{"as_of":"2026-08-13T08:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:14213d1b59bf51d41c3fadf038e1ce96449e55557e88e7a57d6df9346afc37ed","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T17:49:42.644020Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.08549/citation-record","integrity":"/paper/2412.08549/integrity","json":"/paper/2412.08549/citation-record.json","paper":"/paper/2412.08549"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2301.11325","last_updated":"2023-01-26T18:58:53Z","snapshot_observed_at":"2026-08-12T18:49:23.347422Z","submitted_at":"2023-01-26T18:58:53Z","title":"MusicLM: Generating Music From Text","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.11325","snapshot_observed_at":"2026-08-11T17:49:42.493048Z","title":"Denk, Zalán Borsos, Jesse Engel, Mauro Verzetti, Antoine Caillon, Qingqing Huang, Aren Jansen, Adam Roberts, Marco Tagliasacchi, Matt Sharifi, Neil Zeghidour, and Christian Frank","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.493048Z"},"links":{"cited_paper":"/paper/2301.11325","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:3564333cc91daf1ccc3fe20ba7a728312cdd24a535770cf63a0935b942d170c1","observation_id":"6b4fc50c-148d-452d-bd59-0e2c70a3e2bc","resolution":{"observed_at":"2026-08-11T17:49:42.493048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14542","last_updated":"2024-01-25T22:20:42Z","snapshot_observed_at":"2026-08-13T07:33:54.907568Z","submitted_at":"2024-01-25T22:20:42Z","title":"Exploring Musical Roots: Applying Audio Embeddings to Empower Influence Attribution for a Generative Music Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14542","snapshot_observed_at":"2026-08-11T17:49:42.498822Z","title":"Exploring musical roots: Applying audio embeddings to empower influence attribution for a generative music model, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.498822Z"},"links":{"cited_paper":"/paper/2401.14542","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:9977f26693737c61c0f0fbcc900aba03a8a9e0fe5da65289c8a5b17165379a64","observation_id":"e77c646d-161e-4080-94c0-570f7c70ccd4","resolution":{"observed_at":"2026-08-11T17:49:42.498822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.12941","last_updated":"2023-10-19T17:39:02Z","snapshot_observed_at":"2026-08-13T05:45:11.765043Z","submitted_at":"2023-10-19T17:39:02Z","title":"The Foundation Model Transparency Index","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.12941","snapshot_observed_at":"2026-08-11T17:49:42.503886Z","title":"The foundation model transparency index, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.503886Z"},"links":{"cited_paper":"/paper/2310.12941","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:f76eaa7287e5909d19fd9bc9561789ec533e05ba8fbcfdc82f507e45dbd3d7a7","observation_id":"f55a1c4c-707f-48c2-a764-804c6f1d796e","resolution":{"observed_at":"2026-08-11T17:49:42.503886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:42.508901Z","title":"Membership inference attacks from first principles","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.508901Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:dd9125430d322cf44c1a83b72c14aee2573e87527d029099f7b31a684a2e1c92","observation_id":"72974984-af44-4359-b1f4-081815b6dda0","resolution":{"observed_at":"2026-08-11T17:49:42.508901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:43.234418Z","title":"The secret sharer: Evaluating and testing unintended memorization in neural networks","venue":null,"work_id":"1025537d-2039-4f51-ade9-a0e655be4da1","year":2019},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.514050Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:df3b8b340eac7922c5c974765e7bff19de056554ad9ac03c294df804e4cde89b","observation_id":"d1aa6627-8508-4aa4-ba03-fab83f4d81c3","resolution":{"observed_at":"2026-08-11T17:49:43.239823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:42.518790Z","title":"Extracting training data from diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.518790Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:52d116e13c02ced7bdddc29b018d9a0ec6d625b3e7fb8f311f61527340fb02a7","observation_id":"d384d416-f36a-47f7-bafc-559860d3de46","resolution":{"observed_at":"2026-08-11T17:49:42.518790Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12770","last_updated":"2024-01-07T07:05:37Z","snapshot_observed_at":"2026-07-06T16:09:59.750388Z","submitted_at":"2023-08-24T13:17:35Z","title":"WavMark: Watermarking for Audio Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12770","snapshot_observed_at":"2026-08-11T17:49:42.523782Z","title":"Wavmark: Watermarking for audio generation, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.523782Z"},"links":{"cited_paper":"/paper/2308.12770","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:7bded6715afead9a6f8c55ecda200a79cc18114bc4a0d5ab0fa983681e553896","observation_id":"74cc6489-2926-4a80-88a0-a7c43c7c6dfe","resolution":{"observed_at":"2026-08-11T17:49:42.523782Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:43.210631Z","title":"Simple and controllable music generation.Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":"3c585d6a-dc3e-4e54-b6f1-dad00c1a2669","year":2024},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.528428Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:a1f95a68f40fe6e304e632d16d6895c57cda3a22405e26e747c68987512e9686","observation_id":"842e10d4-237e-4195-897f-144f26e8fafb","resolution":{"observed_at":"2026-08-11T17:49:43.215446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:43.196511Z","title":"drake” and “the weeknd","venue":null,"work_id":"b500786e-7513-459e-9bae-11d117c09245","year":2023},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.532459Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:94c268ce90635119bc9135831b6cdec94d5a741144784f98edf86d15045c0dbd","observation_id":"cda9306e-a24b-479b-8603-ca2444a1d2ad","resolution":{"observed_at":"2026-08-11T17:49:43.201210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.12867","last_updated":"2020-04-27T15:23:42Z","snapshot_observed_at":"2026-07-31T15:28:04.059683Z","submitted_at":"2020-04-27T15:23:42Z","title":"The Accuracy of Restricted Boltzmann Machine Models of Ising Systems","version":1},"cited_work":{"arxiv_id":"2004.12867","doi":null,"metadata_source":"pith","pith_arxiv_id":"2004.12867","snapshot_observed_at":"2026-08-11T17:49:42.933159Z","title":"The Accuracy of Restricted Boltzmann Machine Models of Ising Systems","venue":"physics.comp-ph","work_id":"f61ebefe-e33d-4562-b6fb-0997bb4b63d5","year":2020},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.537724Z"},"links":{"cited_paper":"/paper/2004.12867","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:d0394cf5a3649fc0388f658f2b18dd35692236d9914ff82fa911ecff7eef44f1","observation_id":"71efc51c-b708-43d3-8d2b-1343d35cf49e","resolution":{"observed_at":"2026-08-11T17:49:42.939012Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16201","last_updated":"2025-03-30T08:39:32Z","snapshot_observed_at":"2026-08-12T23:36:36.745844Z","submitted_at":"2024-06-23T19:40:11Z","title":"Blind Baselines Beat Membership Inference Attacks for Foundation Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.16201","snapshot_observed_at":"2026-08-11T17:49:42.541917Z","title":"Blind baselines beat membership inference attacks for foundation models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.541917Z"},"links":{"cited_paper":"/paper/2406.16201","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:c232167c6c392b604193c2f778c9cbf4192fe7de7fbeef79f964f488806d5902","observation_id":"53bf9283-ae66-43c5-8a06-9fb49b60fac5","resolution":{"observed_at":"2026-08-11T17:49:42.541917Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:43.181509Z","title":"Oliveira, and Lei Li","venue":null,"work_id":"04d42997-69e4-4943-8a7e-94a498932ab2","year":2024},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.546100Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:4c3f685284f56904fc10b099cac2cbbb3458511fd286730b8a1743b22ab89be5","observation_id":"14e4452b-ea1c-45cc-beae-ca09d3d58b21","resolution":{"observed_at":"2026-08-11T17:49:43.186658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.13438","last_updated":"2022-10-24T17:52:02Z","snapshot_observed_at":"2026-08-09T07:12:13.721596Z","submitted_at":"2022-10-24T17:52:02Z","title":"High Fidelity Neural Audio Compression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.13438","snapshot_observed_at":"2026-08-11T17:49:42.550671Z","title":"High fidelity neural audio compression, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.550671Z"},"links":{"cited_paper":"/paper/2210.13438","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:9e5845ff7a4b3a0494e1501fb2db0708c8a6f7acb9295b824dda1b9846458902","observation_id":"99fb7e17-010c-43dd-ad92-c7e33690bdcf","resolution":{"observed_at":"2026-08-11T17:49:42.550671Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04686","last_updated":"2023-07-12T17:06:41Z","snapshot_observed_at":"2026-08-12T02:08:45.241329Z","submitted_at":"2023-07-10T16:42:03Z","title":"VampNet: Music Generation via Masked Acoustic Token Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.04686","snapshot_observed_at":"2026-08-11T17:49:42.555192Z","title":"Vampnet: Music generation via masked acoustic token modeling, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.555192Z"},"links":{"cited_paper":"/paper/2307.04686","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:a646852737b2e932ccfb2eb98a4728cdd5033ee99fc5c8ef5b4d7681d37730ce","observation_id":"79c9ba49-fd6c-4aa0-9051-3c09f957c784","resolution":{"observed_at":"2026-08-11T17:49:42.555192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:43.166837Z","title":"Beyonce and adele publisher accuses firms of training ai on songs, 5 2024","venue":null,"work_id":"87a151a5-4f64-45bf-959e-206e8db7648a","year":2024},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.559809Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:c4611d0d724e51852e6233b5dab1f38b61583d4a97e9ce33fa73739fbd1ec6b9","observation_id":"c2c079d5-4f31-486e-a9cf-d31c5f05f356","resolution":{"observed_at":"2026-08-11T17:49:43.171226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:42.564085Z","title":"Cnn architectures for large-scale audio classification","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.564085Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:274ffce475ab31dc791b11c1dae1d893cd9317d5146be1a9baa94164871711c7","observation_id":"c60cd0b0-d033-4a6b-b28e-cf6e3479a24b","resolution":{"observed_at":"2026-08-11T17:49:42.564085Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:42.568425Z","title":"Deduplicating training data mitigates privacy risks in language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.568425Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:04a929c70786f8f8ca8bb162bc91d4c59b4a09251e6b0848c098221d54914c97","observation_id":"307249fa-1126-49ff-b5d9-98f6b22d93e6","resolution":{"observed_at":"2026-08-11T17:49:42.568425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.08466","last_updated":"2019-01-17T16:12:43Z","snapshot_observed_at":"2026-08-08T16:07:44.435146Z","submitted_at":"2018-12-20T10:28:00Z","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.08466","snapshot_observed_at":"2026-08-11T17:49:42.572599Z","title":"Fréchet audio distance: A metric for evaluating music enhancement algorithms, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.572599Z"},"links":{"cited_paper":"/paper/1812.08466","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:33755fcb71a692cf8aa47ade126f8ed869ace4f5289f81701558f2c07f508a85","observation_id":"4715ead8-532b-4910-83b6-6a049752cac8","resolution":{"observed_at":"2026-08-11T17:49:42.572599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2003.80938","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:42.838256Z","title":"Spread-spectrum watermarking of audio","venue":null,"work_id":"c2be2afd-92d6-493a-b00f-a7a041341049","year":2003},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.577177Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:eef3413a63f21b95db7950692dc437728d470b73bb34dc3fc73d3d78a087074a","observation_id":"2c8c330e-7ff4-43fc-ad6f-7aa86c472e58","resolution":{"observed_at":"2026-08-11T17:49:42.848840Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:43.130771Z","title":"Us record labels sue ai music generators suno and udio for copyright infringement, 6 2024","venue":null,"work_id":"5fa1844e-fcfc-40bf-9752-7d837f2e96a9","year":2024},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.581647Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:658d5ddf5b3652f7033fb4fd2d8fc18b4c973073148a029bf8825fea2c25135f","observation_id":"eef78128-14a6-4b2f-9f57-b24eae8f1c56","resolution":{"observed_at":"2026-08-11T17:49:43.135861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.06546","last_updated":"2023-10-26T22:17:49Z","snapshot_observed_at":"2026-07-06T15:41:13.274608Z","submitted_at":"2023-06-11T00:13:00Z","title":"High-Fidelity Audio Compression with Improved RVQGAN","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.06546","snapshot_observed_at":"2026-08-11T17:49:42.586137Z","title":"High-fidelity audio compression with improved rvqgan, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.586137Z"},"links":{"cited_paper":"/paper/2306.06546","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:0d682916f3bfea6432567e4e5267526b5e4aab27727136acd7bde8c309df69c9","observation_id":"eb938b15-2c87-467d-814e-7b3490621349","resolution":{"observed_at":"2026-08-11T17:49:42.586137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:43.114510Z","title":"Copyright traps for large language models","venue":null,"work_id":"361a1119-1ac4-460a-bfab-28a8ae6323f0","year":2024},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.590864Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:9d2a253ccb2a9d1a47fa6e7fb5d45fec6b9e09c1183a66c18ff310e2baec4767","observation_id":"0af0fffd-21f7-489e-95d5-0a9d131b6fac","resolution":{"observed_at":"2026-08-11T17:49:43.119201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.17975","last_updated":"2025-03-07T16:30:07Z","snapshot_observed_at":"2026-08-12T23:34:54.039125Z","submitted_at":"2024-06-25T23:12:07Z","title":"SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.17975","snapshot_observed_at":"2026-08-11T17:49:42.595502Z","title":"Sok: Membership inference attacks on llms are rushing nowhere (and how to fix it), 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.595502Z"},"links":{"cited_paper":"/paper/2406.17975","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:ed18eac44c871ba7eae1df56315bcf073a79a533bb7a4df697018ede6cd8b69a","observation_id":"df123b63-996c-4378-a84c-7fb2e9685ec7","resolution":{"observed_at":"2026-08-11T17:49:42.595502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:43.098707Z","title":"An empirical analysis of memorization in fine-tuned autoregressive language models","venue":null,"work_id":"e0c046e2-a239-492c-91dc-068a22762a01","year":2022},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.600068Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:86be1f503ae9ae9b7464bbab226d24c96a540b5a8373ae8e41b2429e22230feb","observation_id":"ccfeb941-96af-4616-8150-de5f2670dd91","resolution":{"observed_at":"2026-08-11T17:49:43.103573Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.17035","last_updated":"2023-11-28T18:47:03Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-11-28T18:47:03Z","title":"Scalable Extraction of Training Data from (Production) Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.17035","snapshot_observed_at":"2026-08-11T17:49:42.604514Z","title":"Feder Cooper, Daphne Ippolito, Christopher A","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.604514Z"},"links":{"cited_paper":"/paper/2311.17035","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:97bdce4543e348117a1fc14405e4be6314a45ea8549109abfaf3723001ad4433","observation_id":"8fe65e3c-d85a-4ba1-924e-ae7707f3d4bb","resolution":{"observed_at":"2026-08-11T17:49:42.604514Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:43.080940Z","title":"Neuroscience","venue":null,"work_id":"774cf41a-88df-47bf-a026-1d13ea5f9f70","year":2001},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.608890Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:15228915a1fce8ce4a6886f1f3b58334ac573401b7c9f1fdf3e3e9d8fabacf82","observation_id":"f123f29a-ae1c-4520-9dbe-625ab934b436","resolution":{"observed_at":"2026-08-11T17:49:43.087022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:43.065854Z","title":"Radioactive data: tracing through training","venue":null,"work_id":"5c97c724-7258-4f43-b0a9-82cced86bfa7","year":2020},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.613154Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:47ebb9247e7fc00e845b15fc8f703ca38cfa290581735f11ca566100021ea49f","observation_id":"b68656ff-c954-4223-885a-0974d9112536","resolution":{"observed_at":"2026-08-11T17:49:43.070458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:43.049517Z","title":"Proactive detection of voice cloning with localized watermarking","venue":null,"work_id":"17d1432f-9cff-4305-b299-15702201d2b2","year":2024},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.617454Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:184d534e7a3009c74649262e67239a130d3137cfc43d43166a5bd9927ab1fb02","observation_id":"a613d2c7-bd8d-4df8-b9ce-9f991142d1f6","resolution":{"observed_at":"2026-08-11T17:49:43.054870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:42.622035Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.622035Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:58e17f3d22979dad0f4a436075a20165e7d3b64fb0d6e1920b8832a5655fd0eb","observation_id":"69c31db6-ee10-4f7f-85fd-38deee4f91d8","resolution":{"observed_at":"2026-08-11T17:49:42.622035Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.03860","last_updated":"2022-12-12T18:52:13Z","snapshot_observed_at":"2026-08-12T10:19:39.853027Z","submitted_at":"2022-12-07T18:58:02Z","title":"Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.03860","snapshot_observed_at":"2026-08-11T17:49:42.626494Z","title":"Diffusion art or digital forgery? investigating data replication in diffusion models, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.626494Z"},"links":{"cited_paper":"/paper/2212.03860","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:91a7913ca61ec779ec698849394e4f38fc7ac04a3f02a72588d0ac0d8cd6946c","observation_id":"98925e5f-ef38-4f5a-b144-caa5fa8e11b8","resolution":{"observed_at":"2026-08-11T17:49:42.626494Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.20086","last_updated":"2023-05-31T17:58:02Z","snapshot_observed_at":"2026-08-05T07:34:02.814882Z","submitted_at":"2023-05-31T17:58:02Z","title":"Understanding and Mitigating Copying in Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.20086","snapshot_observed_at":"2026-08-11T17:49:42.631137Z","title":"Understanding and mitigating copying in diffusion models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.631137Z"},"links":{"cited_paper":"/paper/2305.20086","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:d0e0e0b5d7f7d57d351551e6789defcbe9132a981566d188e00e3b048efb9573","observation_id":"008dd644-b76e-4192-a6ea-30db9354e809","resolution":{"observed_at":"2026-08-11T17:49:42.631137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:42.636010Z","title":"Machine learning models that remember too much","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.636010Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:62164515190c70f896fd23fefe7661ede41df2e8f92c5c2a339e0fc28eea071f","observation_id":"f89619cb-0bd7-4fa8-a6fa-fc233740f2d9","resolution":{"observed_at":"2026-08-11T17:49:42.636010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03108","last_updated":"2024-04-09T16:31:33Z","snapshot_observed_at":"2026-08-03T13:51:10.982372Z","submitted_at":"2023-07-06T16:27:39Z","title":"DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.03108","snapshot_observed_at":"2026-08-11T17:49:42.639842Z","title":"Metaxas, and Shiqing Ma","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.639842Z"},"links":{"cited_paper":"/paper/2307.03108","citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:04a22c6952c877705df81fbacb991be1b0162e68eac0821802db2e646f2e7cfa","observation_id":"4f277eb8-4e0d-4b5d-8a75-36c50b8b621a","resolution":{"observed_at":"2026-08-11T17:49:42.639842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:49:43.011933Z","title":"Enhanced membership inference attacks against machine learning models","venue":null,"work_id":"f50e67e2-5f41-4c2d-9a7f-f777dec5c845","year":2022},"citing_paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T17:49:42.644020Z"},"links":{"citing_paper":"/paper/2412.08549"},"observation_digest":"sha256:24033f713edfcbc35727b2c35ae15fe413cc92dbc29fc52f3a2ef828dbcda983","observation_id":"3985e18b-1eb5-4a38-be99-f777f4bc8ed1","resolution":{"observed_at":"2026-08-11T17:49:43.017701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.08549","last_updated":"2024-12-12T10:49:10Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T04:51:14.349486Z","submitted_at":"2024-12-11T17:10:44Z","title":"Watermarking Training Data of Music Generation Models"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":20,"verified_exact":1,"verified_fuzzy":11},"total_outbound_references":34},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2412.08549."}