{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XE37FWNYOANAZTBCJECG7W4HZ5","short_pith_number":"pith:XE37FWNY","canonical_record":{"source":{"id":"1703.06697","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2017-03-20T12:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"3bb363aa9d4c5ce68c6e1672aaad71945feded7b09daa64ccbe1f47d383e9bfa","abstract_canon_sha256":"94697a0f77e16cec6446e63a392814d1e7dcaf27d044d4649d19c657c5d07c5f"},"schema_version":"1.0"},"canonical_sha256":"b937f2d9b8701a0ccc2249046fdb87cf519d29d90efdf203fb660d052ea98299","source":{"kind":"arxiv","id":"1703.06697","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06697","created_at":"2026-05-18T00:43:13Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06697v2","created_at":"2026-05-18T00:43:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06697","created_at":"2026-05-18T00:43:13Z"},{"alias_kind":"pith_short_12","alias_value":"XE37FWNYOANA","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XE37FWNYOANAZTBC","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XE37FWNY","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XE37FWNYOANAZTBCJECG7W4HZ5","target":"record","payload":{"canonical_record":{"source":{"id":"1703.06697","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2017-03-20T12:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"3bb363aa9d4c5ce68c6e1672aaad71945feded7b09daa64ccbe1f47d383e9bfa","abstract_canon_sha256":"94697a0f77e16cec6446e63a392814d1e7dcaf27d044d4649d19c657c5d07c5f"},"schema_version":"1.0"},"canonical_sha256":"b937f2d9b8701a0ccc2249046fdb87cf519d29d90efdf203fb660d052ea98299","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:13.043362Z","signature_b64":"5CfAZvFypG91B5qi6wbxBLDTBz1+dtU4EZ2MvP5tltY4vNA3wgBDTWCoEl/f6VTRYZXK8xhauX+O2yY+4kq1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b937f2d9b8701a0ccc2249046fdb87cf519d29d90efdf203fb660d052ea98299","last_reissued_at":"2026-05-18T00:43:13.042814Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:13.042814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.06697","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":"2026-05-18T00:43:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rQMEdHP6eBAEc0D8+qkGElrlAxneTgxH56XjeogZlCNwsf7s3h9ETOiC3EhCB8+oMTTt7kHrq1pPmM3qQXCUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T00:58:48.237952Z"},"content_sha256":"1b16cf36326d294ad5a911ce95a927804c7fbd221cbfdfa8e3d9e0acdeab805f","schema_version":"1.0","event_id":"sha256:1b16cf36326d294ad5a911ce95a927804c7fbd221cbfdfa8e3d9e0acdeab805f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XE37FWNYOANAZTBCJECG7W4HZ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Timbre Analysis of Music Audio Signals with Convolutional Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Emilia G\\'omez, Jordi Pons, Olga Slizovskaia, Rong Gong, Xavier Serra","submitted_at":"2017-03-20T12:00:04Z","abstract_excerpt":"The focus of this work is to study how to efficiently tailor Convolutional Neural Networks (CNNs) towards learning timbre representations from log-mel magnitude spectrograms. We first review the trends when designing CNN architectures. Through this literature overview we discuss which are the crucial points to consider for efficiently learning timbre representations using CNNs. From this discussion we propose a design strategy meant to capture the relevant time-frequency contexts for learning timbre, which permits using domain knowledge for designing architectures. In addition, one of our main"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06697","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":"2026-05-18T00:43:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9CPxhoJnpzUfwuRIX8d/NRlhmUEyu/oYwEuPjJILmgt+xFZ04f57f9hBmGfkWkKKa1ZNRQfHRHj0QNgtUBMQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T00:58:48.238689Z"},"content_sha256":"884ee8505ebef0be659c7e92f4eee81119ca7b879d1b403360ca5952815c85f2","schema_version":"1.0","event_id":"sha256:884ee8505ebef0be659c7e92f4eee81119ca7b879d1b403360ca5952815c85f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XE37FWNYOANAZTBCJECG7W4HZ5/bundle.json","state_url":"https://pith.science/pith/XE37FWNYOANAZTBCJECG7W4HZ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XE37FWNYOANAZTBCJECG7W4HZ5/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":"2026-06-08T00:58:48Z","links":{"resolver":"https://pith.science/pith/XE37FWNYOANAZTBCJECG7W4HZ5","bundle":"https://pith.science/pith/XE37FWNYOANAZTBCJECG7W4HZ5/bundle.json","state":"https://pith.science/pith/XE37FWNYOANAZTBCJECG7W4HZ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XE37FWNYOANAZTBCJECG7W4HZ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XE37FWNYOANAZTBCJECG7W4HZ5","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":"94697a0f77e16cec6446e63a392814d1e7dcaf27d044d4649d19c657c5d07c5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2017-03-20T12:00:04Z","title_canon_sha256":"3bb363aa9d4c5ce68c6e1672aaad71945feded7b09daa64ccbe1f47d383e9bfa"},"schema_version":"1.0","source":{"id":"1703.06697","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06697","created_at":"2026-05-18T00:43:13Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06697v2","created_at":"2026-05-18T00:43:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06697","created_at":"2026-05-18T00:43:13Z"},{"alias_kind":"pith_short_12","alias_value":"XE37FWNYOANA","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XE37FWNYOANAZTBC","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XE37FWNY","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:884ee8505ebef0be659c7e92f4eee81119ca7b879d1b403360ca5952815c85f2","target":"graph","created_at":"2026-05-18T00:43:13Z","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":"The focus of this work is to study how to efficiently tailor Convolutional Neural Networks (CNNs) towards learning timbre representations from log-mel magnitude spectrograms. We first review the trends when designing CNN architectures. Through this literature overview we discuss which are the crucial points to consider for efficiently learning timbre representations using CNNs. From this discussion we propose a design strategy meant to capture the relevant time-frequency contexts for learning timbre, which permits using domain knowledge for designing architectures. In addition, one of our main","authors_text":"Emilia G\\'omez, Jordi Pons, Olga Slizovskaia, Rong Gong, Xavier Serra","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2017-03-20T12:00:04Z","title":"Timbre Analysis of Music Audio Signals with Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06697","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":"sha256:1b16cf36326d294ad5a911ce95a927804c7fbd221cbfdfa8e3d9e0acdeab805f","target":"record","created_at":"2026-05-18T00:43:13Z","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":"94697a0f77e16cec6446e63a392814d1e7dcaf27d044d4649d19c657c5d07c5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2017-03-20T12:00:04Z","title_canon_sha256":"3bb363aa9d4c5ce68c6e1672aaad71945feded7b09daa64ccbe1f47d383e9bfa"},"schema_version":"1.0","source":{"id":"1703.06697","kind":"arxiv","version":2}},"canonical_sha256":"b937f2d9b8701a0ccc2249046fdb87cf519d29d90efdf203fb660d052ea98299","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b937f2d9b8701a0ccc2249046fdb87cf519d29d90efdf203fb660d052ea98299","first_computed_at":"2026-05-18T00:43:13.042814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:13.042814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5CfAZvFypG91B5qi6wbxBLDTBz1+dtU4EZ2MvP5tltY4vNA3wgBDTWCoEl/f6VTRYZXK8xhauX+O2yY+4kq1Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:13.043362Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.06697","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b16cf36326d294ad5a911ce95a927804c7fbd221cbfdfa8e3d9e0acdeab805f","sha256:884ee8505ebef0be659c7e92f4eee81119ca7b879d1b403360ca5952815c85f2"],"state_sha256":"e732a01f8502d16fc2583a11d282d1e5491c75848f6208a5812224e0752746bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zoAm+I/dUkqYY4qqf1llXiLZevz5pbS/1H0Wq1ZPWYJ4rgyWg9qSFQy47yP+SYIhtximBSwXRb8dJJVbOEb7Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T00:58:48.242463Z","bundle_sha256":"b97e8af3fbe49790b7ef5e148c1ef2100f7c9cd91fdb5bf921dc12c5c0c0f700"}}