{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QT6I6LTYWUCQVENB2LMCH7EWXK","short_pith_number":"pith:QT6I6LTY","canonical_record":{"source":{"id":"2505.24844","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T17:43:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"42e35a66000bcbdf69ba412d684c99a78b54b13d029fe657b28d48134c4246d6","abstract_canon_sha256":"9cf8aee37df4cf96cfb8a6c23a41a1dc012d1c4b5f3b5a8d657ea96ece4f5281"},"schema_version":"1.0"},"canonical_sha256":"84fc8f2e78b5050a91a1d2d823fc96baa07d7d7d8ea2dd9c5c7f4685893e41e5","source":{"kind":"arxiv","id":"2505.24844","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24844","created_at":"2026-07-05T11:12:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24844v1","created_at":"2026-07-05T11:12:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24844","created_at":"2026-07-05T11:12:57Z"},{"alias_kind":"pith_short_12","alias_value":"QT6I6LTYWUCQ","created_at":"2026-07-05T11:12:57Z"},{"alias_kind":"pith_short_16","alias_value":"QT6I6LTYWUCQVENB","created_at":"2026-07-05T11:12:57Z"},{"alias_kind":"pith_short_8","alias_value":"QT6I6LTY","created_at":"2026-07-05T11:12:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QT6I6LTYWUCQVENB2LMCH7EWXK","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24844","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T17:43:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"42e35a66000bcbdf69ba412d684c99a78b54b13d029fe657b28d48134c4246d6","abstract_canon_sha256":"9cf8aee37df4cf96cfb8a6c23a41a1dc012d1c4b5f3b5a8d657ea96ece4f5281"},"schema_version":"1.0"},"canonical_sha256":"84fc8f2e78b5050a91a1d2d823fc96baa07d7d7d8ea2dd9c5c7f4685893e41e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:57.737344Z","signature_b64":"IlUBeS5OjaCUIFn/aaJIfHGnKF2USSiopwImqofIG5g+ZcOFl/qr9qYDrhG/ff+wLyOkmJfauspLGqkGIcNeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84fc8f2e78b5050a91a1d2d823fc96baa07d7d7d8ea2dd9c5c7f4685893e41e5","last_reissued_at":"2026-07-05T11:12:57.736770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:57.736770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24844","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":"2026-07-05T11:12:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yziqUq1GUsL1E+/qJIXu3Wr4FBTW/lwxoA3QOCgb2qEFf+KyTI6/zRdlbLKzKfBJwko3KfdVBIP+VmBFM7nxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:10:15.731832Z"},"content_sha256":"60ad657f4e5336137addd7a8e20c398e06aef9af8fa19e16501c621e0eebbe90","schema_version":"1.0","event_id":"sha256:60ad657f4e5336137addd7a8e20c398e06aef9af8fa19e16501c621e0eebbe90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QT6I6LTYWUCQVENB2LMCH7EWXK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Francesco Tonin, Volkan Cevher, Wanyun Xie","submitted_at":"2025-05-30T17:43:10Z","abstract_excerpt":"Training data mixtures greatly impact the generalization performance of large language models. Existing domain reweighting methods often rely on costly weight computations and require retraining when new data is introduced. To this end, we introduce a flexible and efficient data mixing framework, Chameleon, that employs leverage scores to quantify domain importance within a learned embedding space. We first construct a domain affinity matrix over domain embeddings. The induced leverage scores determine a mixture that upweights domains sharing common representations in embedding space. This for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24844","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/2505.24844/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":"2026-07-05T11:12:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gBPSBnfGCjcZ/dTUechaNVQUKY+jSzQ65q3L9g9T6sEgpb6oaLPT1AmgtZv/B6ypj9C9Ul7z7xkDUKdYeKRsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:10:15.732339Z"},"content_sha256":"630af33b8cfa24ba2880e1e3a2095488188829bb8b032706701b9638e7e19ad5","schema_version":"1.0","event_id":"sha256:630af33b8cfa24ba2880e1e3a2095488188829bb8b032706701b9638e7e19ad5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QT6I6LTYWUCQVENB2LMCH7EWXK/bundle.json","state_url":"https://pith.science/pith/QT6I6LTYWUCQVENB2LMCH7EWXK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QT6I6LTYWUCQVENB2LMCH7EWXK/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":"2026-08-08T03:10:15Z","links":{"resolver":"https://pith.science/pith/QT6I6LTYWUCQVENB2LMCH7EWXK","bundle":"https://pith.science/pith/QT6I6LTYWUCQVENB2LMCH7EWXK/bundle.json","state":"https://pith.science/pith/QT6I6LTYWUCQVENB2LMCH7EWXK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QT6I6LTYWUCQVENB2LMCH7EWXK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QT6I6LTYWUCQVENB2LMCH7EWXK","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":"9cf8aee37df4cf96cfb8a6c23a41a1dc012d1c4b5f3b5a8d657ea96ece4f5281","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T17:43:10Z","title_canon_sha256":"42e35a66000bcbdf69ba412d684c99a78b54b13d029fe657b28d48134c4246d6"},"schema_version":"1.0","source":{"id":"2505.24844","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24844","created_at":"2026-07-05T11:12:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24844v1","created_at":"2026-07-05T11:12:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24844","created_at":"2026-07-05T11:12:57Z"},{"alias_kind":"pith_short_12","alias_value":"QT6I6LTYWUCQ","created_at":"2026-07-05T11:12:57Z"},{"alias_kind":"pith_short_16","alias_value":"QT6I6LTYWUCQVENB","created_at":"2026-07-05T11:12:57Z"},{"alias_kind":"pith_short_8","alias_value":"QT6I6LTY","created_at":"2026-07-05T11:12:57Z"}],"graph_snapshots":[{"event_id":"sha256:630af33b8cfa24ba2880e1e3a2095488188829bb8b032706701b9638e7e19ad5","target":"graph","created_at":"2026-07-05T11:12:57Z","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/2505.24844/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training data mixtures greatly impact the generalization performance of large language models. Existing domain reweighting methods often rely on costly weight computations and require retraining when new data is introduced. To this end, we introduce a flexible and efficient data mixing framework, Chameleon, that employs leverage scores to quantify domain importance within a learned embedding space. We first construct a domain affinity matrix over domain embeddings. The induced leverage scores determine a mixture that upweights domains sharing common representations in embedding space. This for","authors_text":"Francesco Tonin, Volkan Cevher, Wanyun Xie","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T17:43:10Z","title":"Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24844","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":"sha256:60ad657f4e5336137addd7a8e20c398e06aef9af8fa19e16501c621e0eebbe90","target":"record","created_at":"2026-07-05T11:12:57Z","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":"9cf8aee37df4cf96cfb8a6c23a41a1dc012d1c4b5f3b5a8d657ea96ece4f5281","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T17:43:10Z","title_canon_sha256":"42e35a66000bcbdf69ba412d684c99a78b54b13d029fe657b28d48134c4246d6"},"schema_version":"1.0","source":{"id":"2505.24844","kind":"arxiv","version":1}},"canonical_sha256":"84fc8f2e78b5050a91a1d2d823fc96baa07d7d7d8ea2dd9c5c7f4685893e41e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84fc8f2e78b5050a91a1d2d823fc96baa07d7d7d8ea2dd9c5c7f4685893e41e5","first_computed_at":"2026-07-05T11:12:57.736770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:57.736770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IlUBeS5OjaCUIFn/aaJIfHGnKF2USSiopwImqofIG5g+ZcOFl/qr9qYDrhG/ff+wLyOkmJfauspLGqkGIcNeBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:57.737344Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24844","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60ad657f4e5336137addd7a8e20c398e06aef9af8fa19e16501c621e0eebbe90","sha256:630af33b8cfa24ba2880e1e3a2095488188829bb8b032706701b9638e7e19ad5"],"state_sha256":"0312116e26d97ea5802c5e5a9eee4099d1d6ec66d23604f9fb31e3db31117360"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y1mC+E+ffQe/WmSX7xcFb5s0YkzofsExtR2ExW3PVp29V6+qKORPNe7fSWvhHniSC8TLxuS+2x+swGytVSvsCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:10:15.735732Z","bundle_sha256":"4463e80d62ddb88fbd297d4ed0affe9fe7baeadd4f77a8a020a4dcfebaafabdd"}}