{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VM2FN2YZPZ7FBEHQZ2DFI5Z3NH","short_pith_number":"pith:VM2FN2YZ","canonical_record":{"source":{"id":"2506.11116","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T06:37:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d00ac5d7961b58d2f7cd428ad2f04a802737e7f8bc8e28f91042ce271cf328c4","abstract_canon_sha256":"af84c1a9fd0f330070e3853050400f4a7665721221e2af2871f1d788e2dbd795"},"schema_version":"1.0"},"canonical_sha256":"ab3456eb197e7e5090f0ce8654773b69f4656eaa9a87b1db070cfd2ad08c50b1","source":{"kind":"arxiv","id":"2506.11116","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11116","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11116v1","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11116","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"VM2FN2YZPZ7F","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_16","alias_value":"VM2FN2YZPZ7FBEHQ","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_8","alias_value":"VM2FN2YZ","created_at":"2026-07-05T11:20:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VM2FN2YZPZ7FBEHQZ2DFI5Z3NH","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11116","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T06:37:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d00ac5d7961b58d2f7cd428ad2f04a802737e7f8bc8e28f91042ce271cf328c4","abstract_canon_sha256":"af84c1a9fd0f330070e3853050400f4a7665721221e2af2871f1d788e2dbd795"},"schema_version":"1.0"},"canonical_sha256":"ab3456eb197e7e5090f0ce8654773b69f4656eaa9a87b1db070cfd2ad08c50b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:59.726267Z","signature_b64":"Vng+ZNMDLWW8KqYyqMwhvaUwJ2SKH9EmYdErWuM/Bn3hrT7fa5/5+OCmmaALh7rMa5TJNbVjjCei4l/UsmmpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab3456eb197e7e5090f0ce8654773b69f4656eaa9a87b1db070cfd2ad08c50b1","last_reissued_at":"2026-07-05T11:20:59.725514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:59.725514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11116","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":"2026-07-05T11:20:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f7swWbLZemG3tKYSCjpDaI84iLuQB2AOf8p5E+lFexU7N87btJlznwTualGT6x5Ww8m6KSIdaIaF8yOnMdo0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T14:54:01.638543Z"},"content_sha256":"7d7fd763313cb623b3830e663bb9f3b2e21f3b7fabd8c3f26c248a66838a7901","schema_version":"1.0","event_id":"sha256:7d7fd763313cb623b3830e663bb9f3b2e21f3b7fabd8c3f26c248a66838a7901"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VM2FN2YZPZ7FBEHQZ2DFI5Z3NH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo-Wen Zhang, Boyan Gao, Guang Liu, Hanyu Zhao, Jijie Li, Liangdong Wang, Li Du, Yonghua Lin","submitted_at":"2025-06-09T06:37:15Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate strong performance in real-world applications, yet existing open-source instruction datasets often concentrate on narrow domains, such as mathematics or coding, limiting generalization and widening the gap with proprietary models. To bridge this gap, we introduce Infinity-Instruct, a high-quality instruction dataset designed to enhance both foundational and chat capabilities of LLMs through a two-phase pipeline. In Phase 1, we curate 7.4M high-quality foundational instructions (InfInstruct-F-7.4M) from over 100M samples using hybrid data selection techn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11116","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/2506.11116/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":"2026-07-05T11:20:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qIbh482GhkwYPbKy9AcHRz11W80umJV5JPuSt812wvKnCatyUnxpNUogrsvHZ05VNYJ+xKcuj4KaJFM4pgvrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T14:54:01.638935Z"},"content_sha256":"caff703a58668b2d91da2e391e371482bca4d3e402bc9856808a2a213fb35a02","schema_version":"1.0","event_id":"sha256:caff703a58668b2d91da2e391e371482bca4d3e402bc9856808a2a213fb35a02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VM2FN2YZPZ7FBEHQZ2DFI5Z3NH/bundle.json","state_url":"https://pith.science/pith/VM2FN2YZPZ7FBEHQZ2DFI5Z3NH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VM2FN2YZPZ7FBEHQZ2DFI5Z3NH/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":"2026-07-27T14:54:01Z","links":{"resolver":"https://pith.science/pith/VM2FN2YZPZ7FBEHQZ2DFI5Z3NH","bundle":"https://pith.science/pith/VM2FN2YZPZ7FBEHQZ2DFI5Z3NH/bundle.json","state":"https://pith.science/pith/VM2FN2YZPZ7FBEHQZ2DFI5Z3NH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VM2FN2YZPZ7FBEHQZ2DFI5Z3NH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VM2FN2YZPZ7FBEHQZ2DFI5Z3NH","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":"af84c1a9fd0f330070e3853050400f4a7665721221e2af2871f1d788e2dbd795","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T06:37:15Z","title_canon_sha256":"d00ac5d7961b58d2f7cd428ad2f04a802737e7f8bc8e28f91042ce271cf328c4"},"schema_version":"1.0","source":{"id":"2506.11116","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11116","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11116v1","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11116","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"VM2FN2YZPZ7F","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_16","alias_value":"VM2FN2YZPZ7FBEHQ","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_8","alias_value":"VM2FN2YZ","created_at":"2026-07-05T11:20:59Z"}],"graph_snapshots":[{"event_id":"sha256:caff703a58668b2d91da2e391e371482bca4d3e402bc9856808a2a213fb35a02","target":"graph","created_at":"2026-07-05T11:20:59Z","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/2506.11116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) demonstrate strong performance in real-world applications, yet existing open-source instruction datasets often concentrate on narrow domains, such as mathematics or coding, limiting generalization and widening the gap with proprietary models. To bridge this gap, we introduce Infinity-Instruct, a high-quality instruction dataset designed to enhance both foundational and chat capabilities of LLMs through a two-phase pipeline. In Phase 1, we curate 7.4M high-quality foundational instructions (InfInstruct-F-7.4M) from over 100M samples using hybrid data selection techn","authors_text":"Bo-Wen Zhang, Boyan Gao, Guang Liu, Hanyu Zhao, Jijie Li, Liangdong Wang, Li Du, Yonghua Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T06:37:15Z","title":"Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11116","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":"sha256:7d7fd763313cb623b3830e663bb9f3b2e21f3b7fabd8c3f26c248a66838a7901","target":"record","created_at":"2026-07-05T11:20:59Z","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":"af84c1a9fd0f330070e3853050400f4a7665721221e2af2871f1d788e2dbd795","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T06:37:15Z","title_canon_sha256":"d00ac5d7961b58d2f7cd428ad2f04a802737e7f8bc8e28f91042ce271cf328c4"},"schema_version":"1.0","source":{"id":"2506.11116","kind":"arxiv","version":1}},"canonical_sha256":"ab3456eb197e7e5090f0ce8654773b69f4656eaa9a87b1db070cfd2ad08c50b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab3456eb197e7e5090f0ce8654773b69f4656eaa9a87b1db070cfd2ad08c50b1","first_computed_at":"2026-07-05T11:20:59.725514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:59.725514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vng+ZNMDLWW8KqYyqMwhvaUwJ2SKH9EmYdErWuM/Bn3hrT7fa5/5+OCmmaALh7rMa5TJNbVjjCei4l/UsmmpDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:59.726267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11116","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d7fd763313cb623b3830e663bb9f3b2e21f3b7fabd8c3f26c248a66838a7901","sha256:caff703a58668b2d91da2e391e371482bca4d3e402bc9856808a2a213fb35a02"],"state_sha256":"d05404a8f98920cc9a45178fb1905d668cf916b8b20bd9f6c33e18a0d32dae88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G7UbRkjKIs/7tsQsX0rK2yDSxFHmhyQhfui0/iBCIS7Lm+GjvfkhCHgpUKranGqwqXQES/tuPHK3xavbxz8pBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T14:54:01.641807Z","bundle_sha256":"b7892f9c2649cb649229492f1fdce9034f30f03c635151aace2d90d897795af0"}}