Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T21:35:06.767136Z
Paper Citation Record · LEDGER
As of 8 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 1 inbound Pith citation observation for arXiv:2506.23873.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T21:35:06.767136Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T21:35:03.959317Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-06T21:35:06.839984Z
55 of 55 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 528fbdf2-b88e-4234-b372-c74b9fd65329 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Emergent musical properties of a transformer under contrastive self-supervised learning
Reference 1
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation cb29155c-c71a-4b9c-ba2a-12dbec1b318e · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Unresolved cited work
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 863e3748-17fb-4e42-a69a-dac2464abb00 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning no chord
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c9526bc9-2ade-4e72-8da3-6f1c7f2eeb58 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning We also assess their contribution to global tasks
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 7bd71412-e790-41c1-9ad5-fef69fe9df2e · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning ViT-1D has 12 layers in total
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6ce22dc1-2153-44d0-af30-1407ef227914 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning ,zT k ] at layers k = 3, 6, 9, 12 (same as Section 5, denoted z3 to z12), along with tokens from a randomly initialized ViT-1D model, de- noted zr
Reference 6
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f59d7daf-a86b-4800-aefc-1a5c815c5819 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Applying NT-Xent loss only to the class token in a lightweight ViT-1D surprisingly enables sequence tokens to handle local tasks while con- tributing to global ones
Reference 7
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d3466fb9-5df9-4222-a525-8f8ec989325f · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Contrastive learn- ing of musical representations,
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f8824715-575b-44c0-80e4-047e53cb353a · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Emergent musical properties of a transformer under contrastive self-supervised learning
Reference 9
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c7500886-066b-4b50-b661-9fecfb08d8c3 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Convolutional operators in the time- frequency domain,
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation ee3b7738-b9c7-4256-8402-d824ef6a9fbe · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Pesto: Pitch estimation with self-supervised transposition-equivariant objective,
Reference 11
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 1fc77fcb-fae8-4e59-acd8-47eea56e370a · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Equivariant self-supervision for musical tempo estimation,
Reference 12
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d38845ea-aff5-4295-8489-914c11e7db75 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning STONE: Self- supervised tonality estimator,
Reference 13
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation a4b40a51-bb0e-4bf4-9f7c-d7feafde0300 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning S-key: Self-supervised learning of major and minor keys from audio,
Reference 14
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation b07e0440-454d-402f-bc93-2a599556c5cb · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Data cleansing with contrastive learning for vocal note event annotations,
Reference 15
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 865fbb87-2a6a-4007-86df-e97febd206a5 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Foundation Models for Music: A Survey
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bdbe5d22-1502-4b3b-a90d-4e42b4422e2a · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Supervised and un- supervised learning of audio representations for music understanding,
Reference 17
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 58c03637-db8d-4e40-8338-de22e327f3aa · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning A simple framework for contrastive learning of visual representations,
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4e614b17-e1c1-4134-9d65-12dae3c6600c · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Exploring simple siamese rep- resentation learning,
Reference 19
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 458e0e72-5dee-4e42-9a35-276709968ecb · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning S3t: Self-supervised pre-training with swin transformer for music classification,
Reference 20
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4d988db2-b634-4d48-ad42-bd4fba13f267 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Multi- source contrastive learning from musical audio,
Reference 21
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation a3bbf4ac-2314-45cb-8010-ec63bc69de56 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning On the effect of data-augmentation on local embedding properties in the contrastive learning of music audio representations,
Reference 22
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 96188798-a9b3-4f25-ad9b-c73e1b069693 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Towards proper contrastive self-supervised learning strategies for mu- sic audio representation,
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation fd279e44-5c74-4ff4-a46d-9d74ec13a658 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Jukebox: A Generative Model for Music
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2aaf93c1-9bbb-4bc0-9a6e-78093de39268 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Music2latent: Consistency autoencoders for latent audio compres- sion,
Reference 25
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 17ce145e-450e-4671-8857-7628a823c927 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Mert: Acoustic music understand- ing model with large-scale self-supervised training,
Reference 26
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation bf08a89e-44f0-4548-adcd-7ea92fc5e838 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Hu- bert: Self-supervised speech representation learning by masked prediction of hidden units,
Reference 27
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation a36c6b53-2ee3-4af9-ac30-dd0535a7b306 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Masked Modeling Duo: Towards a Universal Audio Pre-training Framework,
Reference 28
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 9ed29d95-722a-4f58-8a8c-b338ce9d31e7 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning A foundation model for music informatics,
Reference 29
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 55d2706a-a363-4f84-8e75-fca37ed507c6 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Towards learning universal audio repre- sentations,
Reference 30
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 899d05f0-b107-4a45-8970-142757f7b261 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Efficient training of audio transformers with patchout,
Reference 31
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f5c98dbb-9457-4fed-803d-2f660091463a · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning AST: Audio Spectrogram Transformer,
Reference 32
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6d486a54-0999-4ea3-8da7-b63a8d4957d1 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Contrastive audio-language learning for music,
Reference 33
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 074b5f9a-a406-4fbf-9f62-3a7b9d51397f · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning MuLan: A joint embedding of music audio and natural language,
Reference 34
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 98d301f3-89f8-4c4a-8df1-dc3832eb69e6 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning An image is worth 16x16 words: Trans- formers for image recognition at scale,
Reference 35
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 0ddd29b2-f065-40fb-8084-8d812f25c609 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Emerging properties in self-supervised vision transformers,
Reference 36
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d749dca6-d96e-4f2a-ab1b-82d70efb1fa3 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Dinov2: Learning robust visual features without su- pervision,
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 226d7449-df82-40ae-a6f2-03f66a9dc5c3 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning An experimental comparison of multi-view self-supervised methods for music tagging,
Reference 38
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 13f4b01c-0950-48c2-a97d-ffc126b7b848 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Evaluation of algorithms using games: The case of music tagging,
Reference 39
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation e28d92d8-1aab-41b5-ae3a-56c8a7637f0d · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Sample-level deep convolutional neural networks for music auto- tagging using raw waveforms,
Reference 40
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 0bfdffd7-e98b-44b1-965b-5f578e7b2b94 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Fmak: A dataset of key and mode annotations for the free music archive– extended abstract,
Reference 41
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation fa88e5c1-f5a9-4383-a79c-b8aab4f90d48 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Fma: A dataset for music analysis,
Reference 42
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4261a79d-38a1-49c8-963a-6dcde246119f · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Two datasets for tempo estimation and key detection in electronic dance music annotated from user corrections,
Reference 43
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation e23889d3-0cbb-4bd8-af08-b83929fd044d · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Mir_eval: A transparent implementation of common mir metrics
Reference 44
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 2c3cc49e-13ae-4d75-b100-b650bc73cc34 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning A review of rhythm de- scription systems,
Reference 45
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation e8384560-86f0-475e-a6dc-a925eb01e127 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Gtzan- rhythm: Extending the gtzan test-set with beat, down- beat and swing annotations,
Reference 46
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 29e5a141-58f7-462c-ae10-9a1b598ad9d0 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning An efficient state- space model for joint tempo and meter tracking
Reference 47
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 3b5e2a55-18bf-417a-9cae-bc64d6d9fe20 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Schubert win- terreise dataset: A multimodal scenario for music anal- ysis,
Reference 48
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 1caf7440-4e60-42e1-9807-91284e18a930 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Rwc music database: Popular, classical, and jazz music databases,
Reference 49
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4e433577-08ba-47a5-a0e9-024df2af5a6b · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Attention is all you need,
Reference 50
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c959286e-801c-4fea-b083-faeeb55374d1 · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Sbert-wk: A sentence em- bedding method by dissecting bert-based word mod- els,
Reference 51
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 0efdfb1f-c557-4300-9d88-530e218306df · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning Multipitch esti- mation of piano sounds using a new probabilistic spec- tral smoothness principle,
Reference 52
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 34d065b2-aead-4b5b-a7e5-bb482dc064bf · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python,
Reference 53
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 8f7bef19-b1bc-43b1-9700-72719f01615b · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning How many layers and why? An analysis of the model depth in transformers,
Reference 54
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 29c93086-8781-4103-8290-204c23bc153c · outbound
Emergent musical properties of a transformer under contrastive self-supervised learning What does bert look at? an analysis of bert’s attention,
Reference 55
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f8824715-575b-44c0-80e4-047e53cb353a · inbound
Emergent musical properties of a transformer under contrastive self-supervised learning Emergent musical properties of a transformer under contrastive self-supervised learning
Reference 9
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.