{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:66MAX7UCOADDI55SGR34MQRY4Y","short_pith_number":"pith:66MAX7UC","canonical_record":{"source":{"id":"2603.07079","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-07T07:26:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bea500c72439d5997bfeefa2e7fd622a291f63b95b313bd066f2cb989c47dca3","abstract_canon_sha256":"e5d920a4e7581dc8284f5fee8fc6b9ed7635296d959262634cd1250d0df490b7"},"schema_version":"1.0"},"canonical_sha256":"f7980bfe8270063477b23477c64238e6313e3fd975fafb9a7ea2091792815ac3","source":{"kind":"arxiv","id":"2603.07079","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.07079","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"arxiv_version","alias_value":"2603.07079v2","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07079","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"pith_short_12","alias_value":"66MAX7UCOADD","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"pith_short_16","alias_value":"66MAX7UCOADDI55S","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"pith_short_8","alias_value":"66MAX7UC","created_at":"2026-05-25T02:02:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:66MAX7UCOADDI55SGR34MQRY4Y","target":"record","payload":{"canonical_record":{"source":{"id":"2603.07079","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-07T07:26:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bea500c72439d5997bfeefa2e7fd622a291f63b95b313bd066f2cb989c47dca3","abstract_canon_sha256":"e5d920a4e7581dc8284f5fee8fc6b9ed7635296d959262634cd1250d0df490b7"},"schema_version":"1.0"},"canonical_sha256":"f7980bfe8270063477b23477c64238e6313e3fd975fafb9a7ea2091792815ac3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:14.034893Z","signature_b64":"UUfL25837omQVc8w/43ykNHzQKRJGYQ+A0uZC8NQqs1P1/KsdHkCIYjfFOxJHPgZEk3jTUjGLyp9wNNnmwhIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7980bfe8270063477b23477c64238e6313e3fd975fafb9a7ea2091792815ac3","last_reissued_at":"2026-05-25T02:02:14.033926Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:14.033926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.07079","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":"2026-05-25T02:02:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CCIShZicWgcD+cM1Z1fIfAp1Bnr998E4G+1aOBtvWOY3xZhp8KxqCFcyRpdK4rWwLnHkbxWuJJ3bPv07pOnFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:32:09.157335Z"},"content_sha256":"6aac23da29532cb9f1c84af311b5aa987a147bfd9743a7d7cb7bca6c345c5b3d","schema_version":"1.0","event_id":"sha256:6aac23da29532cb9f1c84af311b5aa987a147bfd9743a7d7cb7bca6c345c5b3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:66MAX7UCOADDI55SGR34MQRY4Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Entropy-Aware On-Policy Distillation of Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Dennis Wei, Kimin Lee, Nathalie Baracaldo, Swanand Ravindra Kadhe, Taywon Min, Woogyeol Jin, Yi Zhou, Yongjin Yang","submitted_at":"2026-03-07T07:26:18Z","abstract_excerpt":"On-policy distillation is a promising approach for transferring knowledge between language models, where a student learns from dense token-level signals along its own trajectories. This framework typically uses reverse KL divergence, encouraging the student to match the teacher's high-confidence predictions. However, we show that the mode-seeking property of reverse KL reduces generation diversity and yields unstable learning signals when the teacher distribution has high entropy. To address this, we introduce Entropy-Aware On-Policy Distillation. Our key idea is augmenting the standard revers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.07079","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/2603.07079/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":"2026-05-25T02:02:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L81kdH8/4eCEvxynurE0UbycMuDA9NldPunqFbDBC2tmk5mbESyO+62t5yCe85EZi5HB9cSHIxhacFQWMIc4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:32:09.157822Z"},"content_sha256":"e7ff871148a821635bc3a02d0a1140bf995d7509d1b1e9c0a6638fa6c3f71e93","schema_version":"1.0","event_id":"sha256:e7ff871148a821635bc3a02d0a1140bf995d7509d1b1e9c0a6638fa6c3f71e93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/66MAX7UCOADDI55SGR34MQRY4Y/bundle.json","state_url":"https://pith.science/pith/66MAX7UCOADDI55SGR34MQRY4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/66MAX7UCOADDI55SGR34MQRY4Y/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":"2026-05-25T23:32:09Z","links":{"resolver":"https://pith.science/pith/66MAX7UCOADDI55SGR34MQRY4Y","bundle":"https://pith.science/pith/66MAX7UCOADDI55SGR34MQRY4Y/bundle.json","state":"https://pith.science/pith/66MAX7UCOADDI55SGR34MQRY4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/66MAX7UCOADDI55SGR34MQRY4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:66MAX7UCOADDI55SGR34MQRY4Y","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":"e5d920a4e7581dc8284f5fee8fc6b9ed7635296d959262634cd1250d0df490b7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-07T07:26:18Z","title_canon_sha256":"bea500c72439d5997bfeefa2e7fd622a291f63b95b313bd066f2cb989c47dca3"},"schema_version":"1.0","source":{"id":"2603.07079","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.07079","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"arxiv_version","alias_value":"2603.07079v2","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07079","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"pith_short_12","alias_value":"66MAX7UCOADD","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"pith_short_16","alias_value":"66MAX7UCOADDI55S","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"pith_short_8","alias_value":"66MAX7UC","created_at":"2026-05-25T02:02:14Z"}],"graph_snapshots":[{"event_id":"sha256:e7ff871148a821635bc3a02d0a1140bf995d7509d1b1e9c0a6638fa6c3f71e93","target":"graph","created_at":"2026-05-25T02:02:14Z","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/2603.07079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation is a promising approach for transferring knowledge between language models, where a student learns from dense token-level signals along its own trajectories. This framework typically uses reverse KL divergence, encouraging the student to match the teacher's high-confidence predictions. However, we show that the mode-seeking property of reverse KL reduces generation diversity and yields unstable learning signals when the teacher distribution has high entropy. To address this, we introduce Entropy-Aware On-Policy Distillation. Our key idea is augmenting the standard revers","authors_text":"Dennis Wei, Kimin Lee, Nathalie Baracaldo, Swanand Ravindra Kadhe, Taywon Min, Woogyeol Jin, Yi Zhou, Yongjin Yang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-07T07:26:18Z","title":"Entropy-Aware On-Policy Distillation of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.07079","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":"sha256:6aac23da29532cb9f1c84af311b5aa987a147bfd9743a7d7cb7bca6c345c5b3d","target":"record","created_at":"2026-05-25T02:02:14Z","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":"e5d920a4e7581dc8284f5fee8fc6b9ed7635296d959262634cd1250d0df490b7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-07T07:26:18Z","title_canon_sha256":"bea500c72439d5997bfeefa2e7fd622a291f63b95b313bd066f2cb989c47dca3"},"schema_version":"1.0","source":{"id":"2603.07079","kind":"arxiv","version":2}},"canonical_sha256":"f7980bfe8270063477b23477c64238e6313e3fd975fafb9a7ea2091792815ac3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7980bfe8270063477b23477c64238e6313e3fd975fafb9a7ea2091792815ac3","first_computed_at":"2026-05-25T02:02:14.033926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:14.033926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UUfL25837omQVc8w/43ykNHzQKRJGYQ+A0uZC8NQqs1P1/KsdHkCIYjfFOxJHPgZEk3jTUjGLyp9wNNnmwhIBQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:14.034893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.07079","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6aac23da29532cb9f1c84af311b5aa987a147bfd9743a7d7cb7bca6c345c5b3d","sha256:e7ff871148a821635bc3a02d0a1140bf995d7509d1b1e9c0a6638fa6c3f71e93"],"state_sha256":"51f184323dfc0e96b1325d0d6a1fd0aa08f14eb27589671efccc19d7ee860c10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NuSxd0ZxwBDQxusQBaPiOM+XD90nl+H9GoIFk+OXG/H/FFzGwVDMnOUuEU8VyCmBDZPPSZrPteeEx7TBQCkoAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:32:09.161390Z","bundle_sha256":"6a06db60d0357844d72a738dbe7b9e5fc4df3fff55ccd379ca1d2874d08b82bc"}}