{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:SMSLW3Y6YQAX2334SKTLNHU62T","short_pith_number":"pith:SMSLW3Y6","canonical_record":{"source":{"id":"2008.04470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-11T01:24:45Z","cross_cats_sorted":["cs.LG","cs.NE","cs.SD","stat.ML"],"title_canon_sha256":"e6bb92a2503cdbdcd2fe84f7d31c1960920c166d340e63292d2ca29d07ce6125","abstract_canon_sha256":"865fc5ed2187567934bd472c83ad5a40142125b6086375424358fb95d108f25c"},"schema_version":"1.0"},"canonical_sha256":"9324bb6f1ec4017d6f7c92a6b69e9ed4e185c2d5bed96f5be15acebab1158164","source":{"kind":"arxiv","id":"2008.04470","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.04470","created_at":"2026-07-05T01:26:25Z"},{"alias_kind":"arxiv_version","alias_value":"2008.04470v1","created_at":"2026-07-05T01:26:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04470","created_at":"2026-07-05T01:26:25Z"},{"alias_kind":"pith_short_12","alias_value":"SMSLW3Y6YQAX","created_at":"2026-07-05T01:26:25Z"},{"alias_kind":"pith_short_16","alias_value":"SMSLW3Y6YQAX2334","created_at":"2026-07-05T01:26:25Z"},{"alias_kind":"pith_short_8","alias_value":"SMSLW3Y6","created_at":"2026-07-05T01:26:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:SMSLW3Y6YQAX2334SKTLNHU62T","target":"record","payload":{"canonical_record":{"source":{"id":"2008.04470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-11T01:24:45Z","cross_cats_sorted":["cs.LG","cs.NE","cs.SD","stat.ML"],"title_canon_sha256":"e6bb92a2503cdbdcd2fe84f7d31c1960920c166d340e63292d2ca29d07ce6125","abstract_canon_sha256":"865fc5ed2187567934bd472c83ad5a40142125b6086375424358fb95d108f25c"},"schema_version":"1.0"},"canonical_sha256":"9324bb6f1ec4017d6f7c92a6b69e9ed4e185c2d5bed96f5be15acebab1158164","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:25.277106Z","signature_b64":"xO6LN+hEUGXYZI6QZbr8tNCF9Iyj/8SQdUDvyA4AXPHtYaUaeQOKjV5DqaLtK/rXEXcNg62cBbu5hgtfxjOdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9324bb6f1ec4017d6f7c92a6b69e9ed4e185c2d5bed96f5be15acebab1158164","last_reissued_at":"2026-07-05T01:26:25.276698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:25.276698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.04470","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":"2026-07-05T01:26:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fnDJpKhmwTnhaBoIDEhJ1Q0FlK+SPVEU7QMxuRuPSCEx+Ch/AKJoB04zNZ2/M3+e16fnmUsbUOc4iN0ZQ1GJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T09:36:46.473087Z"},"content_sha256":"b0d7f1c627a565cd5aa48254669188514da601f0523e140d89e7135b1541f4f1","schema_version":"1.0","event_id":"sha256:b0d7f1c627a565cd5aa48254669188514da601f0523e140d89e7135b1541f4f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:SMSLW3Y6YQAX2334SKTLNHU62T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Arvindh Krishnaswamy, Jean-Marc Valin, Karim Helwani, Neerad Phansalkar, Ritwik Giri, Umut Isik","submitted_at":"2020-08-11T01:24:45Z","abstract_excerpt":"Neural network applications generally benefit from larger-sized models, but for current speech enhancement models, larger scale networks often suffer from decreased robustness to the variety of real-world use cases beyond what is encountered in training data. We introduce several innovations that lead to better large neural networks for speech enhancement. The novel PoCoNet architecture is a convolutional neural network that, with the use of frequency-positional embeddings, is able to more efficiently build frequency-dependent features in the early layers. A semi-supervised method helps increa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04470","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/2008.04470/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":"2026-07-05T01:26:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2XDxLcF031lI792+tqo7sPBx1PPnF2qsu8YAhmcFM58ALZac3K7qkBEcTGHMfC2bHtSxZBYyrfnBq3QbHWdoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T09:36:46.474073Z"},"content_sha256":"e5ab83a45557ea086b8311d2e5c3e6dfe2697cb0771a131cbd711482ef22dd2f","schema_version":"1.0","event_id":"sha256:e5ab83a45557ea086b8311d2e5c3e6dfe2697cb0771a131cbd711482ef22dd2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T/bundle.json","state_url":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SMSLW3Y6YQAX2334SKTLNHU62T/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":"2026-08-01T09:36:46Z","links":{"resolver":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T","bundle":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T/bundle.json","state":"https://pith.science/pith/SMSLW3Y6YQAX2334SKTLNHU62T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SMSLW3Y6YQAX2334SKTLNHU62T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SMSLW3Y6YQAX2334SKTLNHU62T","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":"865fc5ed2187567934bd472c83ad5a40142125b6086375424358fb95d108f25c","cross_cats_sorted":["cs.LG","cs.NE","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-11T01:24:45Z","title_canon_sha256":"e6bb92a2503cdbdcd2fe84f7d31c1960920c166d340e63292d2ca29d07ce6125"},"schema_version":"1.0","source":{"id":"2008.04470","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.04470","created_at":"2026-07-05T01:26:25Z"},{"alias_kind":"arxiv_version","alias_value":"2008.04470v1","created_at":"2026-07-05T01:26:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04470","created_at":"2026-07-05T01:26:25Z"},{"alias_kind":"pith_short_12","alias_value":"SMSLW3Y6YQAX","created_at":"2026-07-05T01:26:25Z"},{"alias_kind":"pith_short_16","alias_value":"SMSLW3Y6YQAX2334","created_at":"2026-07-05T01:26:25Z"},{"alias_kind":"pith_short_8","alias_value":"SMSLW3Y6","created_at":"2026-07-05T01:26:25Z"}],"graph_snapshots":[{"event_id":"sha256:e5ab83a45557ea086b8311d2e5c3e6dfe2697cb0771a131cbd711482ef22dd2f","target":"graph","created_at":"2026-07-05T01:26:25Z","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/2008.04470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural network applications generally benefit from larger-sized models, but for current speech enhancement models, larger scale networks often suffer from decreased robustness to the variety of real-world use cases beyond what is encountered in training data. We introduce several innovations that lead to better large neural networks for speech enhancement. The novel PoCoNet architecture is a convolutional neural network that, with the use of frequency-positional embeddings, is able to more efficiently build frequency-dependent features in the early layers. A semi-supervised method helps increa","authors_text":"Arvindh Krishnaswamy, Jean-Marc Valin, Karim Helwani, Neerad Phansalkar, Ritwik Giri, Umut Isik","cross_cats":["cs.LG","cs.NE","cs.SD","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-11T01:24:45Z","title":"PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04470","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:b0d7f1c627a565cd5aa48254669188514da601f0523e140d89e7135b1541f4f1","target":"record","created_at":"2026-07-05T01:26:25Z","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":"865fc5ed2187567934bd472c83ad5a40142125b6086375424358fb95d108f25c","cross_cats_sorted":["cs.LG","cs.NE","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-11T01:24:45Z","title_canon_sha256":"e6bb92a2503cdbdcd2fe84f7d31c1960920c166d340e63292d2ca29d07ce6125"},"schema_version":"1.0","source":{"id":"2008.04470","kind":"arxiv","version":1}},"canonical_sha256":"9324bb6f1ec4017d6f7c92a6b69e9ed4e185c2d5bed96f5be15acebab1158164","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9324bb6f1ec4017d6f7c92a6b69e9ed4e185c2d5bed96f5be15acebab1158164","first_computed_at":"2026-07-05T01:26:25.276698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:26:25.276698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xO6LN+hEUGXYZI6QZbr8tNCF9Iyj/8SQdUDvyA4AXPHtYaUaeQOKjV5DqaLtK/rXEXcNg62cBbu5hgtfxjOdCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:26:25.277106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.04470","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0d7f1c627a565cd5aa48254669188514da601f0523e140d89e7135b1541f4f1","sha256:e5ab83a45557ea086b8311d2e5c3e6dfe2697cb0771a131cbd711482ef22dd2f"],"state_sha256":"071923a8f04a05e44a3fe919c168a9ebf2f5acef9647e2a6eda758c71dd60286"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yBDLjwmK2k1k1n9vdKPRMI9kj627rD9FP5ieNAuTKbLZEqB0JRc3JGYjvAX8jyPp1/Kozo+CbEcdJKA7WD8eCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T09:36:46.485546Z","bundle_sha256":"fe2bdec07697ad25d1a1ef14c7fd12a9d26dede9ca86b78af4026c2ddc74d6df"}}