{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DULOFREYPFO44TDFLY52JPOARO","short_pith_number":"pith:DULOFREY","canonical_record":{"source":{"id":"2505.12762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T06:42:44Z","cross_cats_sorted":[],"title_canon_sha256":"bbf753163c89873b2fd789db60e9898950602468bf078c073694a06256c38856","abstract_canon_sha256":"d61ab34ab611998f08dc85c75f708e510cdc8cb1138cc7b4ea758aa19445edc5"},"schema_version":"1.0"},"canonical_sha256":"1d16e2c498795dce4c655e3ba4bdc08b99fe2b96d006e41e902228423faa8ef2","source":{"kind":"arxiv","id":"2505.12762","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12762","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12762v1","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12762","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"DULOFREYPFO4","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"DULOFREYPFO44TDF","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"DULOFREY","created_at":"2026-07-05T11:05:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DULOFREYPFO44TDFLY52JPOARO","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T06:42:44Z","cross_cats_sorted":[],"title_canon_sha256":"bbf753163c89873b2fd789db60e9898950602468bf078c073694a06256c38856","abstract_canon_sha256":"d61ab34ab611998f08dc85c75f708e510cdc8cb1138cc7b4ea758aa19445edc5"},"schema_version":"1.0"},"canonical_sha256":"1d16e2c498795dce4c655e3ba4bdc08b99fe2b96d006e41e902228423faa8ef2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:09.245240Z","signature_b64":"pHpWwglzW5pL1jZSgCDuaEhgc9kQTEzS3ZgBjesSIELImA919SGPXoFeG45L6fZ0b/I9UY80z9cIL71YwItwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d16e2c498795dce4c655e3ba4bdc08b99fe2b96d006e41e902228423faa8ef2","last_reissued_at":"2026-07-05T11:05:09.244790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:09.244790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12762","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":"2026-07-05T11:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QwYnKBlxNSiwgOWQ11UfSDwRrDlSFdMbkz5reYvWKWoucPuDHyBHvQvN8/uDP3e9smxM3eDvI7cHzooyEywPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T16:14:14.930130Z"},"content_sha256":"3009063f35461225dc9578df084994d22839cac8a3d2a32f2492b2c45299810e","schema_version":"1.0","event_id":"sha256:3009063f35461225dc9578df084994d22839cac8a3d2a32f2492b2c45299810e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DULOFREYPFO44TDFLY52JPOARO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chendi Qu, Chenlin Ming, Conghui He, Lijun Wu, Mengzhang Cai, Qizhi Pei, Xiaoming Duan, Yu Li, Zhuoshi Pan","submitted_at":"2025-05-19T06:42:44Z","abstract_excerpt":"Large Language Models (LLMs) have achieved impressive performance through Supervised Fine-tuning (SFT) on diverse instructional datasets. When training on multiple capabilities simultaneously, the mixture training dataset, governed by volumes of data from different domains, is a critical factor that directly impacts the final model's performance. Unlike many studies that focus on enhancing the quality of training datasets through data selection methods, few works explore the intricate relationship between the compositional quantity of mixture training datasets and the emergent capabilities of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12762","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/2505.12762/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":"2026-07-05T11:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HveBzRKnG3ehNga+kUPwZSYGvmzdGkvHJdv7QDK4WcLzYe96EDfSvi9bH1VeBAS0JvVsSavwwbkR/Wx8y5M2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T16:14:14.930646Z"},"content_sha256":"ea2ed798224110485fec7fd84b39161ecfa86ce2e921c59dfa55950d3a050642","schema_version":"1.0","event_id":"sha256:ea2ed798224110485fec7fd84b39161ecfa86ce2e921c59dfa55950d3a050642"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DULOFREYPFO44TDFLY52JPOARO/bundle.json","state_url":"https://pith.science/pith/DULOFREYPFO44TDFLY52JPOARO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DULOFREYPFO44TDFLY52JPOARO/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":"2026-08-16T16:14:14Z","links":{"resolver":"https://pith.science/pith/DULOFREYPFO44TDFLY52JPOARO","bundle":"https://pith.science/pith/DULOFREYPFO44TDFLY52JPOARO/bundle.json","state":"https://pith.science/pith/DULOFREYPFO44TDFLY52JPOARO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DULOFREYPFO44TDFLY52JPOARO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DULOFREYPFO44TDFLY52JPOARO","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":"d61ab34ab611998f08dc85c75f708e510cdc8cb1138cc7b4ea758aa19445edc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T06:42:44Z","title_canon_sha256":"bbf753163c89873b2fd789db60e9898950602468bf078c073694a06256c38856"},"schema_version":"1.0","source":{"id":"2505.12762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12762","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12762v1","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12762","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"DULOFREYPFO4","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"DULOFREYPFO44TDF","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"DULOFREY","created_at":"2026-07-05T11:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:ea2ed798224110485fec7fd84b39161ecfa86ce2e921c59dfa55950d3a050642","target":"graph","created_at":"2026-07-05T11:05:09Z","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/2505.12762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have achieved impressive performance through Supervised Fine-tuning (SFT) on diverse instructional datasets. When training on multiple capabilities simultaneously, the mixture training dataset, governed by volumes of data from different domains, is a critical factor that directly impacts the final model's performance. Unlike many studies that focus on enhancing the quality of training datasets through data selection methods, few works explore the intricate relationship between the compositional quantity of mixture training datasets and the emergent capabilities of ","authors_text":"Chendi Qu, Chenlin Ming, Conghui He, Lijun Wu, Mengzhang Cai, Qizhi Pei, Xiaoming Duan, Yu Li, Zhuoshi Pan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T06:42:44Z","title":"IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12762","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":"sha256:3009063f35461225dc9578df084994d22839cac8a3d2a32f2492b2c45299810e","target":"record","created_at":"2026-07-05T11:05:09Z","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":"d61ab34ab611998f08dc85c75f708e510cdc8cb1138cc7b4ea758aa19445edc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T06:42:44Z","title_canon_sha256":"bbf753163c89873b2fd789db60e9898950602468bf078c073694a06256c38856"},"schema_version":"1.0","source":{"id":"2505.12762","kind":"arxiv","version":1}},"canonical_sha256":"1d16e2c498795dce4c655e3ba4bdc08b99fe2b96d006e41e902228423faa8ef2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d16e2c498795dce4c655e3ba4bdc08b99fe2b96d006e41e902228423faa8ef2","first_computed_at":"2026-07-05T11:05:09.244790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:09.244790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pHpWwglzW5pL1jZSgCDuaEhgc9kQTEzS3ZgBjesSIELImA919SGPXoFeG45L6fZ0b/I9UY80z9cIL71YwItwBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:09.245240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3009063f35461225dc9578df084994d22839cac8a3d2a32f2492b2c45299810e","sha256:ea2ed798224110485fec7fd84b39161ecfa86ce2e921c59dfa55950d3a050642"],"state_sha256":"f0b920efff86ef1473df66a8e73bf7ac03f706f0f92576a79c9bd42d1a922268"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tZ/MFLYM3BFso4WjxY0xzs5RWmOkgZD0GitNroMC7BdRIW6iHZsaI4Y8LK2xS0dbpYQU1hAn7tudB0Kw5WbjAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T16:14:14.935820Z","bundle_sha256":"e178d5174331c57302b140dc2d5f12538df758b925cf2c6c5a241256c03c620c"}}