{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:P766BRZW45ZMOWCGMYU6BSRDHE","short_pith_number":"pith:P766BRZW","canonical_record":{"source":{"id":"2407.03040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T12:04:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc39fb0c262c7793ff335d471e279eecab57fdcf5790b9d3a3af26be9bfe3135","abstract_canon_sha256":"3c358e27b4e9d3e55073008e727d72471f915284cca50479907dddd46ecda01c"},"schema_version":"1.0"},"canonical_sha256":"7ffde0c736e772c758466629e0ca2339086645e6a8690f9a0831eacf6b225ff7","source":{"kind":"arxiv","id":"2407.03040","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03040","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03040v1","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03040","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"pith_short_12","alias_value":"P766BRZW45ZM","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"pith_short_16","alias_value":"P766BRZW45ZMOWCG","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"pith_short_8","alias_value":"P766BRZW","created_at":"2026-07-05T08:39:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:P766BRZW45ZMOWCGMYU6BSRDHE","target":"record","payload":{"canonical_record":{"source":{"id":"2407.03040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T12:04:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc39fb0c262c7793ff335d471e279eecab57fdcf5790b9d3a3af26be9bfe3135","abstract_canon_sha256":"3c358e27b4e9d3e55073008e727d72471f915284cca50479907dddd46ecda01c"},"schema_version":"1.0"},"canonical_sha256":"7ffde0c736e772c758466629e0ca2339086645e6a8690f9a0831eacf6b225ff7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:45.526477Z","signature_b64":"alBo4DitdvppMuK35KjAkbKUzrMZN4Ng6HsHfnrza17yRym031JGc9/mbFDtGr6jNMDY3e+cow3TpJYXUHuxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ffde0c736e772c758466629e0ca2339086645e6a8690f9a0831eacf6b225ff7","last_reissued_at":"2026-07-05T08:39:45.525908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:45.525908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.03040","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":"2026-07-05T08:39:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y3KpkzZ0adUXt6SupwDWX5wN/h6Rd++OjsmGPb4EHjG4ghfjeHorWI3JkKX6keosPjLleTlNioNFa6WPRZgRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:37:45.681749Z"},"content_sha256":"90101c95273ec4aa0f5ba4e15b8df64a092cf623db61aa2471457812c2c031e6","schema_version":"1.0","event_id":"sha256:90101c95273ec4aa0f5ba4e15b8df64a092cf623db61aa2471457812c2c031e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:P766BRZW45ZMOWCGMYU6BSRDHE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Raw Text is All you Need: Knowledge-intensive Multi-turn Instruction Tuning for Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hangyuan Ji, Jian Yang, Jingbo Dun, Jixuan Nie, Linzheng Chai, Qifeng Li, Tongliang Li, Wenfeng Song, Xia Hou, Xianjie Wu, Zhoujun Li","submitted_at":"2024-07-03T12:04:10Z","abstract_excerpt":"Instruction tuning as an effective technique aligns the outputs of large language models (LLMs) with human preference. But how to generate the seasonal multi-turn dialogues from raw documents for instruction tuning still requires further exploration. In this paper, we present a novel framework named R2S that leverages the CoD-Chain of Dialogue logic to guide large language models (LLMs) in generating knowledge-intensive multi-turn dialogues for instruction tuning. By integrating raw documents from both open-source datasets and domain-specific web-crawled documents into a benchmark K-BENCH, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03040","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/2407.03040/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":"2026-07-05T08:39:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eGZJ0W9O6qJ/YoSnAOwchCMSKeZ6T2UPRDF+ihOgNv4jGM+S3muZ8vhwngYrC/r4t86WgJRFGNivnW+Ho12oBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:37:45.682303Z"},"content_sha256":"acef0ac33a922eff1d7260921ea1d24ae6c27ba94626a666dc6cfe95b960b51d","schema_version":"1.0","event_id":"sha256:acef0ac33a922eff1d7260921ea1d24ae6c27ba94626a666dc6cfe95b960b51d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P766BRZW45ZMOWCGMYU6BSRDHE/bundle.json","state_url":"https://pith.science/pith/P766BRZW45ZMOWCGMYU6BSRDHE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P766BRZW45ZMOWCGMYU6BSRDHE/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":"2026-08-22T09:37:45Z","links":{"resolver":"https://pith.science/pith/P766BRZW45ZMOWCGMYU6BSRDHE","bundle":"https://pith.science/pith/P766BRZW45ZMOWCGMYU6BSRDHE/bundle.json","state":"https://pith.science/pith/P766BRZW45ZMOWCGMYU6BSRDHE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P766BRZW45ZMOWCGMYU6BSRDHE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P766BRZW45ZMOWCGMYU6BSRDHE","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":"3c358e27b4e9d3e55073008e727d72471f915284cca50479907dddd46ecda01c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T12:04:10Z","title_canon_sha256":"dc39fb0c262c7793ff335d471e279eecab57fdcf5790b9d3a3af26be9bfe3135"},"schema_version":"1.0","source":{"id":"2407.03040","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03040","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03040v1","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03040","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"pith_short_12","alias_value":"P766BRZW45ZM","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"pith_short_16","alias_value":"P766BRZW45ZMOWCG","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"pith_short_8","alias_value":"P766BRZW","created_at":"2026-07-05T08:39:45Z"}],"graph_snapshots":[{"event_id":"sha256:acef0ac33a922eff1d7260921ea1d24ae6c27ba94626a666dc6cfe95b960b51d","target":"graph","created_at":"2026-07-05T08:39:45Z","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/2407.03040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning as an effective technique aligns the outputs of large language models (LLMs) with human preference. But how to generate the seasonal multi-turn dialogues from raw documents for instruction tuning still requires further exploration. In this paper, we present a novel framework named R2S that leverages the CoD-Chain of Dialogue logic to guide large language models (LLMs) in generating knowledge-intensive multi-turn dialogues for instruction tuning. By integrating raw documents from both open-source datasets and domain-specific web-crawled documents into a benchmark K-BENCH, we ","authors_text":"Hangyuan Ji, Jian Yang, Jingbo Dun, Jixuan Nie, Linzheng Chai, Qifeng Li, Tongliang Li, Wenfeng Song, Xia Hou, Xianjie Wu, Zhoujun Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T12:04:10Z","title":"Raw Text is All you Need: Knowledge-intensive Multi-turn Instruction Tuning for Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03040","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":"sha256:90101c95273ec4aa0f5ba4e15b8df64a092cf623db61aa2471457812c2c031e6","target":"record","created_at":"2026-07-05T08:39:45Z","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":"3c358e27b4e9d3e55073008e727d72471f915284cca50479907dddd46ecda01c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T12:04:10Z","title_canon_sha256":"dc39fb0c262c7793ff335d471e279eecab57fdcf5790b9d3a3af26be9bfe3135"},"schema_version":"1.0","source":{"id":"2407.03040","kind":"arxiv","version":1}},"canonical_sha256":"7ffde0c736e772c758466629e0ca2339086645e6a8690f9a0831eacf6b225ff7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ffde0c736e772c758466629e0ca2339086645e6a8690f9a0831eacf6b225ff7","first_computed_at":"2026-07-05T08:39:45.525908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:45.525908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"alBo4DitdvppMuK35KjAkbKUzrMZN4Ng6HsHfnrza17yRym031JGc9/mbFDtGr6jNMDY3e+cow3TpJYXUHuxDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:45.526477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03040","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90101c95273ec4aa0f5ba4e15b8df64a092cf623db61aa2471457812c2c031e6","sha256:acef0ac33a922eff1d7260921ea1d24ae6c27ba94626a666dc6cfe95b960b51d"],"state_sha256":"5b30cf4cac9f0c73745f23c5f5694a024e2bc6342626104653526c74668edb59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qMW93jvEHiCZqq18o/genpYgVkQ4k2AWLFzAmmIFITXNFR+tjzfC95aqw0VnAbGh9Kg8qV1MyMH2p98rwhi6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T09:37:45.689227Z","bundle_sha256":"7007fc3a6c0991abacb121d41812c677918d1a01e844cba6dc5f3edb7ba385c7"}}