:28:59Z","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/2402.10110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning is critical to large language models (LLMs) for achieving better instruction following and task adaptation capabilities but its success heavily relies on the training data quality. Many recent methods focus on improving the data quality but often overlook the compatibility of the data with the student model being finetuned. This paper introduces Selective Reflection-Tuning, a novel paradigm that synergizes a teacher LLM's reflection and introspection for improving existing data quality with the data selection capability of the student LLM, to automatically refine existing in","authors_text":"Jiuhai Chen, Jiuxiang Gu, Lichang Chen, Ming Li, Shwai He, Tianyi Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T17:06:21Z","title":"Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10110","kind":"arxiv","version":2},"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":"sha256:58c2621c97a9ebfdc969ec446d29b7b1b9fee73c6edecfe7443950615b112315","target":"record","created_at":"2026-07-05T08:28:59Z","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":"d78ebe9738f7a7f35f2bd3a2e1581e8913912ce8a96864a7c27298332fdf0bdb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T17:06:21Z","title_canon_sha256":"28d0383eb954cf263fcd4b4645425d502e1fe249a29774cd72c9cf20c0455013"},"schema_version":"1.0","source":{"id":"2402.10110","kind":"arxiv","version":2}},"canonical_sha256":"ca4fe41cfb9120e6fd9d01299e33254f9cdca906d766fb98698ff450e24cfb46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca4fe41cfb9120e6fd9d01299e33254f9cdca906d766fb98698ff450e24cfb46","first_computed_at":"2026-07-05T08:28:59.520725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:59.520725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1kszs0Mf7B6w9ZMf8zoqD+jU1FXI3IO1P6y7MPSsxVpm09E3GsY1bGhcNO/W95XpfASwriD97PjEwKORuxgJDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:59.521202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10110","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58c2621c97a9ebfdc969ec446d29b7b1b9fee73c6edecfe7443950615b112315","sha256:b4b75dcab385ea32ee08a6d4a1f2f7f7377192dc6b0a2097d508e522bdce755c"],"state_sha256":"659cc772cc94a43471ac10e9bb06357c46943d8562e56fc6b4874bfff615c0e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ETFj0s2IFRQ5tF3z65xSDuzJuda3a7g9IFFcDIIu1oascu1CkQuVofcCobsOJo7yxfQrcykzi3RCJfSijaICQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T00:11:43.563493Z","bundle_sha256":"9b1d0f8415e365f416dbf9ce3ef229b91897360eae199c2132232044dd0c3619"}}