{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PALPQJYT7MKQS64DEPUNK6NJ2V","short_pith_number":"pith:PALPQJYT","canonical_record":{"source":{"id":"2411.05735","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-08T17:50:24Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"0c5f75e68fac0c35bb2275b3023078e19ebbf8389181158af042cf97b290104e","abstract_canon_sha256":"788c358109a5fbed05d4023a0c4b55237099d045fd1f9b54a162d0b1d93f5be6"},"schema_version":"1.0"},"canonical_sha256":"7816f82713fb15097b8323e8d579a9d5477c481449ad9df982a80fe634e4fd71","source":{"kind":"arxiv","id":"2411.05735","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05735","created_at":"2026-07-05T10:51:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05735v2","created_at":"2026-07-05T10:51:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05735","created_at":"2026-07-05T10:51:28Z"},{"alias_kind":"pith_short_12","alias_value":"PALPQJYT7MKQ","created_at":"2026-07-05T10:51:28Z"},{"alias_kind":"pith_short_16","alias_value":"PALPQJYT7MKQS64D","created_at":"2026-07-05T10:51:28Z"},{"alias_kind":"pith_short_8","alias_value":"PALPQJYT","created_at":"2026-07-05T10:51:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PALPQJYT7MKQS64DEPUNK6NJ2V","target":"record","payload":{"canonical_record":{"source":{"id":"2411.05735","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-08T17:50:24Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"0c5f75e68fac0c35bb2275b3023078e19ebbf8389181158af042cf97b290104e","abstract_canon_sha256":"788c358109a5fbed05d4023a0c4b55237099d045fd1f9b54a162d0b1d93f5be6"},"schema_version":"1.0"},"canonical_sha256":"7816f82713fb15097b8323e8d579a9d5477c481449ad9df982a80fe634e4fd71","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:28.182002Z","signature_b64":"KL463fnOgucWiM/OrzG8usnclgOT1g+T0LI26gkS2aQ8HK3GaqQhHvenzIG5kSwtf7bHXgeDLPatDAnWJeuDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7816f82713fb15097b8323e8d579a9d5477c481449ad9df982a80fe634e4fd71","last_reissued_at":"2026-07-05T10:51:28.181517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:28.181517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.05735","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:51:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XmKdvnHFLFV94Y0dM9uDVlZ/dK7EJ5l9mkjQshOsRtePO0tkPwC+LbC2SoUD8rRYfglw8LzN3H1/jC2Ipqg0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:48:26.540875Z"},"content_sha256":"ba9412847e58f81d0e8b1aa5c48c46f4dcc2c4b979b883d763ab197bf8d1df1a","schema_version":"1.0","event_id":"sha256:ba9412847e58f81d0e8b1aa5c48c46f4dcc2c4b979b883d763ab197bf8d1df1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PALPQJYT7MKQS64DEPUNK6NJ2V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher R\\'e, Kyunghyun Cho, Mayee F. Chen, Michael Y. Hu, Nicholas Lourie","submitted_at":"2024-11-08T17:50:24Z","abstract_excerpt":"Language model performance depends on identifying the optimal mixture of data groups to train on (e.g., law, code, math). Prior work has proposed a diverse set of methods to efficiently learn mixture proportions, ranging from fitting regression models over training runs to dynamically updating proportions throughout training. Surprisingly, we find that no existing method consistently outperforms a simple stratified sampling baseline in terms of average test perplexity. To understand this inconsistency, we unify existing methods into a standard framework, showing they are equivalent to solving "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05735","kind":"arxiv","version":2},"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/2411.05735/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":"2026-07-05T10:51:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yVSPnI/qCZ5SO4ydKz+u2IwutdLgfRQnY34tvih29iFNNvnizNgOWVYSsfHsmk3xferXIXSO4msF6TbbDh7pDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:48:26.541255Z"},"content_sha256":"d3a58821688c883b5599273dab4429c7a87604522f0dee3366478d94286cbc7a","schema_version":"1.0","event_id":"sha256:d3a58821688c883b5599273dab4429c7a87604522f0dee3366478d94286cbc7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PALPQJYT7MKQS64DEPUNK6NJ2V/bundle.json","state_url":"https://pith.science/pith/PALPQJYT7MKQS64DEPUNK6NJ2V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PALPQJYT7MKQS64DEPUNK6NJ2V/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":"2026-07-06T23:48:26Z","links":{"resolver":"https://pith.science/pith/PALPQJYT7MKQS64DEPUNK6NJ2V","bundle":"https://pith.science/pith/PALPQJYT7MKQS64DEPUNK6NJ2V/bundle.json","state":"https://pith.science/pith/PALPQJYT7MKQS64DEPUNK6NJ2V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PALPQJYT7MKQS64DEPUNK6NJ2V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PALPQJYT7MKQS64DEPUNK6NJ2V","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":"788c358109a5fbed05d4023a0c4b55237099d045fd1f9b54a162d0b1d93f5be6","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-08T17:50:24Z","title_canon_sha256":"0c5f75e68fac0c35bb2275b3023078e19ebbf8389181158af042cf97b290104e"},"schema_version":"1.0","source":{"id":"2411.05735","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05735","created_at":"2026-07-05T10:51:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05735v2","created_at":"2026-07-05T10:51:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05735","created_at":"2026-07-05T10:51:28Z"},{"alias_kind":"pith_short_12","alias_value":"PALPQJYT7MKQ","created_at":"2026-07-05T10:51:28Z"},{"alias_kind":"pith_short_16","alias_value":"PALPQJYT7MKQS64D","created_at":"2026-07-05T10:51:28Z"},{"alias_kind":"pith_short_8","alias_value":"PALPQJYT","created_at":"2026-07-05T10:51:28Z"}],"graph_snapshots":[{"event_id":"sha256:d3a58821688c883b5599273dab4429c7a87604522f0dee3366478d94286cbc7a","target":"graph","created_at":"2026-07-05T10:51:28Z","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/2411.05735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model performance depends on identifying the optimal mixture of data groups to train on (e.g., law, code, math). Prior work has proposed a diverse set of methods to efficiently learn mixture proportions, ranging from fitting regression models over training runs to dynamically updating proportions throughout training. Surprisingly, we find that no existing method consistently outperforms a simple stratified sampling baseline in terms of average test perplexity. To understand this inconsistency, we unify existing methods into a standard framework, showing they are equivalent to solving ","authors_text":"Christopher R\\'e, Kyunghyun Cho, Mayee F. Chen, Michael Y. Hu, Nicholas Lourie","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-08T17:50:24Z","title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05735","kind":"arxiv","version":2},"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:ba9412847e58f81d0e8b1aa5c48c46f4dcc2c4b979b883d763ab197bf8d1df1a","target":"record","created_at":"2026-07-05T10:51:28Z","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":"788c358109a5fbed05d4023a0c4b55237099d045fd1f9b54a162d0b1d93f5be6","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-08T17:50:24Z","title_canon_sha256":"0c5f75e68fac0c35bb2275b3023078e19ebbf8389181158af042cf97b290104e"},"schema_version":"1.0","source":{"id":"2411.05735","kind":"arxiv","version":2}},"canonical_sha256":"7816f82713fb15097b8323e8d579a9d5477c481449ad9df982a80fe634e4fd71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7816f82713fb15097b8323e8d579a9d5477c481449ad9df982a80fe634e4fd71","first_computed_at":"2026-07-05T10:51:28.181517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:28.181517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KL463fnOgucWiM/OrzG8usnclgOT1g+T0LI26gkS2aQ8HK3GaqQhHvenzIG5kSwtf7bHXgeDLPatDAnWJeuDCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:28.182002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05735","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba9412847e58f81d0e8b1aa5c48c46f4dcc2c4b979b883d763ab197bf8d1df1a","sha256:d3a58821688c883b5599273dab4429c7a87604522f0dee3366478d94286cbc7a"],"state_sha256":"85b19e42f555a1048b655c8efa95003b6718363baf090e7c82a3df3c0a75d602"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fSW3wopgIyIBPHg9hETTxHFFWJNHSvjc/zfLPbT49LxIw3arRvvRGEYlSivpwApcgKAYJmpuwrmsADKBkNqUBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:48:26.543187Z","bundle_sha256":"7012d43f450f50d8938de96cd437234b5307e510e1ad1e17a517a9b2077e0d11"}}