{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ALTUXAC72ZNSTCOJL6ECF5BQD2","short_pith_number":"pith:ALTUXAC7","schema_version":"1.0","canonical_sha256":"02e74b805fd65b2989c95f8822f4301ebe4a093a49f23174d2a9783e80b48304","source":{"kind":"arxiv","id":"2010.01733","version":4},"attestation_state":"computed","paper":{"title":"D3Net: Densely connected multidilated DenseNet for music source separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Naoya Takahashi, Yuki Mitsufuji","submitted_at":"2020-10-05T01:03:08Z","abstract_excerpt":"Music source separation involves a large input field to model a long-term dependence of an audio signal. Previous convolutional neural network (CNN)-based approaches address the large input field modeling using sequentially down- and up-sampling feature maps or dilated convolution. In this paper, we claim the importance of a rapid growth of a receptive field and a simultaneous modeling of multi-resolution data in a single convolution layer, and propose a novel CNN architecture called densely connected dilated DenseNet (D3Net). D3Net involves a novel multi-dilated convolution that has different"},"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":"2010.01733","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-05T01:03:08Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"d57f0853d654dec3209f207c793a72b7ddbd4e7670b5664b600b98a3f03aa8c8","abstract_canon_sha256":"f74fa387e2045b69e76e0b34c932ba3ef63b20f6e0f4ca7fa1849a6d5d2e4c6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:50.731799Z","signature_b64":"55qbFFUNNGxl8b3dIY5J0LSYyKeqZs5ItJpWhCTfcURKnZFwv7GmR+wlLG/tdBntE/3F23L/eiwnWs7mFJ9jCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02e74b805fd65b2989c95f8822f4301ebe4a093a49f23174d2a9783e80b48304","last_reissued_at":"2026-07-05T02:26:50.731288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:50.731288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D3Net: Densely connected multidilated DenseNet for music source separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Naoya Takahashi, Yuki Mitsufuji","submitted_at":"2020-10-05T01:03:08Z","abstract_excerpt":"Music source separation involves a large input field to model a long-term dependence of an audio signal. Previous convolutional neural network (CNN)-based approaches address the large input field modeling using sequentially down- and up-sampling feature maps or dilated convolution. In this paper, we claim the importance of a rapid growth of a receptive field and a simultaneous modeling of multi-resolution data in a single convolution layer, and propose a novel CNN architecture called densely connected dilated DenseNet (D3Net). D3Net involves a novel multi-dilated convolution that has different"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01733","kind":"arxiv","version":4},"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/2010.01733/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":"2010.01733","created_at":"2026-07-05T02:26:50.731362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01733v4","created_at":"2026-07-05T02:26:50.731362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01733","created_at":"2026-07-05T02:26:50.731362+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALTUXAC72ZNS","created_at":"2026-07-05T02:26:50.731362+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALTUXAC72ZNSTCOJ","created_at":"2026-07-05T02:26:50.731362+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALTUXAC7","created_at":"2026-07-05T02:26:50.731362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.06965","citing_title":"Improving Music Source Separation with Diffusion and Consistency Refinement","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ALTUXAC72ZNSTCOJL6ECF5BQD2","json":"https://pith.science/pith/ALTUXAC72ZNSTCOJL6ECF5BQD2.json","graph_json":"https://pith.science/api/pith-number/ALTUXAC72ZNSTCOJL6ECF5BQD2/graph.json","events_json":"https://pith.science/api/pith-number/ALTUXAC72ZNSTCOJL6ECF5BQD2/events.json","paper":"https://pith.science/paper/ALTUXAC7"},"agent_actions":{"view_html":"https://pith.science/pith/ALTUXAC72ZNSTCOJL6ECF5BQD2","download_json":"https://pith.science/pith/ALTUXAC72ZNSTCOJL6ECF5BQD2.json","view_paper":"https://pith.science/paper/ALTUXAC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01733&json=true","fetch_graph":"https://pith.science/api/pith-number/ALTUXAC72ZNSTCOJL6ECF5BQD2/graph.json","fetch_events":"https://pith.science/api/pith-number/ALTUXAC72ZNSTCOJL6ECF5BQD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALTUXAC72ZNSTCOJL6ECF5BQD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALTUXAC72ZNSTCOJL6ECF5BQD2/action/storage_attestation","attest_author":"https://pith.science/pith/ALTUXAC72ZNSTCOJL6ECF5BQD2/action/author_attestation","sign_citation":"https://pith.science/pith/ALTUXAC72ZNSTCOJL6ECF5BQD2/action/citation_signature","submit_replication":"https://pith.science/pith/ALTUXAC72ZNSTCOJL6ECF5BQD2/action/replication_record"}},"created_at":"2026-07-05T02:26:50.731362+00:00","updated_at":"2026-07-05T02:26:50.731362+00:00"}