{"as_of":"2026-08-08T07:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:25a4c156879e834a2a397546cbe759ccf6ba4d5e4485cf2aa29e0fa0eed0c2e5","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":12,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:41:21.200157Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.04320","snapshot_observed_at":"2026-08-07T12:41:21.200157Z","title":"Conceptattention: Diffu- sion transformers learn highly interpretable features.arXiv preprint arXiv:2502.04320, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.23758","last_updated":"2025-05-29T17:59:46Z","snapshot_observed_at":"2026-08-07T12:36:05.716723Z","submitted_at":"2025-05-29T17:59:46Z","title":"LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T12:41:21.200157Z"},"links":{"cited_paper":"/paper/2502.04320","citing_paper":"/paper/2505.23758"},"observation_digest":"sha256:93e0313596d13a8d650a9f8bf0cfccb522e40cd1b9c99d4f4021edfa8cad84a9","observation_id":"233f2121-ba18-4444-9534-6a742e222961","resolution":{"observed_at":"2026-08-07T12:41:21.200157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.04320","snapshot_observed_at":"2026-08-07T05:41:31.024475Z","title":"Conceptattention: Diffusion transformers learn highly interpretable features.CoRR, abs/2502.04320, February 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.07280","last_updated":"2025-06-10T11:37:10Z","snapshot_observed_at":"2026-08-07T10:25:31.097897Z","submitted_at":"2025-06-08T20:52:34Z","title":"From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T05:41:31.024475Z"},"links":{"cited_paper":"/paper/2502.04320","citing_paper":"/paper/2506.07280"},"observation_digest":"sha256:00bb14086e6bdb259f0ecda74269df5dc57a26e79d9c6ad27523943361f65cd8","observation_id":"e5d4b584-b4d5-4ec3-9d37-32aeef6aa1bb","resolution":{"observed_at":"2026-08-07T05:41:31.024475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","version":2},"cited_work":{"arxiv_id":"2502.04320","doi":"10.48550/arxiv.2502.04320","metadata_source":"arxiv_reference","pith_arxiv_id":"2502.04320","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Con- ceptattention: Diffusion transformers learn highly inter- pretable features","venue":"ArXiv.org","work_id":"f5715b3d-4e8a-459a-b8b2-901eb2f0fe8e","year":2025},"citing_paper":{"arxiv_id":"2507.23313","last_updated":"2025-07-31T07:47:01Z","snapshot_observed_at":"2026-08-02T09:25:05.244128Z","submitted_at":"2025-07-31T07:47:01Z","title":"The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-21T23:41:50.534434Z"},"links":{"cited_paper":"/paper/2502.04320","citing_paper":"/paper/2507.23313"},"observation_digest":"sha256:d228727a506f1df8cf808377c01d66e122d78a223f056e71f675f6667d6e4735","observation_id":"e373986a-7abc-4b74-a3b0-20d237a9dc01","resolution":{"observed_at":"2026-05-21T23:44:26.945529Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.04320","snapshot_observed_at":"2026-08-05T13:27:41.569139Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.05323","last_updated":"2025-09-09T12:40:17Z","snapshot_observed_at":"2026-08-08T04:22:53.365053Z","submitted_at":"2025-08-30T19:46:18Z","title":"Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArts","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T13:27:41.569139Z"},"links":{"cited_paper":"/paper/2502.04320","citing_paper":"/paper/2509.05323"},"observation_digest":"sha256:35378bd1a4d6101e33336e1bfa4cfd4a7bbe2b5ca5aec7ccc8d2c4d0ca468981","observation_id":"8e151f58-cd7c-4cf5-925e-a8d75f068994","resolution":{"observed_at":"2026-08-05T13:27:41.569139Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.04320","snapshot_observed_at":"2026-08-04T08:19:59.521627Z","title":"Conceptattention: Diffusion transformers learn highly interpretable features, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.21605","last_updated":"2026-06-17T16:14:08Z","snapshot_observed_at":"2026-08-06T00:04:26.344716Z","submitted_at":"2025-10-24T16:10:09Z","title":"S3OD: Towards Generalizable Salient Object Detection with Synthetic Data","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T08:19:59.521627Z"},"links":{"cited_paper":"/paper/2502.04320","citing_paper":"/paper/2510.21605"},"observation_digest":"sha256:19e6a3bba791e01297ce0c7364d61e3403f7e927769785e2887c589d9b59bb42","observation_id":"286c8497-c10b-40f7-8d9c-569fb466ffb7","resolution":{"observed_at":"2026-08-04T08:19:59.521627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","version":2},"cited_work":{"arxiv_id":"2502.04320","doi":"10.48550/arxiv.2502.04320","metadata_source":"arxiv_reference","pith_arxiv_id":"2502.04320","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Con- ceptattention: Diffusion transformers learn highly inter- pretable features","venue":"ArXiv.org","work_id":"f5715b3d-4e8a-459a-b8b2-901eb2f0fe8e","year":2025},"citing_paper":{"arxiv_id":"2604.19473","last_updated":"2026-04-21T13:56:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-21T13:56:36Z","title":"TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-10T02:45:10.577070Z"},"links":{"cited_paper":"/paper/2502.04320","citing_paper":"/paper/2604.19473"},"observation_digest":"sha256:6c500b2f5071ef75b03385521f7f6bcef3ea65c78bb1d6871ef9c1c44955213e","observation_id":"014dd85b-2817-4cc2-be1c-e2a8fccbdcff","resolution":{"observed_at":"2026-05-10T02:53:29.908134Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","version":2},"cited_work":{"arxiv_id":"2502.04320","doi":"10.48550/arxiv.2502.04320","metadata_source":"arxiv_reference","pith_arxiv_id":"2502.04320","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Con- ceptattention: Diffusion transformers learn highly inter- pretable features","venue":"ArXiv.org","work_id":"f5715b3d-4e8a-459a-b8b2-901eb2f0fe8e","year":2025},"citing_paper":{"arxiv_id":"2604.23786","last_updated":"2026-07-17T17:17:29Z","snapshot_observed_at":"2026-08-02T15:32:57.242948Z","submitted_at":"2026-04-26T16:22:39Z","title":"FAIR_XAI: Improving Multimodal Foundation Model Fairness via Explainability for Wellbeing Assessment","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-08T06:16:59.725843Z"},"links":{"cited_paper":"/paper/2502.04320","citing_paper":"/paper/2604.23786"},"observation_digest":"sha256:90240e21c3fb8803e4ee9db317651d0a8dce24874f68255c58972b60ec5f0c97","observation_id":"fe15ad0f-f369-4514-aa9c-f95023a90daa","resolution":{"observed_at":"2026-05-11T21:16:12.253353Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.04320","snapshot_observed_at":"2026-08-02T15:32:58.066814Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.23786","last_updated":"2026-07-17T17:17:29Z","snapshot_observed_at":"2026-08-02T15:32:57.242948Z","submitted_at":"2026-04-26T16:22:39Z","title":"FAIR_XAI: Improving Multimodal Foundation Model Fairness via Explainability for Wellbeing Assessment","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T15:32:58.066814Z"},"links":{"cited_paper":"/paper/2502.04320","citing_paper":"/paper/2604.23786"},"observation_digest":"sha256:f1966291fc5e802fb2284ee64ce96bcd8864a3474991f4cdb5a329270964c06b","observation_id":"26316507-ecd0-4158-ae13-55a10d372608","resolution":{"observed_at":"2026-08-02T15:32:58.066814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","version":2},"cited_work":{"arxiv_id":"2502.04320","doi":"10.48550/arxiv.2502.04320","metadata_source":"arxiv_reference","pith_arxiv_id":"2502.04320","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Con- ceptattention: Diffusion transformers learn highly inter- pretable features","venue":"ArXiv.org","work_id":"f5715b3d-4e8a-459a-b8b2-901eb2f0fe8e","year":2025},"citing_paper":{"arxiv_id":"2605.07907","last_updated":"2026-05-08T15:45:34Z","snapshot_observed_at":"2026-07-06T23:20:15.696237Z","submitted_at":"2026-05-08T15:45:34Z","title":"Consistency Regularised Gradient Flows for Inverse Problems","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-05-11T03:21:35.082352Z"},"links":{"cited_paper":"/paper/2502.04320","citing_paper":"/paper/2605.07907"},"observation_digest":"sha256:e542114c172f76ea68cc375f0ffebde09aaa5e496885cabb8a283b6f00e4b265","observation_id":"1e0e87f6-6282-4654-a044-369e679d2a9a","resolution":{"observed_at":"2026-05-11T03:25:55.059096Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","version":2},"cited_work":{"arxiv_id":"2502.04320","doi":"10.48550/arxiv.2502.04320","metadata_source":"arxiv_reference","pith_arxiv_id":"2502.04320","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Con- ceptattention: Diffusion transformers learn highly inter- pretable features","venue":"ArXiv.org","work_id":"f5715b3d-4e8a-459a-b8b2-901eb2f0fe8e","year":2025},"citing_paper":{"arxiv_id":"2605.10180","last_updated":"2026-05-11T08:31:57Z","snapshot_observed_at":"2026-08-01T15:31:49.304094Z","submitted_at":"2026-05-11T08:31:57Z","title":"What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-12T04:35:39.370969Z"},"links":{"cited_paper":"/paper/2502.04320","citing_paper":"/paper/2605.10180"},"observation_digest":"sha256:da3fda9f239a9885c46aeb60cb4d978e3bcc5f07bbea0115d5d2ff97f6066b0e","observation_id":"b53677f1-09e8-4e1f-b252-47ec5ad2bebb","resolution":{"observed_at":"2026-05-12T06:06:26.433353Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","version":2},"cited_work":{"arxiv_id":"2502.04320","doi":"10.48550/arxiv.2502.04320","metadata_source":"arxiv_reference","pith_arxiv_id":"2502.04320","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Con- ceptattention: Diffusion transformers learn highly inter- pretable features","venue":"ArXiv.org","work_id":"f5715b3d-4e8a-459a-b8b2-901eb2f0fe8e","year":2025},"citing_paper":{"arxiv_id":"2606.06875","last_updated":"2026-06-05T03:43:04Z","snapshot_observed_at":"2026-08-07T19:50:21.203269Z","submitted_at":"2026-06-05T03:43:04Z","title":"Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-27T22:58:44.478077Z"},"links":{"cited_paper":"/paper/2502.04320","citing_paper":"/paper/2606.06875"},"observation_digest":"sha256:3d7e476bc0d054ed5ab55a85aedc87a715f0c8b85f307325fb7b5f5026acf168","observation_id":"794bcc62-c9f1-4579-80ab-8a00799ac7e8","resolution":{"observed_at":"2026-07-02T16:07:09.083615Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.04320","snapshot_observed_at":"2026-08-01T13:25:54.283706Z","title":"Conceptattention: Diffusion transformers learn highly interpretable features.arXiv preprint arXiv:2502.04320, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19139","last_updated":"2026-07-30T16:07:04Z","snapshot_observed_at":"2026-08-03T13:02:29.806237Z","submitted_at":"2026-07-21T14:29:59Z","title":"Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T13:25:54.283706Z"},"links":{"cited_paper":"/paper/2502.04320","citing_paper":"/paper/2607.19139"},"observation_digest":"sha256:8fa907420fad8ed0ec920c330b19b293177c525863873626bb0da43785b3f306","observation_id":"1c2eb649-ccb4-42b1-a613-5a0adcff069e","resolution":{"observed_at":"2026-08-01T13:25:54.283706Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.04320/citation-record","integrity":"/paper/2502.04320/integrity","json":"/paper/2502.04320/citation-record.json","paper":"/paper/2502.04320"},"outbound":[],"paper":{"arxiv_id":"2502.04320","last_updated":"2025-07-01T20:00:27Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T02:51:36.096592Z","submitted_at":"2025-02-06T18:59:00Z","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 12 inbound Pith citation observations for arXiv:2502.04320."}