{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AXJ3PHEMXNOADFE6BFSL5K3OFC","short_pith_number":"pith:AXJ3PHEM","canonical_record":{"source":{"id":"2606.04401","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T03:28:46Z","cross_cats_sorted":[],"title_canon_sha256":"cfc6bc72f96f87add87210c49e44a0e8114b4e8cc69eaaab4148bc6a04de71c2","abstract_canon_sha256":"8d4444eec9abf9fd941ff5e3a431e6d6de3761827ae9a1d50648d7d079154e26"},"schema_version":"1.0"},"canonical_sha256":"05d3b79c8cbb5c01949e0964beab6e28abb2386bd3b966f9379d4d77c61650b6","source":{"kind":"arxiv","id":"2606.04401","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04401","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04401v1","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04401","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"AXJ3PHEMXNOA","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"AXJ3PHEMXNOADFE6","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"AXJ3PHEM","created_at":"2026-06-04T01:09:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AXJ3PHEMXNOADFE6BFSL5K3OFC","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04401","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T03:28:46Z","cross_cats_sorted":[],"title_canon_sha256":"cfc6bc72f96f87add87210c49e44a0e8114b4e8cc69eaaab4148bc6a04de71c2","abstract_canon_sha256":"8d4444eec9abf9fd941ff5e3a431e6d6de3761827ae9a1d50648d7d079154e26"},"schema_version":"1.0"},"canonical_sha256":"05d3b79c8cbb5c01949e0964beab6e28abb2386bd3b966f9379d4d77c61650b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:06.727020Z","signature_b64":"f8bq+D2xKn9/0KL1ZGMiX1hEj8exNpbK5VJMe6ny6dxtj/f0PM0IFzDT14HUczKHjl0bjhiB+ezxy9RPZWW8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05d3b79c8cbb5c01949e0964beab6e28abb2386bd3b966f9379d4d77c61650b6","last_reissued_at":"2026-06-04T01:09:06.726458Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:06.726458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04401","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":"2026-06-04T01:09:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IeHg/zSnaBSoaXt4zeS8v9KDWsw01YduCBaipzmSJAHvAjKj1zGuHkzUzenm9Rm1tEw18JGg49H0RvJucHMFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:07:24.781128Z"},"content_sha256":"24430d5990e9dc247de9e37da84356f18523e36b8dd84b0af915d30dc904f0a0","schema_version":"1.0","event_id":"sha256:24430d5990e9dc247de9e37da84356f18523e36b8dd84b0af915d30dc904f0a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AXJ3PHEMXNOADFE6BFSL5K3OFC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TANDEM: Bi-Level Data Mixture Optimization with Twin Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Deping Xiang, Guoqiang Gong, Haoran Li, Jiaxing Wang, Jin Xu, Ju Fan, Ke Zhang, Mingyang Yi, Pengzhang Liu, Qixiang Jiang, Zhen Chen, Zicheng Zhang","submitted_at":"2026-06-03T03:28:46Z","abstract_excerpt":"The capabilities of large language models (LLMs) significantly depend on training data drawn from various domains. Optimizing domain-specific mixture ratios can be modeled as a bi-level optimization problem, which we simplify into a single-level penalized form and solve with twin networks: a proxy model trained on primary data and a dynamically updated reference model trained with additional data. Our proposed method, Twin Networks for bi-level DatA mixturE optiMization (TANDEM), measures the data efficacy through the difference between the twin models and up-weights domains that benefit more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04401","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/2606.04401/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":"2026-06-04T01:09:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JUr0tZD9uyb1JuR8v8KGvVy+oRYdBWOtOojL2MvQ4Ky+aXJzBASuzKitUxBR2rpI5aeJ4cVXJrCwcsHVDR8kCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:07:24.781794Z"},"content_sha256":"f84d1aadd88652f65dfe5d9171a1bb9d097e0881fff23de281cf6e552455c4db","schema_version":"1.0","event_id":"sha256:f84d1aadd88652f65dfe5d9171a1bb9d097e0881fff23de281cf6e552455c4db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AXJ3PHEMXNOADFE6BFSL5K3OFC/bundle.json","state_url":"https://pith.science/pith/AXJ3PHEMXNOADFE6BFSL5K3OFC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AXJ3PHEMXNOADFE6BFSL5K3OFC/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":"2026-06-07T16:07:24Z","links":{"resolver":"https://pith.science/pith/AXJ3PHEMXNOADFE6BFSL5K3OFC","bundle":"https://pith.science/pith/AXJ3PHEMXNOADFE6BFSL5K3OFC/bundle.json","state":"https://pith.science/pith/AXJ3PHEMXNOADFE6BFSL5K3OFC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AXJ3PHEMXNOADFE6BFSL5K3OFC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AXJ3PHEMXNOADFE6BFSL5K3OFC","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":"8d4444eec9abf9fd941ff5e3a431e6d6de3761827ae9a1d50648d7d079154e26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T03:28:46Z","title_canon_sha256":"cfc6bc72f96f87add87210c49e44a0e8114b4e8cc69eaaab4148bc6a04de71c2"},"schema_version":"1.0","source":{"id":"2606.04401","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04401","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04401v1","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04401","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"AXJ3PHEMXNOA","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"AXJ3PHEMXNOADFE6","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"AXJ3PHEM","created_at":"2026-06-04T01:09:06Z"}],"graph_snapshots":[{"event_id":"sha256:f84d1aadd88652f65dfe5d9171a1bb9d097e0881fff23de281cf6e552455c4db","target":"graph","created_at":"2026-06-04T01:09:06Z","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/2606.04401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The capabilities of large language models (LLMs) significantly depend on training data drawn from various domains. Optimizing domain-specific mixture ratios can be modeled as a bi-level optimization problem, which we simplify into a single-level penalized form and solve with twin networks: a proxy model trained on primary data and a dynamically updated reference model trained with additional data. Our proposed method, Twin Networks for bi-level DatA mixturE optiMization (TANDEM), measures the data efficacy through the difference between the twin models and up-weights domains that benefit more ","authors_text":"Deping Xiang, Guoqiang Gong, Haoran Li, Jiaxing Wang, Jin Xu, Ju Fan, Ke Zhang, Mingyang Yi, Pengzhang Liu, Qixiang Jiang, Zhen Chen, Zicheng Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T03:28:46Z","title":"TANDEM: Bi-Level Data Mixture Optimization with Twin Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04401","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":"sha256:24430d5990e9dc247de9e37da84356f18523e36b8dd84b0af915d30dc904f0a0","target":"record","created_at":"2026-06-04T01:09:06Z","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":"8d4444eec9abf9fd941ff5e3a431e6d6de3761827ae9a1d50648d7d079154e26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T03:28:46Z","title_canon_sha256":"cfc6bc72f96f87add87210c49e44a0e8114b4e8cc69eaaab4148bc6a04de71c2"},"schema_version":"1.0","source":{"id":"2606.04401","kind":"arxiv","version":1}},"canonical_sha256":"05d3b79c8cbb5c01949e0964beab6e28abb2386bd3b966f9379d4d77c61650b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05d3b79c8cbb5c01949e0964beab6e28abb2386bd3b966f9379d4d77c61650b6","first_computed_at":"2026-06-04T01:09:06.726458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:06.726458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f8bq+D2xKn9/0KL1ZGMiX1hEj8exNpbK5VJMe6ny6dxtj/f0PM0IFzDT14HUczKHjl0bjhiB+ezxy9RPZWW8Cg==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:06.727020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04401","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24430d5990e9dc247de9e37da84356f18523e36b8dd84b0af915d30dc904f0a0","sha256:f84d1aadd88652f65dfe5d9171a1bb9d097e0881fff23de281cf6e552455c4db"],"state_sha256":"d9d9e07b5442e5f453d115832d96b243c2ac101398ccb5eb84ad94969b23033f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nwxsUg3b1vlL2BdKnmfGrlUPyLqq+TIPvsqPnYZvUHI0SI3uqRzYLjT8ol6YrJix8XDeYNhD4Ax0Y+kKYuGICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T16:07:24.785534Z","bundle_sha256":"c4c123bbd9ab9fad6641c66e5ff6ebe80e639bc6e41b62074b0d0d0316ee0354"}}