{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:35Y6VFK55I45NGXBLUMNEWIJPG","short_pith_number":"pith:35Y6VFK5","canonical_record":{"source":{"id":"1802.06412","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-18T17:54:19Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"8d4a153f6cbc0d55b3ab152a7642bb5f69de91d0fc5da036914a4047626d9636","abstract_canon_sha256":"e43a205a903ebb55a0c0a40101f5e71c42ebdaadab2dd7a8d938de7dd2fab7e0"},"schema_version":"1.0"},"canonical_sha256":"df71ea955dea39d69ae15d18d25909798563baa6d569c204551264d8437a709d","source":{"kind":"arxiv","id":"1802.06412","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06412","created_at":"2026-05-18T00:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06412v2","created_at":"2026-05-18T00:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06412","created_at":"2026-05-18T00:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"35Y6VFK55I45","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"35Y6VFK55I45NGXB","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"35Y6VFK5","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:35Y6VFK55I45NGXBLUMNEWIJPG","target":"record","payload":{"canonical_record":{"source":{"id":"1802.06412","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-18T17:54:19Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"8d4a153f6cbc0d55b3ab152a7642bb5f69de91d0fc5da036914a4047626d9636","abstract_canon_sha256":"e43a205a903ebb55a0c0a40101f5e71c42ebdaadab2dd7a8d938de7dd2fab7e0"},"schema_version":"1.0"},"canonical_sha256":"df71ea955dea39d69ae15d18d25909798563baa6d569c204551264d8437a709d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:54.379188Z","signature_b64":"TdJY0I7sRUQFcT0pE8UO+eERSCcQHUzHCWzjeParn/d3zrvdHeRzl2dvzZYx77ii6bq9ZiO/5ckG1l7WHl2cCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df71ea955dea39d69ae15d18d25909798563baa6d569c204551264d8437a709d","last_reissued_at":"2026-05-18T00:22:54.378793Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:54.378793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.06412","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":"2026-05-18T00:22:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fqyq6uP+bHsBGSkCwlYXg8SXqyr4osZmnyP7hIHHluGNYFdowTIwi/ADIwaBZbQLVbHWYuPpliQ78u6UtOstAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T13:44:07.349658Z"},"content_sha256":"0c980c832f3a569f73ea67678e456a3b05228fbc67a4c2a94c1b2b7d341f83e7","schema_version":"1.0","event_id":"sha256:0c980c832f3a569f73ea67678e456a3b05228fbc67a4c2a94c1b2b7d341f83e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:35Y6VFK55I45NGXBLUMNEWIJPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved TDNNs using Deep Kernels and Frequency Dependent Grid-RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Florian Kreyssig, Philip Woodland","submitted_at":"2018-02-18T17:54:19Z","abstract_excerpt":"Time delay neural networks (TDNNs) are an effective acoustic model for large vocabulary speech recognition. The strength of the model can be attributed to its ability to effectively model long temporal contexts. However, current TDNN models are relatively shallow, which limits the modelling capability. This paper proposes a method of increasing the network depth by deepening the kernel used in the TDNN temporal convolutions. The best performing kernel consists of three fully connected layers with a residual (ResNet) connection from the output of the first to the output of the third. The additi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06412","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":""},"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":"2026-05-18T00:22:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+JItgtZBK/Tl6hWRCduOziwA+kGLopZtcR1aelogR8vgc6L2lmbZJnU7fLRiY7gfoOdj78SPPmLrLl1DS74sAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T13:44:07.350010Z"},"content_sha256":"49d929f7c2e20644ee3c629e132a44f3d163c994df0b3e94c709e292b86f32f7","schema_version":"1.0","event_id":"sha256:49d929f7c2e20644ee3c629e132a44f3d163c994df0b3e94c709e292b86f32f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/35Y6VFK55I45NGXBLUMNEWIJPG/bundle.json","state_url":"https://pith.science/pith/35Y6VFK55I45NGXBLUMNEWIJPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/35Y6VFK55I45NGXBLUMNEWIJPG/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":"2026-06-02T13:44:07Z","links":{"resolver":"https://pith.science/pith/35Y6VFK55I45NGXBLUMNEWIJPG","bundle":"https://pith.science/pith/35Y6VFK55I45NGXBLUMNEWIJPG/bundle.json","state":"https://pith.science/pith/35Y6VFK55I45NGXBLUMNEWIJPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/35Y6VFK55I45NGXBLUMNEWIJPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:35Y6VFK55I45NGXBLUMNEWIJPG","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":"e43a205a903ebb55a0c0a40101f5e71c42ebdaadab2dd7a8d938de7dd2fab7e0","cross_cats_sorted":["cs.AI","cs.SD","eess.AS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-18T17:54:19Z","title_canon_sha256":"8d4a153f6cbc0d55b3ab152a7642bb5f69de91d0fc5da036914a4047626d9636"},"schema_version":"1.0","source":{"id":"1802.06412","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06412","created_at":"2026-05-18T00:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06412v2","created_at":"2026-05-18T00:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06412","created_at":"2026-05-18T00:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"35Y6VFK55I45","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"35Y6VFK55I45NGXB","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"35Y6VFK5","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:49d929f7c2e20644ee3c629e132a44f3d163c994df0b3e94c709e292b86f32f7","target":"graph","created_at":"2026-05-18T00:22:54Z","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"},"paper":{"abstract_excerpt":"Time delay neural networks (TDNNs) are an effective acoustic model for large vocabulary speech recognition. The strength of the model can be attributed to its ability to effectively model long temporal contexts. However, current TDNN models are relatively shallow, which limits the modelling capability. This paper proposes a method of increasing the network depth by deepening the kernel used in the TDNN temporal convolutions. The best performing kernel consists of three fully connected layers with a residual (ResNet) connection from the output of the first to the output of the third. The additi","authors_text":"Chao Zhang, Florian Kreyssig, Philip Woodland","cross_cats":["cs.AI","cs.SD","eess.AS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-18T17:54:19Z","title":"Improved TDNNs using Deep Kernels and Frequency Dependent Grid-RNNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06412","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":"sha256:0c980c832f3a569f73ea67678e456a3b05228fbc67a4c2a94c1b2b7d341f83e7","target":"record","created_at":"2026-05-18T00:22:54Z","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":"e43a205a903ebb55a0c0a40101f5e71c42ebdaadab2dd7a8d938de7dd2fab7e0","cross_cats_sorted":["cs.AI","cs.SD","eess.AS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-18T17:54:19Z","title_canon_sha256":"8d4a153f6cbc0d55b3ab152a7642bb5f69de91d0fc5da036914a4047626d9636"},"schema_version":"1.0","source":{"id":"1802.06412","kind":"arxiv","version":2}},"canonical_sha256":"df71ea955dea39d69ae15d18d25909798563baa6d569c204551264d8437a709d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df71ea955dea39d69ae15d18d25909798563baa6d569c204551264d8437a709d","first_computed_at":"2026-05-18T00:22:54.378793Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:54.378793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TdJY0I7sRUQFcT0pE8UO+eERSCcQHUzHCWzjeParn/d3zrvdHeRzl2dvzZYx77ii6bq9ZiO/5ckG1l7WHl2cCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:54.379188Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06412","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c980c832f3a569f73ea67678e456a3b05228fbc67a4c2a94c1b2b7d341f83e7","sha256:49d929f7c2e20644ee3c629e132a44f3d163c994df0b3e94c709e292b86f32f7"],"state_sha256":"135615ae348ee7c5221db6615c63e728111e23652b534f7d3ac59e288c78eff1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0A4zrntH7d3mfF/9n7sczhFH6q67UPF7GjNuTBxb07mfsH5lSVTdGBXamcbqap2+RK6YeyFa5a4mAkXJNelDAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T13:44:07.352079Z","bundle_sha256":"533139eb7103fd664107eedcf74cabc6ea8e1aa4453e24055036505136a046bf"}}