{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AIXQYZU32EHAWWJTTO4YADCHFH","short_pith_number":"pith:AIXQYZU3","canonical_record":{"source":{"id":"2410.10210","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T07:09:02Z","cross_cats_sorted":[],"title_canon_sha256":"f2bd40ad4f25411f1cf8ec3abd03965218876e6f4d141c83398bf059e0416280","abstract_canon_sha256":"74c768cff5b831bb9a0ed76968059f0c38ba133eb3f3e6db722bedb1228a46bd"},"schema_version":"1.0"},"canonical_sha256":"022f0c669bd10e0b59339bb9800c4729d3f7ddfb16eb202d6a013ebf60340442","source":{"kind":"arxiv","id":"2410.10210","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10210","created_at":"2026-07-05T09:20:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10210v2","created_at":"2026-07-05T09:20:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10210","created_at":"2026-07-05T09:20:49Z"},{"alias_kind":"pith_short_12","alias_value":"AIXQYZU32EHA","created_at":"2026-07-05T09:20:49Z"},{"alias_kind":"pith_short_16","alias_value":"AIXQYZU32EHAWWJT","created_at":"2026-07-05T09:20:49Z"},{"alias_kind":"pith_short_8","alias_value":"AIXQYZU3","created_at":"2026-07-05T09:20:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AIXQYZU32EHAWWJTTO4YADCHFH","target":"record","payload":{"canonical_record":{"source":{"id":"2410.10210","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T07:09:02Z","cross_cats_sorted":[],"title_canon_sha256":"f2bd40ad4f25411f1cf8ec3abd03965218876e6f4d141c83398bf059e0416280","abstract_canon_sha256":"74c768cff5b831bb9a0ed76968059f0c38ba133eb3f3e6db722bedb1228a46bd"},"schema_version":"1.0"},"canonical_sha256":"022f0c669bd10e0b59339bb9800c4729d3f7ddfb16eb202d6a013ebf60340442","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:49.739638Z","signature_b64":"h5TIOFl8HdYaCpiLuCMWm9+DoW/tSbr5QrkRiqB6e8ASZptYJmuzKlchqFv0h+NT0EOmCZQov70JRiRvMc2tAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"022f0c669bd10e0b59339bb9800c4729d3f7ddfb16eb202d6a013ebf60340442","last_reissued_at":"2026-07-05T09:20:49.739155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:49.739155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.10210","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":"2026-07-05T09:20:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"990jpjsImmoLmjq6ChkpUTSDvuoiFIYpw2sIX75WMM7UyIDtJEFY1YVK/hAOUyKQpSYD+rbEANV/zfs0jnpwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:59:14.210497Z"},"content_sha256":"abc11577ac62891e9176aaa90291b859c12d54287b29aeae046decb7ec39910b","schema_version":"1.0","event_id":"sha256:abc11577ac62891e9176aaa90291b859c12d54287b29aeae046decb7ec39910b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AIXQYZU32EHAWWJTTO4YADCHFH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Minimum Tuning to Unlock Long Output from LLMs with High Quality Data as the Key","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daoze Zhang, Jintao Huang, Xingjun Wang, Yingda Chen, Yunlin Mao, Yuze Zhao","submitted_at":"2024-10-14T07:09:02Z","abstract_excerpt":"As large language models rapidly evolve to support longer context, there is a notable disparity in their capability to generate output at greater lengths. Recent study suggests that the primary cause for this imbalance may arise from the lack of data with long-output during alignment training. In light of this observation, attempts are made to re-align foundation models with data that fills the gap, which result in models capable of generating lengthy output when instructed. In this paper, we explore the impact of data-quality in tuning a model for long output, and the possibility of doing so "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10210","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/2410.10210/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":"2026-07-05T09:20:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AyYjRPClk5O+SEUogpnVbc8jaR05gAnGKf2Wx6kiPjjxzKcc0kKyIFodJ6l+EWpbGQBCvuF/Eu5YATMIu2ooCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:59:14.211835Z"},"content_sha256":"86ff9f3e19e44bd82989369a6759ed22b42f1fbf36270240fb13e478d015f5a7","schema_version":"1.0","event_id":"sha256:86ff9f3e19e44bd82989369a6759ed22b42f1fbf36270240fb13e478d015f5a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AIXQYZU32EHAWWJTTO4YADCHFH/bundle.json","state_url":"https://pith.science/pith/AIXQYZU32EHAWWJTTO4YADCHFH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AIXQYZU32EHAWWJTTO4YADCHFH/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":"2026-08-17T14:59:14Z","links":{"resolver":"https://pith.science/pith/AIXQYZU32EHAWWJTTO4YADCHFH","bundle":"https://pith.science/pith/AIXQYZU32EHAWWJTTO4YADCHFH/bundle.json","state":"https://pith.science/pith/AIXQYZU32EHAWWJTTO4YADCHFH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AIXQYZU32EHAWWJTTO4YADCHFH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AIXQYZU32EHAWWJTTO4YADCHFH","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":"74c768cff5b831bb9a0ed76968059f0c38ba133eb3f3e6db722bedb1228a46bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T07:09:02Z","title_canon_sha256":"f2bd40ad4f25411f1cf8ec3abd03965218876e6f4d141c83398bf059e0416280"},"schema_version":"1.0","source":{"id":"2410.10210","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10210","created_at":"2026-07-05T09:20:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10210v2","created_at":"2026-07-05T09:20:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10210","created_at":"2026-07-05T09:20:49Z"},{"alias_kind":"pith_short_12","alias_value":"AIXQYZU32EHA","created_at":"2026-07-05T09:20:49Z"},{"alias_kind":"pith_short_16","alias_value":"AIXQYZU32EHAWWJT","created_at":"2026-07-05T09:20:49Z"},{"alias_kind":"pith_short_8","alias_value":"AIXQYZU3","created_at":"2026-07-05T09:20:49Z"}],"graph_snapshots":[{"event_id":"sha256:86ff9f3e19e44bd82989369a6759ed22b42f1fbf36270240fb13e478d015f5a7","target":"graph","created_at":"2026-07-05T09:20:49Z","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/2410.10210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models rapidly evolve to support longer context, there is a notable disparity in their capability to generate output at greater lengths. Recent study suggests that the primary cause for this imbalance may arise from the lack of data with long-output during alignment training. In light of this observation, attempts are made to re-align foundation models with data that fills the gap, which result in models capable of generating lengthy output when instructed. In this paper, we explore the impact of data-quality in tuning a model for long output, and the possibility of doing so ","authors_text":"Daoze Zhang, Jintao Huang, Xingjun Wang, Yingda Chen, Yunlin Mao, Yuze Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T07:09:02Z","title":"Minimum Tuning to Unlock Long Output from LLMs with High Quality Data as the Key"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10210","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:abc11577ac62891e9176aaa90291b859c12d54287b29aeae046decb7ec39910b","target":"record","created_at":"2026-07-05T09:20:49Z","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":"74c768cff5b831bb9a0ed76968059f0c38ba133eb3f3e6db722bedb1228a46bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T07:09:02Z","title_canon_sha256":"f2bd40ad4f25411f1cf8ec3abd03965218876e6f4d141c83398bf059e0416280"},"schema_version":"1.0","source":{"id":"2410.10210","kind":"arxiv","version":2}},"canonical_sha256":"022f0c669bd10e0b59339bb9800c4729d3f7ddfb16eb202d6a013ebf60340442","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"022f0c669bd10e0b59339bb9800c4729d3f7ddfb16eb202d6a013ebf60340442","first_computed_at":"2026-07-05T09:20:49.739155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:49.739155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h5TIOFl8HdYaCpiLuCMWm9+DoW/tSbr5QrkRiqB6e8ASZptYJmuzKlchqFv0h+NT0EOmCZQov70JRiRvMc2tAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:49.739638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10210","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abc11577ac62891e9176aaa90291b859c12d54287b29aeae046decb7ec39910b","sha256:86ff9f3e19e44bd82989369a6759ed22b42f1fbf36270240fb13e478d015f5a7"],"state_sha256":"3646933a87bc3f8f4f4e1cfcde88afaf6cbf97d7a7b9177b533529d944b735f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ewH57nf9qsp5qBk9zAd830xoGHyTU7on1S/C6RPYqYqt8oCSS6wgJd8WwvULLKVf42D40tG08/y8Qn8vzjx8Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:59:14.222054Z","bundle_sha256":"bdbf77204e1333e67967b49a87cd399f5737549b3753ef875ff2c91efa4105fd"}}