{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:PBTFPQSF47NOYW6OT47G323P3X","short_pith_number":"pith:PBTFPQSF","canonical_record":{"source":{"id":"1603.05800","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-18T09:16:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ddeebaa39328ba2f330425109ac2f25eae8db6876641b0848ac46f2b7584f842","abstract_canon_sha256":"298514d9f39d070de18f05086a48f689a34fb06e78363aeb811719d7b2961b8f"},"schema_version":"1.0"},"canonical_sha256":"786657c245e7daec5bce9f3e6deb6fddc4f40d5b5fcef0cd5da383154a3d8ffe","source":{"kind":"arxiv","id":"1603.05800","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.05800","created_at":"2026-05-18T01:18:53Z"},{"alias_kind":"arxiv_version","alias_value":"1603.05800v1","created_at":"2026-05-18T01:18:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.05800","created_at":"2026-05-18T01:18:53Z"},{"alias_kind":"pith_short_12","alias_value":"PBTFPQSF47NO","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PBTFPQSF47NOYW6O","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PBTFPQSF","created_at":"2026-05-18T12:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:PBTFPQSF47NOYW6OT47G323P3X","target":"record","payload":{"canonical_record":{"source":{"id":"1603.05800","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-18T09:16:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ddeebaa39328ba2f330425109ac2f25eae8db6876641b0848ac46f2b7584f842","abstract_canon_sha256":"298514d9f39d070de18f05086a48f689a34fb06e78363aeb811719d7b2961b8f"},"schema_version":"1.0"},"canonical_sha256":"786657c245e7daec5bce9f3e6deb6fddc4f40d5b5fcef0cd5da383154a3d8ffe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:18:53.496002Z","signature_b64":"EqBmtwfVnOHOhhXixDNJ6ibHsM9tymH08GqdSm7ArFQ6zxlL43+hMkBQ/JfuIsCHtru6WBFbfcHzaMM0v6ecCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"786657c245e7daec5bce9f3e6deb6fddc4f40d5b5fcef0cd5da383154a3d8ffe","last_reissued_at":"2026-05-18T01:18:53.495201Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:18:53.495201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.05800","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":"2026-05-18T01:18:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wpT7TAmH3eJJVXwcH9KW+Qp/mKplrajnXDb8tKWhf39mFQmybQpntpK0QR+c8E7vvhaqC8Xz9JzZKOEWA6LnAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:39:52.081379Z"},"content_sha256":"ae1d40a8b0f372266d3845b9ef8643125bea439992cc26d0646b2af46792e4f6","schema_version":"1.0","event_id":"sha256:ae1d40a8b0f372266d3845b9ef8643125bea439992cc26d0646b2af46792e4f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:PBTFPQSF47NOYW6OT47G323P3X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparison between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alireza Bagheri Garakani, Aurelien Bellet, Avner May, Brian Kingsbury, Dong Guo, Fei Sha, Kuan Liu, Linxi Fan, Michael Collins, Michael Picheny, Zhiyun Lu","submitted_at":"2016-03-18T09:16:01Z","abstract_excerpt":"We study large-scale kernel methods for acoustic modeling and compare to DNNs on performance metrics related to both acoustic modeling and recognition. Measuring perplexity and frame-level classification accuracy, kernel-based acoustic models are as effective as their DNN counterparts. However, on token-error-rates DNN models can be significantly better. We have discovered that this might be attributed to DNN's unique strength in reducing both the perplexity and the entropy of the predicted posterior probabilities. Motivated by our findings, we propose a new technique, entropy regularized perp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.05800","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":""},"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":"2026-05-18T01:18:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nJxSvjvIju8S4GqSA4JginlP87mHWlMuYQv3g0Bv0cSev7fas+wVMVWGA3lpItofwhJj14qiHVzvIvYJo0nnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:39:52.082134Z"},"content_sha256":"2beabbdb1b474c158cfd4df60bb2561a630c8a74532414edb6d869971021265b","schema_version":"1.0","event_id":"sha256:2beabbdb1b474c158cfd4df60bb2561a630c8a74532414edb6d869971021265b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PBTFPQSF47NOYW6OT47G323P3X/bundle.json","state_url":"https://pith.science/pith/PBTFPQSF47NOYW6OT47G323P3X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PBTFPQSF47NOYW6OT47G323P3X/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":"2026-05-30T19:39:52Z","links":{"resolver":"https://pith.science/pith/PBTFPQSF47NOYW6OT47G323P3X","bundle":"https://pith.science/pith/PBTFPQSF47NOYW6OT47G323P3X/bundle.json","state":"https://pith.science/pith/PBTFPQSF47NOYW6OT47G323P3X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PBTFPQSF47NOYW6OT47G323P3X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:PBTFPQSF47NOYW6OT47G323P3X","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":"298514d9f39d070de18f05086a48f689a34fb06e78363aeb811719d7b2961b8f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-18T09:16:01Z","title_canon_sha256":"ddeebaa39328ba2f330425109ac2f25eae8db6876641b0848ac46f2b7584f842"},"schema_version":"1.0","source":{"id":"1603.05800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.05800","created_at":"2026-05-18T01:18:53Z"},{"alias_kind":"arxiv_version","alias_value":"1603.05800v1","created_at":"2026-05-18T01:18:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.05800","created_at":"2026-05-18T01:18:53Z"},{"alias_kind":"pith_short_12","alias_value":"PBTFPQSF47NO","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PBTFPQSF47NOYW6O","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PBTFPQSF","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:2beabbdb1b474c158cfd4df60bb2561a630c8a74532414edb6d869971021265b","target":"graph","created_at":"2026-05-18T01:18:53Z","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"},"paper":{"abstract_excerpt":"We study large-scale kernel methods for acoustic modeling and compare to DNNs on performance metrics related to both acoustic modeling and recognition. Measuring perplexity and frame-level classification accuracy, kernel-based acoustic models are as effective as their DNN counterparts. However, on token-error-rates DNN models can be significantly better. We have discovered that this might be attributed to DNN's unique strength in reducing both the perplexity and the entropy of the predicted posterior probabilities. Motivated by our findings, we propose a new technique, entropy regularized perp","authors_text":"Alireza Bagheri Garakani, Aurelien Bellet, Avner May, Brian Kingsbury, Dong Guo, Fei Sha, Kuan Liu, Linxi Fan, Michael Collins, Michael Picheny, Zhiyun Lu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-18T09:16:01Z","title":"A Comparison between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.05800","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:ae1d40a8b0f372266d3845b9ef8643125bea439992cc26d0646b2af46792e4f6","target":"record","created_at":"2026-05-18T01:18:53Z","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":"298514d9f39d070de18f05086a48f689a34fb06e78363aeb811719d7b2961b8f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-18T09:16:01Z","title_canon_sha256":"ddeebaa39328ba2f330425109ac2f25eae8db6876641b0848ac46f2b7584f842"},"schema_version":"1.0","source":{"id":"1603.05800","kind":"arxiv","version":1}},"canonical_sha256":"786657c245e7daec5bce9f3e6deb6fddc4f40d5b5fcef0cd5da383154a3d8ffe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"786657c245e7daec5bce9f3e6deb6fddc4f40d5b5fcef0cd5da383154a3d8ffe","first_computed_at":"2026-05-18T01:18:53.495201Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:18:53.495201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EqBmtwfVnOHOhhXixDNJ6ibHsM9tymH08GqdSm7ArFQ6zxlL43+hMkBQ/JfuIsCHtru6WBFbfcHzaMM0v6ecCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:18:53.496002Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.05800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae1d40a8b0f372266d3845b9ef8643125bea439992cc26d0646b2af46792e4f6","sha256:2beabbdb1b474c158cfd4df60bb2561a630c8a74532414edb6d869971021265b"],"state_sha256":"3c98c23bf165b9fe508e28b447a3f5bad9f2fa300c5d91ede878e11ae018d83c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXYZxmPQBv8Ym8L1GWSWbqnLiA3GD+JNjIA32sMNV3WH/wUEhKeUuSPatpbvsfaPJgK6Os9PdIq/sYHKplFAAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T19:39:52.086922Z","bundle_sha256":"9eaeeafa33ee2a8d01305ca4a1ba5ad3022720c4017a99e475c4147a6e288f5d"}}