{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KAEN5YMVJ7X3GL6E7QQQ7YZCUT","short_pith_number":"pith:KAEN5YMV","canonical_record":{"source":{"id":"1906.10996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-06-26T11:52:49Z","cross_cats_sorted":["cs.CV","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"ff3d2399e407e55636d64c6896c2313e4c331d8410e16b5eef0e1299e2305e78","abstract_canon_sha256":"70c4ae7b0492cc348fdff7440420f3828fe7a1e48ed891c17852578cda6d5d1c"},"schema_version":"1.0"},"canonical_sha256":"5008dee1954fefb32fc4fc210fe322a4e11a1ccc2c662ac46c4fe7a30426794e","source":{"kind":"arxiv","id":"1906.10996","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10996","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10996v1","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10996","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"pith_short_12","alias_value":"KAEN5YMVJ7X3","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KAEN5YMVJ7X3GL6E","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KAEN5YMV","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KAEN5YMVJ7X3GL6E7QQQ7YZCUT","target":"record","payload":{"canonical_record":{"source":{"id":"1906.10996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-06-26T11:52:49Z","cross_cats_sorted":["cs.CV","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"ff3d2399e407e55636d64c6896c2313e4c331d8410e16b5eef0e1299e2305e78","abstract_canon_sha256":"70c4ae7b0492cc348fdff7440420f3828fe7a1e48ed891c17852578cda6d5d1c"},"schema_version":"1.0"},"canonical_sha256":"5008dee1954fefb32fc4fc210fe322a4e11a1ccc2c662ac46c4fe7a30426794e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:10.332292Z","signature_b64":"rmesfdSHGNfNyO1p/nHmIqJeo/+rzDz0qAU7uBZdG2cfaCv0oV0S5hGNDKuzQAiHerVTkC4to66HZR71NDKsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5008dee1954fefb32fc4fc210fe322a4e11a1ccc2c662ac46c4fe7a30426794e","last_reissued_at":"2026-05-17T23:42:10.331660Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:10.331660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.10996","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":"2026-05-17T23:42:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GNMxx4ct1ymZcbPzj42QG/SlS+Auqev0bPxv2aCRIlBeXtm0GUe+wC60mjtl5uLoCTFZCCQYLNTx2ACCzRd7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T19:34:21.873029Z"},"content_sha256":"5b8e2af34e55c66ce8e55c45cbb314972a128725b7cd3eae5b26cab45cbae3ee","schema_version":"1.0","event_id":"sha256:5b8e2af34e55c66ce8e55c45cbb314972a128725b7cd3eae5b26cab45cbae3ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KAEN5YMVJ7X3GL6E7QQQ7YZCUT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Soft-Attention Models for Tempo-invariant Audio-Sheet Music Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.IR","authors_text":"Andreas Arzt, Gerhard Widmer, Luis Carvalho, Matthias Dorfer, Stefan Balke","submitted_at":"2019-06-26T11:52:49Z","abstract_excerpt":"Connecting large libraries of digitized audio recordings to their corresponding sheet music images has long been a motivation for researchers to develop new cross-modal retrieval systems. In recent years, retrieval systems based on embedding space learning with deep neural networks got a step closer to fulfilling this vision. However, global and local tempo deviations in the music recordings still require careful tuning of the amount of temporal context given to the system. In this paper, we address this problem by introducing an additional soft-attention mechanism on the audio input. Quantita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10996","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":""},"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":"2026-05-17T23:42:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H2gHPaqGqwiXz922yKD9VbENUcISunPgN0gR1trbTGFBb1MLws+MScFcHd8lj4hn/i7uqlzH6h+OZJMkRDLTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T19:34:21.873752Z"},"content_sha256":"35c8d79e4ffa24a53a43adbf64a662c6ce48378342e3d1dd0b9e0c1b766fa037","schema_version":"1.0","event_id":"sha256:35c8d79e4ffa24a53a43adbf64a662c6ce48378342e3d1dd0b9e0c1b766fa037"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KAEN5YMVJ7X3GL6E7QQQ7YZCUT/bundle.json","state_url":"https://pith.science/pith/KAEN5YMVJ7X3GL6E7QQQ7YZCUT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KAEN5YMVJ7X3GL6E7QQQ7YZCUT/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":"2026-05-23T19:34:21Z","links":{"resolver":"https://pith.science/pith/KAEN5YMVJ7X3GL6E7QQQ7YZCUT","bundle":"https://pith.science/pith/KAEN5YMVJ7X3GL6E7QQQ7YZCUT/bundle.json","state":"https://pith.science/pith/KAEN5YMVJ7X3GL6E7QQQ7YZCUT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KAEN5YMVJ7X3GL6E7QQQ7YZCUT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KAEN5YMVJ7X3GL6E7QQQ7YZCUT","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":"70c4ae7b0492cc348fdff7440420f3828fe7a1e48ed891c17852578cda6d5d1c","cross_cats_sorted":["cs.CV","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-06-26T11:52:49Z","title_canon_sha256":"ff3d2399e407e55636d64c6896c2313e4c331d8410e16b5eef0e1299e2305e78"},"schema_version":"1.0","source":{"id":"1906.10996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10996","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10996v1","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10996","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"pith_short_12","alias_value":"KAEN5YMVJ7X3","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KAEN5YMVJ7X3GL6E","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KAEN5YMV","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:35c8d79e4ffa24a53a43adbf64a662c6ce48378342e3d1dd0b9e0c1b766fa037","target":"graph","created_at":"2026-05-17T23:42:10Z","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":"Connecting large libraries of digitized audio recordings to their corresponding sheet music images has long been a motivation for researchers to develop new cross-modal retrieval systems. In recent years, retrieval systems based on embedding space learning with deep neural networks got a step closer to fulfilling this vision. However, global and local tempo deviations in the music recordings still require careful tuning of the amount of temporal context given to the system. In this paper, we address this problem by introducing an additional soft-attention mechanism on the audio input. Quantita","authors_text":"Andreas Arzt, Gerhard Widmer, Luis Carvalho, Matthias Dorfer, Stefan Balke","cross_cats":["cs.CV","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-06-26T11:52:49Z","title":"Learning Soft-Attention Models for Tempo-invariant Audio-Sheet Music Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10996","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":"sha256:5b8e2af34e55c66ce8e55c45cbb314972a128725b7cd3eae5b26cab45cbae3ee","target":"record","created_at":"2026-05-17T23:42:10Z","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":"70c4ae7b0492cc348fdff7440420f3828fe7a1e48ed891c17852578cda6d5d1c","cross_cats_sorted":["cs.CV","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-06-26T11:52:49Z","title_canon_sha256":"ff3d2399e407e55636d64c6896c2313e4c331d8410e16b5eef0e1299e2305e78"},"schema_version":"1.0","source":{"id":"1906.10996","kind":"arxiv","version":1}},"canonical_sha256":"5008dee1954fefb32fc4fc210fe322a4e11a1ccc2c662ac46c4fe7a30426794e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5008dee1954fefb32fc4fc210fe322a4e11a1ccc2c662ac46c4fe7a30426794e","first_computed_at":"2026-05-17T23:42:10.331660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:10.331660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rmesfdSHGNfNyO1p/nHmIqJeo/+rzDz0qAU7uBZdG2cfaCv0oV0S5hGNDKuzQAiHerVTkC4to66HZR71NDKsDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:10.332292Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.10996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b8e2af34e55c66ce8e55c45cbb314972a128725b7cd3eae5b26cab45cbae3ee","sha256:35c8d79e4ffa24a53a43adbf64a662c6ce48378342e3d1dd0b9e0c1b766fa037"],"state_sha256":"95979e0bae7bf7db4791bd77d1d857b0f5e6caa084a6799dff09ce01befa952b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uYP/VejdmHFg29SQ9G3iNhtxGO+j4YHAuWAGIDOTQk7NJeHkhJIvhRPmlh1QSBeyKk5XmqxX+dejXx6SBD+rAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T19:34:21.877405Z","bundle_sha256":"0288f8333a79c20e217a686a495cd0ac76dcd225fe762321608c02136d99682d"}}