{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KYFTQOSR4XYUTMZK4KYYCXU35N","short_pith_number":"pith:KYFTQOSR","canonical_record":{"source":{"id":"2606.24133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T04:32:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"05acf51fa6bb38afea7713719be43d7ae444d830b5f3b9640d073cb5005d723f","abstract_canon_sha256":"ab5a0c088e27837b423db200df9e7e795d57767a4099ac298b86d453cb9acbe4"},"schema_version":"1.0"},"canonical_sha256":"560b383a51e5f149b32ae2b1815e9beb637729c258012fd27022106187c99e49","source":{"kind":"arxiv","id":"2606.24133","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24133","created_at":"2026-06-24T01:14:41Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24133v1","created_at":"2026-06-24T01:14:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24133","created_at":"2026-06-24T01:14:41Z"},{"alias_kind":"pith_short_12","alias_value":"KYFTQOSR4XYU","created_at":"2026-06-24T01:14:41Z"},{"alias_kind":"pith_short_16","alias_value":"KYFTQOSR4XYUTMZK","created_at":"2026-06-24T01:14:41Z"},{"alias_kind":"pith_short_8","alias_value":"KYFTQOSR","created_at":"2026-06-24T01:14:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KYFTQOSR4XYUTMZK4KYYCXU35N","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T04:32:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"05acf51fa6bb38afea7713719be43d7ae444d830b5f3b9640d073cb5005d723f","abstract_canon_sha256":"ab5a0c088e27837b423db200df9e7e795d57767a4099ac298b86d453cb9acbe4"},"schema_version":"1.0"},"canonical_sha256":"560b383a51e5f149b32ae2b1815e9beb637729c258012fd27022106187c99e49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:41.935877Z","signature_b64":"1Byf5glXHRPpAbrRjSJQTUZ6aGEazoUYEpvARtnMh1hKWD1wyXE7Gtk28zYFld9T2SVRhAFnKRwTD0TMScb2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"560b383a51e5f149b32ae2b1815e9beb637729c258012fd27022106187c99e49","last_reissued_at":"2026-06-24T01:14:41.935450Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:41.935450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24133","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":"2026-06-24T01:14:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hjoEcKoci7Jk5IfO/TiZKs8d9AdFqpwigyguXvQ1U56up8aD4rZBEpZ1H9jo7tF0k+ryIjAoawmwfQ6b3emxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T20:23:43.709731Z"},"content_sha256":"bf6523835814752d2f483d6ec56bf3c8c7af0dfa335a42cb8ac9f1b22c030cb9","schema_version":"1.0","event_id":"sha256:bf6523835814752d2f483d6ec56bf3c8c7af0dfa335a42cb8ac9f1b22c030cb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KYFTQOSR4XYUTMZK4KYYCXU35N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Chenhao Dang, Jing Ma, Mingjie Liao","submitted_at":"2026-06-23T04:32:46Z","abstract_excerpt":"The composition of training data, governed by the diversity of sources and their mixing strategy, is a cornerstone of Large Language Model (LLM) pre-training. Online Data Mixing (ODM), the technique of adaptively adjusting data mixtures during training, has emerged as a promising direction to improve efficiency. However, existing methods are constrained by their reliance on a singular optimization perspective, which fundamentally overlooks the need for complex LLM pre-training to consider the dynamic data composition from multiple dimensions. To overcome this limitation, we introduce the Holis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24133","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/2606.24133/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":"2026-06-24T01:14:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RRx4ASt2UII+w1+gPJPNB5Twer+in60r7vpABx8nM3SLTGmT3ljqwjjc0BinKPFpJbVn14vUYwi4R8JX5QOHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T20:23:43.710095Z"},"content_sha256":"0c9dccea6aa60ee5bbe36aa52243a16aee1d77992505994201785406c305f425","schema_version":"1.0","event_id":"sha256:0c9dccea6aa60ee5bbe36aa52243a16aee1d77992505994201785406c305f425"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KYFTQOSR4XYUTMZK4KYYCXU35N/bundle.json","state_url":"https://pith.science/pith/KYFTQOSR4XYUTMZK4KYYCXU35N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KYFTQOSR4XYUTMZK4KYYCXU35N/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":"2026-06-28T20:23:43Z","links":{"resolver":"https://pith.science/pith/KYFTQOSR4XYUTMZK4KYYCXU35N","bundle":"https://pith.science/pith/KYFTQOSR4XYUTMZK4KYYCXU35N/bundle.json","state":"https://pith.science/pith/KYFTQOSR4XYUTMZK4KYYCXU35N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KYFTQOSR4XYUTMZK4KYYCXU35N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KYFTQOSR4XYUTMZK4KYYCXU35N","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":"ab5a0c088e27837b423db200df9e7e795d57767a4099ac298b86d453cb9acbe4","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T04:32:46Z","title_canon_sha256":"05acf51fa6bb38afea7713719be43d7ae444d830b5f3b9640d073cb5005d723f"},"schema_version":"1.0","source":{"id":"2606.24133","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24133","created_at":"2026-06-24T01:14:41Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24133v1","created_at":"2026-06-24T01:14:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24133","created_at":"2026-06-24T01:14:41Z"},{"alias_kind":"pith_short_12","alias_value":"KYFTQOSR4XYU","created_at":"2026-06-24T01:14:41Z"},{"alias_kind":"pith_short_16","alias_value":"KYFTQOSR4XYUTMZK","created_at":"2026-06-24T01:14:41Z"},{"alias_kind":"pith_short_8","alias_value":"KYFTQOSR","created_at":"2026-06-24T01:14:41Z"}],"graph_snapshots":[{"event_id":"sha256:0c9dccea6aa60ee5bbe36aa52243a16aee1d77992505994201785406c305f425","target":"graph","created_at":"2026-06-24T01:14:41Z","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/2606.24133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The composition of training data, governed by the diversity of sources and their mixing strategy, is a cornerstone of Large Language Model (LLM) pre-training. Online Data Mixing (ODM), the technique of adaptively adjusting data mixtures during training, has emerged as a promising direction to improve efficiency. However, existing methods are constrained by their reliance on a singular optimization perspective, which fundamentally overlooks the need for complex LLM pre-training to consider the dynamic data composition from multiple dimensions. To overcome this limitation, we introduce the Holis","authors_text":"Chenhao Dang, Jing Ma, Mingjie Liao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T04:32:46Z","title":"Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24133","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:bf6523835814752d2f483d6ec56bf3c8c7af0dfa335a42cb8ac9f1b22c030cb9","target":"record","created_at":"2026-06-24T01:14:41Z","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":"ab5a0c088e27837b423db200df9e7e795d57767a4099ac298b86d453cb9acbe4","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T04:32:46Z","title_canon_sha256":"05acf51fa6bb38afea7713719be43d7ae444d830b5f3b9640d073cb5005d723f"},"schema_version":"1.0","source":{"id":"2606.24133","kind":"arxiv","version":1}},"canonical_sha256":"560b383a51e5f149b32ae2b1815e9beb637729c258012fd27022106187c99e49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"560b383a51e5f149b32ae2b1815e9beb637729c258012fd27022106187c99e49","first_computed_at":"2026-06-24T01:14:41.935450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:41.935450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Byf5glXHRPpAbrRjSJQTUZ6aGEazoUYEpvARtnMh1hKWD1wyXE7Gtk28zYFld9T2SVRhAFnKRwTD0TMScb2BA==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:41.935877Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24133","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf6523835814752d2f483d6ec56bf3c8c7af0dfa335a42cb8ac9f1b22c030cb9","sha256:0c9dccea6aa60ee5bbe36aa52243a16aee1d77992505994201785406c305f425"],"state_sha256":"381218ec83a14d11f725e30ca96eff6043831646447b8e6c0b9251769b50786d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"faZgJDJgXWu+RScFiQzj0vZd6Tvt0wOlm4n3WypAF9yI2rVcKPsluZYIghB2kWFRVZw8wrlIh3Z82MieMQLADw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T20:23:43.712120Z","bundle_sha256":"2b018aad6babf41ad16e2384b49f2b9a35250b61f06cfddc0d630ef805d31893"}}