{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y3HD7TB4JS4NZXLIGXCRN7U37I","short_pith_number":"pith:Y3HD7TB4","canonical_record":{"source":{"id":"2508.17677","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-25T05:18:32Z","cross_cats_sorted":[],"title_canon_sha256":"9f0c50ffa328a4d993ef8fad9be5526350dca798b203fbcb0266fe8c10eb9e64","abstract_canon_sha256":"f90229af4eae3e4a46ad91d432ccb64ddac5c207c261ce16c4227ebf4f5b74e3"},"schema_version":"1.0"},"canonical_sha256":"c6ce3fcc3c4cb8dcdd6835c516fe9bfa370fa93bf4be4dbe31414571044dfc49","source":{"kind":"arxiv","id":"2508.17677","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17677","created_at":"2026-07-05T11:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17677v1","created_at":"2026-07-05T11:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17677","created_at":"2026-07-05T11:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"Y3HD7TB4JS4N","created_at":"2026-07-05T11:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"Y3HD7TB4JS4NZXLI","created_at":"2026-07-05T11:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"Y3HD7TB4","created_at":"2026-07-05T11:58:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y3HD7TB4JS4NZXLIGXCRN7U37I","target":"record","payload":{"canonical_record":{"source":{"id":"2508.17677","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-25T05:18:32Z","cross_cats_sorted":[],"title_canon_sha256":"9f0c50ffa328a4d993ef8fad9be5526350dca798b203fbcb0266fe8c10eb9e64","abstract_canon_sha256":"f90229af4eae3e4a46ad91d432ccb64ddac5c207c261ce16c4227ebf4f5b74e3"},"schema_version":"1.0"},"canonical_sha256":"c6ce3fcc3c4cb8dcdd6835c516fe9bfa370fa93bf4be4dbe31414571044dfc49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:45.656528Z","signature_b64":"7D7Ocu0UhFzhxLUwy9GUlXQnfbk5/FnlNacz2VDv/GWnAvstmh70MVxcs6GLglGU6txT2Np/gbKIOdUf5EyJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6ce3fcc3c4cb8dcdd6835c516fe9bfa370fa93bf4be4dbe31414571044dfc49","last_reissued_at":"2026-07-05T11:58:45.656044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:45.656044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.17677","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":"2026-07-05T11:58:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s9fMneH5Ie6cNPnaqDbyLC0vJeN4w6ya74EKorqzVyoSNK2Ji5gXWLQEMHo2PvLnR4tCk9sqm2JWbqrxYzJdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:13:09.127850Z"},"content_sha256":"b3bd9e519df82d775ab427c3b7e40df54322a858ca232511e7138fa5d967c3d1","schema_version":"1.0","event_id":"sha256:b3bd9e519df82d775ab427c3b7e40df54322a858ca232511e7138fa5d967c3d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y3HD7TB4JS4NZXLIGXCRN7U37I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Binbin Liu, Fengze Liu, Jiyao Deng, Taifeng Wang, Weidong Zhou, Xiaohuan Zhou, Xuecheng Wu, Yifan Wang, Yuanfan Guo","submitted_at":"2025-08-25T05:18:32Z","abstract_excerpt":"The data mixture used in the pre-training of a language model is a cornerstone of its final performance. However, a static mixing strategy is suboptimal, as the model's learning preferences for various data domains shift dynamically throughout training. Crucially, observing these evolving preferences in a computationally efficient manner remains a significant challenge. To address this, we propose TiKMiX, a method that dynamically adjusts the data mixture according to the model's evolving preferences. TiKMiX introduces Group Influence, an efficient metric for evaluating the impact of data doma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17677","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/2508.17677/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":"2026-07-05T11:58:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bp54J48Q2fo7BjfjYCHawNsZLYRDA9nKtxQ+oJZjMggLG2TrVWQN8sUDiLjOCLtX867Ow2hD2RV1LgSruBpGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:13:09.128279Z"},"content_sha256":"a100dc9934f2c3b9865fe4c779e7d248500a59848939302a3c2c847bccf39afa","schema_version":"1.0","event_id":"sha256:a100dc9934f2c3b9865fe4c779e7d248500a59848939302a3c2c847bccf39afa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y3HD7TB4JS4NZXLIGXCRN7U37I/bundle.json","state_url":"https://pith.science/pith/Y3HD7TB4JS4NZXLIGXCRN7U37I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y3HD7TB4JS4NZXLIGXCRN7U37I/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":"2026-08-05T14:13:09Z","links":{"resolver":"https://pith.science/pith/Y3HD7TB4JS4NZXLIGXCRN7U37I","bundle":"https://pith.science/pith/Y3HD7TB4JS4NZXLIGXCRN7U37I/bundle.json","state":"https://pith.science/pith/Y3HD7TB4JS4NZXLIGXCRN7U37I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y3HD7TB4JS4NZXLIGXCRN7U37I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y3HD7TB4JS4NZXLIGXCRN7U37I","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":"f90229af4eae3e4a46ad91d432ccb64ddac5c207c261ce16c4227ebf4f5b74e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-25T05:18:32Z","title_canon_sha256":"9f0c50ffa328a4d993ef8fad9be5526350dca798b203fbcb0266fe8c10eb9e64"},"schema_version":"1.0","source":{"id":"2508.17677","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17677","created_at":"2026-07-05T11:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17677v1","created_at":"2026-07-05T11:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17677","created_at":"2026-07-05T11:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"Y3HD7TB4JS4N","created_at":"2026-07-05T11:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"Y3HD7TB4JS4NZXLI","created_at":"2026-07-05T11:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"Y3HD7TB4","created_at":"2026-07-05T11:58:45Z"}],"graph_snapshots":[{"event_id":"sha256:a100dc9934f2c3b9865fe4c779e7d248500a59848939302a3c2c847bccf39afa","target":"graph","created_at":"2026-07-05T11:58:45Z","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/2508.17677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The data mixture used in the pre-training of a language model is a cornerstone of its final performance. However, a static mixing strategy is suboptimal, as the model's learning preferences for various data domains shift dynamically throughout training. Crucially, observing these evolving preferences in a computationally efficient manner remains a significant challenge. To address this, we propose TiKMiX, a method that dynamically adjusts the data mixture according to the model's evolving preferences. TiKMiX introduces Group Influence, an efficient metric for evaluating the impact of data doma","authors_text":"Binbin Liu, Fengze Liu, Jiyao Deng, Taifeng Wang, Weidong Zhou, Xiaohuan Zhou, Xuecheng Wu, Yifan Wang, Yuanfan Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-25T05:18:32Z","title":"TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17677","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:b3bd9e519df82d775ab427c3b7e40df54322a858ca232511e7138fa5d967c3d1","target":"record","created_at":"2026-07-05T11:58:45Z","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":"f90229af4eae3e4a46ad91d432ccb64ddac5c207c261ce16c4227ebf4f5b74e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-25T05:18:32Z","title_canon_sha256":"9f0c50ffa328a4d993ef8fad9be5526350dca798b203fbcb0266fe8c10eb9e64"},"schema_version":"1.0","source":{"id":"2508.17677","kind":"arxiv","version":1}},"canonical_sha256":"c6ce3fcc3c4cb8dcdd6835c516fe9bfa370fa93bf4be4dbe31414571044dfc49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6ce3fcc3c4cb8dcdd6835c516fe9bfa370fa93bf4be4dbe31414571044dfc49","first_computed_at":"2026-07-05T11:58:45.656044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:45.656044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7D7Ocu0UhFzhxLUwy9GUlXQnfbk5/FnlNacz2VDv/GWnAvstmh70MVxcs6GLglGU6txT2Np/gbKIOdUf5EyJDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:45.656528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.17677","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3bd9e519df82d775ab427c3b7e40df54322a858ca232511e7138fa5d967c3d1","sha256:a100dc9934f2c3b9865fe4c779e7d248500a59848939302a3c2c847bccf39afa"],"state_sha256":"ad978fa11f2d5eb74494833263f91b655b43934ef22ecc6385e59418ca358c74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OTf2+5RHVNtOqX54YDORcWxR9PXhjaC6zw0JcyxnkccTiObhr6/0fe1SKf9XqtSF91KoH2lo7hX6kx1XaBg2Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:13:09.132275Z","bundle_sha256":"bbab70fb377178b392fdfab57271964c891037914ceae2097a6e9b0a554570d2"}}