{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4TELM6PMF76ETCB7HAUHFTBJVT","short_pith_number":"pith:4TELM6PM","schema_version":"1.0","canonical_sha256":"e4c8b679ec2ffc49883f382872cc29acfd71d0750cc17324fb04ba94e24820b4","source":{"kind":"arxiv","id":"1909.09577","version":1},"attestation_state":"computed","paper":{"title":"NeMo: a toolkit for building AI applications using Neural Modules","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Boris Ginsburg, Huyen Nguyen, Jack Cook, Jason Li, Jocelyn Huang, Jonathan M. Cohen, Mariya Popova, Oleksii Hrinchuk, Oleksii Kuchaiev, Patrice Castonguay, Ryan Leary, Samuel Kriman, Stanislav Beliaev, Vitaly Lavrukhin","submitted_at":"2019-09-14T03:51:46Z","abstract_excerpt":"NeMo (Neural Modules) is a Python framework-agnostic toolkit for creating AI applications through re-usability, abstraction, and composition. NeMo is built around neural modules, conceptual blocks of neural networks that take typed inputs and produce typed outputs. Such modules typically represent data layers, encoders, decoders, language models, loss functions, or methods of combining activations. NeMo makes it easy to combine and re-use these building blocks while providing a level of semantic correctness checking via its neural type system. The toolkit comes with extendable collections of p"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1909.09577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-14T03:51:46Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"486ad5778f0dcd7d00a6284f97762c8c002dfc72801357ada7ba58b1aa1d6a1e","abstract_canon_sha256":"bf2aece8ae9b0dbe1188b9b6f367827132aa69c70bfbdb24444332eb43070787"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:06:01.773014Z","signature_b64":"3Y/m2KGStPFDulo7HwirNZAGK3Hdx2QHJCGQxntHU0brDJceN/FsrrbC7aOtymz9nPn91I/MwjjIwqK801i/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4c8b679ec2ffc49883f382872cc29acfd71d0750cc17324fb04ba94e24820b4","last_reissued_at":"2026-07-05T00:06:01.772551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:06:01.772551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeMo: a toolkit for building AI applications using Neural Modules","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Boris Ginsburg, Huyen Nguyen, Jack Cook, Jason Li, Jocelyn Huang, Jonathan M. Cohen, Mariya Popova, Oleksii Hrinchuk, Oleksii Kuchaiev, Patrice Castonguay, Ryan Leary, Samuel Kriman, Stanislav Beliaev, Vitaly Lavrukhin","submitted_at":"2019-09-14T03:51:46Z","abstract_excerpt":"NeMo (Neural Modules) is a Python framework-agnostic toolkit for creating AI applications through re-usability, abstraction, and composition. NeMo is built around neural modules, conceptual blocks of neural networks that take typed inputs and produce typed outputs. Such modules typically represent data layers, encoders, decoders, language models, loss functions, or methods of combining activations. NeMo makes it easy to combine and re-use these building blocks while providing a level of semantic correctness checking via its neural type system. The toolkit comes with extendable collections of p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.09577","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/1909.09577/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1909.09577","created_at":"2026-07-05T00:06:01.772605+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.09577v1","created_at":"2026-07-05T00:06:01.772605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.09577","created_at":"2026-07-05T00:06:01.772605+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TELM6PMF76E","created_at":"2026-07-05T00:06:01.772605+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TELM6PMF76ETCB7","created_at":"2026-07-05T00:06:01.772605+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TELM6PM","created_at":"2026-07-05T00:06:01.772605+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25959","citing_title":"SE-AGCNet: An End-to-End Framework for Joint Speech Enhancement and Loudness Control in Meeting Scenarios","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24080","citing_title":"Audio--Image Alignment as a Continued-Pretraining Stage Improves Low-Resource ASR","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24169","citing_title":"Data Scale, Not Latency, Shapes Cross-Lingual Encoder Transfer in Streaming ASR","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19989","citing_title":"Online Dynamic Batching with Formal Guarantees for LLM Training","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06559","citing_title":"IRAF: Interference-Resilient Adaptive Fusion for Noise-Robust End-to-End Full-Duplex Spoken Dialogue Systems","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04730","citing_title":"Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31469","citing_title":"Scaling Conversational Hungarian ASR: The BEA-Dialogue+ Corpus","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23066","citing_title":"Orbax: Distributed Checkpointing with JAX","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04468","citing_title":"NVILA: Efficient Frontier Visual Language Models","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22746","citing_title":"Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05201","citing_title":"Exploring Speech Foundation Models for Speaker Diarization Across Lifespan","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19695","citing_title":"Cross-Talk Speech Reduction, by Separation, for Separation","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15442","citing_title":"Mind the Gap: Impact of Synthetic Conversational Data on Multi-Talker ASR and Speaker Diarization","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2506.10779","citing_title":"Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16378","citing_title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2512.19442","citing_title":"Real-Time Streamable Generative Speech Restoration with Flow Matching","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27436","citing_title":"BUT System Description for CHiME-9 MCoRec Challenge","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10985","citing_title":"Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05201","citing_title":"Exploring Speech Foundation Models for Speaker Diarization Across Lifespan","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4TELM6PMF76ETCB7HAUHFTBJVT","json":"https://pith.science/pith/4TELM6PMF76ETCB7HAUHFTBJVT.json","graph_json":"https://pith.science/api/pith-number/4TELM6PMF76ETCB7HAUHFTBJVT/graph.json","events_json":"https://pith.science/api/pith-number/4TELM6PMF76ETCB7HAUHFTBJVT/events.json","paper":"https://pith.science/paper/4TELM6PM"},"agent_actions":{"view_html":"https://pith.science/pith/4TELM6PMF76ETCB7HAUHFTBJVT","download_json":"https://pith.science/pith/4TELM6PMF76ETCB7HAUHFTBJVT.json","view_paper":"https://pith.science/paper/4TELM6PM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.09577&json=true","fetch_graph":"https://pith.science/api/pith-number/4TELM6PMF76ETCB7HAUHFTBJVT/graph.json","fetch_events":"https://pith.science/api/pith-number/4TELM6PMF76ETCB7HAUHFTBJVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TELM6PMF76ETCB7HAUHFTBJVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TELM6PMF76ETCB7HAUHFTBJVT/action/storage_attestation","attest_author":"https://pith.science/pith/4TELM6PMF76ETCB7HAUHFTBJVT/action/author_attestation","sign_citation":"https://pith.science/pith/4TELM6PMF76ETCB7HAUHFTBJVT/action/citation_signature","submit_replication":"https://pith.science/pith/4TELM6PMF76ETCB7HAUHFTBJVT/action/replication_record"}},"created_at":"2026-07-05T00:06:01.772605+00:00","updated_at":"2026-07-05T00:06:01.772605+00:00"}