{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:K4WXMVRCOU4SA2M76NYTXREJKP","short_pith_number":"pith:K4WXMVRC","canonical_record":{"source":{"id":"2605.27967","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-05-27T05:03:24Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"a4a56f7756213a3735c130cb93b509624b781ddf2a87ad5fc48ea704bcda531c","abstract_canon_sha256":"b1027389a43d40fcc1ef2226a05e81b61e9a7e21320f8bc22ee27f521c5ed74c"},"schema_version":"1.0"},"canonical_sha256":"572d765622753920699ff3713bc48953ce8853ec8fe37c982b20a3666601d070","source":{"kind":"arxiv","id":"2605.27967","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27967","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27967v1","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27967","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"K4WXMVRCOU4S","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"K4WXMVRCOU4SA2M7","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"K4WXMVRC","created_at":"2026-05-28T01:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:K4WXMVRCOU4SA2M76NYTXREJKP","target":"record","payload":{"canonical_record":{"source":{"id":"2605.27967","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-05-27T05:03:24Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"a4a56f7756213a3735c130cb93b509624b781ddf2a87ad5fc48ea704bcda531c","abstract_canon_sha256":"b1027389a43d40fcc1ef2226a05e81b61e9a7e21320f8bc22ee27f521c5ed74c"},"schema_version":"1.0"},"canonical_sha256":"572d765622753920699ff3713bc48953ce8853ec8fe37c982b20a3666601d070","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:54.826077Z","signature_b64":"RWSVAeNh+KtftJGe6tgT3NdX3PmXh+WhkjQgbZMHuuxicy1jScdshfazXwkYRMdzSEqkK68mT4pGpBQk8Q4UBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"572d765622753920699ff3713bc48953ce8853ec8fe37c982b20a3666601d070","last_reissued_at":"2026-05-28T01:04:54.825664Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:54.825664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.27967","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":"2026-05-28T01:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P/Hg9DqUjH5dNJMChMEzIAOt2f3e1ZhE7jHozqLqGtxJ2m9mlEwSyINScgNudFGqgDYb4eZFVJ/CZPO9OsMsDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T06:42:17.735129Z"},"content_sha256":"87cba57dff526acd0bd4d183436942c2ca3ad442db4a66f04e84561a436609ca","schema_version":"1.0","event_id":"sha256:87cba57dff526acd0bd4d183436942c2ca3ad442db4a66f04e84561a436609ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:K4WXMVRCOU4SA2M76NYTXREJKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Teacher Knowledge Distillation via Teacher-Informed Mixture Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"stat.ME","authors_text":"Jiazhang Cai, Luyang Fang, Ping Ma, Wenxuan Zhong, Yongkai Chen","submitted_at":"2026-05-27T05:03:24Z","abstract_excerpt":"Knowledge distillation is a powerful method for model compression, enabling the efficient deployment of complex deep learning models (teachers), including large language models. However, its underlying statistical mechanisms remain unclear, and uncertainty evaluation is often overlooked, especially in real-world scenarios requiring diverse teacher expertise. To address these challenges, we introduce \\textit{Multi-Teacher Bayesian Knowledge Distillation} (MT-BKD), where a distilled student model learns from multiple teachers within the Bayesian framework. Our approach leverages Bayesian inferen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27967","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/2605.27967/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":"2026-05-28T01:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PegYm7+oNVU8x6A2X9LY6swGAwj2745vINOnSKu5owU2kRA3iFH+Zvs7IpdiDg2nannyeNVxeYPv1KVrAPl+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T06:42:17.735549Z"},"content_sha256":"264ef5eb016db99c55c2900c51ae619ddc0731f1b48513261af4621b72aa1eff","schema_version":"1.0","event_id":"sha256:264ef5eb016db99c55c2900c51ae619ddc0731f1b48513261af4621b72aa1eff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4WXMVRCOU4SA2M76NYTXREJKP/bundle.json","state_url":"https://pith.science/pith/K4WXMVRCOU4SA2M76NYTXREJKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4WXMVRCOU4SA2M76NYTXREJKP/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":"2026-06-12T06:42:17Z","links":{"resolver":"https://pith.science/pith/K4WXMVRCOU4SA2M76NYTXREJKP","bundle":"https://pith.science/pith/K4WXMVRCOU4SA2M76NYTXREJKP/bundle.json","state":"https://pith.science/pith/K4WXMVRCOU4SA2M76NYTXREJKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4WXMVRCOU4SA2M76NYTXREJKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:K4WXMVRCOU4SA2M76NYTXREJKP","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":"b1027389a43d40fcc1ef2226a05e81b61e9a7e21320f8bc22ee27f521c5ed74c","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-05-27T05:03:24Z","title_canon_sha256":"a4a56f7756213a3735c130cb93b509624b781ddf2a87ad5fc48ea704bcda531c"},"schema_version":"1.0","source":{"id":"2605.27967","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27967","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27967v1","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27967","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"K4WXMVRCOU4S","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"K4WXMVRCOU4SA2M7","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"K4WXMVRC","created_at":"2026-05-28T01:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:264ef5eb016db99c55c2900c51ae619ddc0731f1b48513261af4621b72aa1eff","target":"graph","created_at":"2026-05-28T01:04:54Z","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/2605.27967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge distillation is a powerful method for model compression, enabling the efficient deployment of complex deep learning models (teachers), including large language models. However, its underlying statistical mechanisms remain unclear, and uncertainty evaluation is often overlooked, especially in real-world scenarios requiring diverse teacher expertise. To address these challenges, we introduce \\textit{Multi-Teacher Bayesian Knowledge Distillation} (MT-BKD), where a distilled student model learns from multiple teachers within the Bayesian framework. Our approach leverages Bayesian inferen","authors_text":"Jiazhang Cai, Luyang Fang, Ping Ma, Wenxuan Zhong, Yongkai Chen","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-05-27T05:03:24Z","title":"Multi-Teacher Knowledge Distillation via Teacher-Informed Mixture Priors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27967","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":"sha256:87cba57dff526acd0bd4d183436942c2ca3ad442db4a66f04e84561a436609ca","target":"record","created_at":"2026-05-28T01:04:54Z","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":"b1027389a43d40fcc1ef2226a05e81b61e9a7e21320f8bc22ee27f521c5ed74c","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-05-27T05:03:24Z","title_canon_sha256":"a4a56f7756213a3735c130cb93b509624b781ddf2a87ad5fc48ea704bcda531c"},"schema_version":"1.0","source":{"id":"2605.27967","kind":"arxiv","version":1}},"canonical_sha256":"572d765622753920699ff3713bc48953ce8853ec8fe37c982b20a3666601d070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"572d765622753920699ff3713bc48953ce8853ec8fe37c982b20a3666601d070","first_computed_at":"2026-05-28T01:04:54.825664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:54.825664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RWSVAeNh+KtftJGe6tgT3NdX3PmXh+WhkjQgbZMHuuxicy1jScdshfazXwkYRMdzSEqkK68mT4pGpBQk8Q4UBw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:54.826077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27967","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87cba57dff526acd0bd4d183436942c2ca3ad442db4a66f04e84561a436609ca","sha256:264ef5eb016db99c55c2900c51ae619ddc0731f1b48513261af4621b72aa1eff"],"state_sha256":"5f3f3c23a3c12f5cd5170a2fdce9351d37a907e0fd93bc4d5e7487c3529a16de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXwEZTKIQHQ7KMO1lDOQMZfm3gkLjcjbxtmR4g50a2qG3JgLUu+tp7VwcfVYrQEu9STa6LJRGjOcj8LfJXZ+BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T06:42:17.737867Z","bundle_sha256":"11b45fd087e80b3b7def6444ea5debd5f79b5c6bb97cb3bb058cbd9999234d22"}}