Paper Citation Record · LEDGER

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering

As of 15 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 1 inbound Pith citation observation for arXiv:2607.20253.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.20253 v3

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T10:24:21.848332Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:47:17.612675Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-15T14:47:18.305594Z

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy0
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 092c7024-82f6-4346-9df7-a3172c00e569 · outbound

This paper cites MusicLM: Generating Music From Text.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering MusicLM: Generating Music From Text

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:18.006109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15b1b6f4-2bc9-4438-bf93-1ad6a421b749 · outbound

This paper cites Music generation benchmarking methodology.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Music generation benchmarking methodology

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:18.134417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a57b6254-ff95-4b33-b2d7-2a371b5ceec0 · outbound

This paper cites V ocals music leaderboard.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering V ocals music leaderboard

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:18.298421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 291d1b82-2267-412f-9b0c-c0907bf72536 · outbound

This paper cites Yourmt3+: Multi- instrument music transcription with enhanced transformer architectures and cross-dataset stem augmentation.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Yourmt3+: Multi- instrument music transcription with enhanced transformer architectures and cross-dataset stem augmentation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:18.390559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcbc03ff-7951-499d-9455-5e6acfde02ad · outbound

This paper cites Musicldm: Enhancing novelty in text-to-music generation using beat-synchronous mixup strategies.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Musicldm: Enhancing novelty in text-to-music generation using beat-synchronous mixup strategies

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:18.493462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63c8413b-bc8b-4e6e-8f89-03f77c6ee67f · outbound

This paper cites Visqol v3: An open source production ready objective speech and audio metric.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Visqol v3: An open source production ready objective speech and audio metric

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:18.639038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 243b5bf6-cb98-4bcf-aed2-4d70a9fcdb94 · outbound

This paper cites Self-supervised learning with random-projection quantizer for speech recognition.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Self-supervised learning with random-projection quantizer for speech recognition

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:18.749729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf9f9a73-254c-4c92-80ce-6b7bb7d7ccea · outbound

This paper cites Simple and controllable music generation.Advances in neural information processing systems, 36:47704–47720, 2023.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Simple and controllable music generation.Advances in neural information processing systems, 36:47704–47720, 2023

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:18.811849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc40c4c3-9c81-4c21-ad1a-eaebd1d559a0 · outbound

This paper cites Ace-step 1.5: Pushing the boundaries of open-source music generation.arXiv preprint arXiv:2602.00744, 2026.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Ace-step 1.5: Pushing the boundaries of open-source music generation.arXiv preprint arXiv:2602.00744, 2026

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:18.929585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2a48299-6730-44a6-baaf-3ad500282caf · outbound

This paper cites ACE-Step: A Step Towards Music Generation Foundation Model.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering ACE-Step: A Step Towards Music Generation Foundation Model

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:19.082295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c71f853a-4002-407f-ae28-1d97362973d7 · outbound

This paper cites Visqol: an objective speech quality model.EURASIP Journal on Audio, Speech, and Music Processing, 2015(1):13, 2015.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Visqol: an objective speech quality model.EURASIP Journal on Audio, Speech, and Music Processing, 2015(1):13, 2015

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:19.205919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22bc1965-513f-4a7d-b197-0867ecd454a3 · outbound

This paper cites Classifier-Free Diffusion Guidance.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Classifier-Free Diffusion Guidance

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:19.344153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90c79656-f78b-4b0e-a716-6d4069323389 · outbound

This paper cites Levo: High-quality song generation with multi- preference alignment.Advances in Neural Information Processing Systems, 38:102448–102479, 2026.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Levo: High-quality song generation with multi- preference alignment.Advances in Neural Information Processing Systems, 38:102448–102479, 2026

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:19.468121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5251279e-a494-4357-b986-416e5e204f89 · outbound

This paper cites LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:19.629619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3c06397-82d8-41be-b830-95d0becb9592 · outbound

This paper cites Songecho: Towards cover song generation via instance-adaptive element-wise linear modulation.arXiv preprint arXiv:2602.19976, 2026.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Songecho: Towards cover song generation via instance-adaptive element-wise linear modulation.arXiv preprint arXiv:2602.19976, 2026

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:19.768908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a76ba1c-6b22-469b-8255-23c6d38a7d2f · outbound

This paper cites Duo-tok: Dual-track semantic music tokenizer for vocal-accompaniment generation.arXiv preprint arXiv:2511.20224, 2025.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Duo-tok: Dual-track semantic music tokenizer for vocal-accompaniment generation.arXiv preprint arXiv:2511.20224, 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:19.935018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f799bc6a-d8ba-4fea-9d08-17484026fdeb · outbound

This paper cites Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:20.063956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d93b9a5e-1c78-4bbd-addc-9c7b237946a1 · outbound

This paper cites Flow-GRPO: Training Flow Matching Models via Online RL.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Flow-GRPO: Training Flow Matching Models via Online RL

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:20.269589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8885ab35-2372-4fcd-ac94-3bc440302153 · outbound

This paper cites Music source separation with band-split rope transformer.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Music source separation with band-split rope transformer

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:20.398877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3ce65f0-1775-4e9d-b6d2-4995916b2e60 · outbound

This paper cites CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:20.489543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9736da5-4768-4c28-aacb-e671f45f624a · outbound

This paper cites DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:20.586685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8aaec9d-b444-43f3-b35a-2f01365c39bd · outbound

This paper cites Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:20.680861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a479f5c-1c89-4c33-9901-6dcdd626be35 · outbound

This paper cites Flowse-grpo: Training flow matching speech enhancement via online reinforcement learning.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Flowse-grpo: Training flow matching speech enhancement via online reinforcement learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:20.803917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47fae71c-f098-495a-aa25-a922088cebd3 · outbound

This paper cites Flowtts-grpo: Online reinforcement learning with multi-objective reward optimization for flow-matching based text-to-speech, 2026.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Flowtts-grpo: Online reinforcement learning with multi-objective reward optimization for flow-matching based text-to-speech, 2026

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:20.947217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd24275a-1d06-41b5-b55f-731b81c0b864 · outbound

This paper cites RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Music.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Music

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:21.023292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bd7bbfe-c7be-4c12-958e-9c1fd44cbe4a · outbound

This paper cites SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:21.142293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e20899c9-182f-4ab3-a1c9-3040479f2f34 · outbound

This paper cites Mucodec: Ultra low-bitrate music codec for music generation.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Mucodec: Ultra low-bitrate music codec for music generation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:21.220014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d6c1eaa-769f-46a2-b220-4d9e21c9c48f · outbound

This paper cites Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:21.329645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c09a726-b2b2-45c2-9880-1d469f991d87 · outbound

This paper cites Songbloom: Coherent song generation via interleaved autoregressive sketching and diffusion refinement.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Songbloom: Coherent song generation via interleaved autoregressive sketching and diffusion refinement

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:21.422952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8038b852-6a47-4c4c-b062-81309a52f6c6 · outbound

This paper cites HeartMuLa: A Family of Open Sourced Music Foundation Models.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering HeartMuLa: A Family of Open Sourced Music Foundation Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:21.505367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0becebc9-d2e8-4ce0-8b4f-e6aa50428043 · outbound

This paper cites SongEval: A Benchmark Dataset for Song Aesthetics Evaluation.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering SongEval: A Benchmark Dataset for Song Aesthetics Evaluation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:21.592941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b334e699-ae91-4e7c-a3a3-5f6203f96858 · outbound

This paper cites Yue: Scaling open foundation models for long-form music generation.arXiv preprint arXiv:2503.08638, 2025.

Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering Yue: Scaling open foundation models for long-form music generation.arXiv preprint arXiv:2503.08638, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T10:24:21.848332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 653a5994-2993-48f7-b883-9e9841a1efaa · inbound

Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation cites this paper.

Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering

Reference 36

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T14:47:18.310080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.