{"as_of":"2026-08-18T19:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:146c7e8c3c6754f9a63cd3433ab79ced0b545d8a301b2abc64e1d7d030e1bdba","coverage":[{"denominator":142,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:33:25.803378Z","state":"measured"},{"denominator":102,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":102,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-02T19:25:12.921892Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T19:27:18.513044Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"cited_work":{"arxiv_id":"2506.19708","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.19708","snapshot_observed_at":"2026-07-02T19:27:18.513044Z","title":"arXiv preprint arXiv:2506.19708 , year =","venue":null,"work_id":"d8a55527-ac45-4c3f-b5dd-5f6aa225d30e","year":2025},"citing_paper":{"arxiv_id":"2605.05115","last_updated":"2026-05-06T16:46:03Z","snapshot_observed_at":"2026-08-07T10:12:24.411121Z","submitted_at":"2026-05-06T16:46:03Z","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","version":1},"reference_index":197,"source":"arxiv_source","source_observed_at":"2026-05-08T17:47:09.591001Z"},"links":{"cited_paper":"/paper/2506.19708","citing_paper":"/paper/2605.05115"},"observation_digest":"sha256:95f60a7857e2584f1e66d87646d4b2bbc24b5f21c37d0ca22d312d3b6a56004e","observation_id":"619b9bfd-1a9f-4e6a-91e4-decac851353f","resolution":{"observed_at":"2026-05-11T17:16:07.133848Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"cited_work":{"arxiv_id":"2506.19708","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.19708","snapshot_observed_at":"2026-07-02T19:27:18.513044Z","title":"arXiv preprint arXiv:2506.19708 , year =","venue":null,"work_id":"d8a55527-ac45-4c3f-b5dd-5f6aa225d30e","year":2025},"citing_paper":{"arxiv_id":"2607.00183","last_updated":"2026-06-30T20:57:51Z","snapshot_observed_at":"2026-08-16T14:26:34.355273Z","submitted_at":"2026-06-30T20:57:51Z","title":"DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-02T19:25:12.921892Z"},"links":{"cited_paper":"/paper/2506.19708","citing_paper":"/paper/2607.00183"},"observation_digest":"sha256:76f5f01ed62c8860ebc45f556c49229068a6498be972a58cf8961775006a3375","observation_id":"dd582318-4a1a-4f8a-9d57-949adcb4198e","resolution":{"observed_at":"2026-07-02T19:27:18.514295Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.19708/citation-record","integrity":"/paper/2506.19708/integrity","json":"/paper/2506.19708/citation-record.json","paper":"/paper/2506.19708"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:33:22.477040Z","title":"Sora: Creating video from text, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.477040Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:cda70db39c3906c4298fd8142dfba4aeb95acd127a6b4067460a74afbd218dc7","observation_id":"482a1999-05f5-455d-a698-e15895792ca2","resolution":{"observed_at":"2026-08-15T18:33:22.477040Z","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":"2026-08-15T18:33:22.596245Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.596245Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:98a5017387e66a037c1592ee945fba1ca313395a2af71d5c8815c734f5c20159","observation_id":"097c51b4-4b52-437c-8279-2b03ec7f035b","resolution":{"observed_at":"2026-08-15T18:33:22.596245Z","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":"2026-08-15T18:33:22.636395Z","title":"Zero-shot text-to-image generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.636395Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:a4b7e13e8a9f0baa6188a44d205ee2a0d52446b0b9f3024e233878e24a002785","observation_id":"53325ac9-28d7-416b-a2c3-e34f1bdb750f","resolution":{"observed_at":"2026-08-15T18:33:22.636395Z","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":"2026-08-15T18:33:22.675389Z","title":"Photorealistic text-to-image diffusion models with deep language understanding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.675389Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:d552275e0388455868d26458825c9f8118b97b2569be38f54c7619b8263280af","observation_id":"5943a50c-58e7-4a0b-9140-f52b3e659be9","resolution":{"observed_at":"2026-08-15T18:33:22.675389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.10741","last_updated":"2022-03-08T18:18:49Z","snapshot_observed_at":"2026-08-07T12:21:17.790675Z","submitted_at":"2021-12-20T18:42:55Z","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.10741","snapshot_observed_at":"2026-08-15T18:33:22.688145Z","title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.688145Z"},"links":{"cited_paper":"/paper/2112.10741","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:60ce99cff80fa1ca68cad68132e4fccd0a5b358bf7a70e07fd443f1efaf46ec9","observation_id":"51d635d3-4590-4ed7-b9a7-9879f7f76ad7","resolution":{"observed_at":"2026-08-15T18:33:22.688145Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.20327","last_updated":"2024-08-20T03:54:10Z","snapshot_observed_at":"2026-08-18T15:51:40.772410Z","submitted_at":"2024-05-30T17:58:00Z","title":"GECO: Generative Image-to-3D within a SECOnd","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.20327","snapshot_observed_at":"2026-08-15T18:33:22.694879Z","title":"Geco: Generative image- to-3d within a second","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.694879Z"},"links":{"cited_paper":"/paper/2405.20327","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:352d1ed18f900ba77697b9d068d6ae38cce83af3e8c5bc3d1ec5033bc7cb6a44","observation_id":"32be373c-6b5b-4351-9328-7f3ef2a03463","resolution":{"observed_at":"2026-08-15T18:33:22.694879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.14988","last_updated":"2022-09-29T17:50:40Z","snapshot_observed_at":"2026-07-06T13:57:54.539656Z","submitted_at":"2022-09-29T17:50:40Z","title":"DreamFusion: Text-to-3D using 2D Diffusion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.14988","snapshot_observed_at":"2026-08-15T18:33:22.702017Z","title":"Dreamfusion: Text-to-3d using 2d diffusion","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.702017Z"},"links":{"cited_paper":"/paper/2209.14988","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:eadf9c3cda6c093162aca7d3272ac7fd1c31944498a992f137bc3e5236037d6a","observation_id":"cd7630b7-2605-4b14-9cd6-01ea20fcff77","resolution":{"observed_at":"2026-08-15T18:33:22.702017Z","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":"2026-08-15T18:33:22.743271Z","title":"Texture: Text-guided texturing of 3d shapes","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.743271Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:a00493f2071ccf6d4199c509f829833a559f1f45132f0517b8238e0bae60845d","observation_id":"fedaefb3-01a6-4ca5-97be-a63da88d2114","resolution":{"observed_at":"2026-08-15T18:33:22.743271Z","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":"2026-08-15T18:33:22.822752Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.822752Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:0fb19470dd91fa1df53423b5ac0296ea766170cfb832a0d9827b6aa662a8f8ff","observation_id":"f1c521b8-f241-4a09-8270-c3978692abb6","resolution":{"observed_at":"2026-08-15T18:33:22.822752Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.01691","last_updated":"2022-08-16T16:06:33Z","snapshot_observed_at":"2026-08-18T11:44:22.813405Z","submitted_at":"2022-04-04T17:57:11Z","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.01691","snapshot_observed_at":"2026-08-15T18:33:22.872363Z","title":"Do as i can, not as i say: Grounding language in robotic affordances","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.872363Z"},"links":{"cited_paper":"/paper/2204.01691","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:392c8492d7c82418ecd3226f66d982908cfbe494e6b4aedb543b8dd0b89c5d0b","observation_id":"07ee73d6-6c8c-44ae-873d-142a9333441e","resolution":{"observed_at":"2026-08-15T18:33:22.872363Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.05608","last_updated":"2022-07-12T15:20:48Z","snapshot_observed_at":"2026-08-17T09:42:08.942018Z","submitted_at":"2022-07-12T15:20:48Z","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.05608","snapshot_observed_at":"2026-08-15T18:33:22.892187Z","title":"Inner monologue: Embodied reasoning through planning with language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.892187Z"},"links":{"cited_paper":"/paper/2207.05608","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:44d31cf3e206ec6a1538fffe48678ba49ae43be633c66b208de06c0c9c14c91a","observation_id":"7464c206-802b-4b05-b288-b5c8dcd29e57","resolution":{"observed_at":"2026-08-15T18:33:22.892187Z","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":"2026-08-15T18:33:22.898729Z","title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.898729Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:711385950ac9dc634ac265765040e4c6798fa34ef4ea0f69582167789e510e4e","observation_id":"203e24c2-406a-4292-8474-040b2e296d34","resolution":{"observed_at":"2026-08-15T18:33:22.898729Z","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":"2026-08-15T18:33:22.904222Z","title":"Text-guided controllable mesh refinement for interactive 3d modeling","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.904222Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:6d5a0c8f68cf2253b6ee47a7c2a1180095b2a828c6bcafee026c8c70498bd9d6","observation_id":"4e36853f-070a-468d-93a2-c283c486f18f","resolution":{"observed_at":"2026-08-15T18:33:22.904222Z","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":"2026-08-15T18:33:22.910423Z","title":"Smoodi: Stylized motion diffusion model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.910423Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:087f6d00a9be5f35cb6b09bc97131d409715b82abbf39ab530a76a81c0c54e34","observation_id":"10f5f498-774e-45c4-b906-76e0df7b4d24","resolution":{"observed_at":"2026-08-15T18:33:22.910423Z","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":"2026-08-15T18:33:22.916259Z","title":"Meshgpt: Generating triangle meshes with decoder-only transformers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:22.916259Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:c757d7cc2509e4d52680b48fee5cb18baa31266af85a4349ed5541d730bedb90","observation_id":"50647a37-f5f5-43db-87f9-f26e91d2f09f","resolution":{"observed_at":"2026-08-15T18:33:22.916259Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.13807","last_updated":"2022-05-02T19:35:26Z","snapshot_observed_at":"2026-08-16T17:04:41.030388Z","submitted_at":"2022-04-25T18:54:39Z","title":"A very preliminary analysis of DALL-E 2","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.13807","snapshot_observed_at":"2026-08-15T18:33:23.000282Z","title":"A very preliminary analysis of dall-e 2.arXiv preprint arXiv:2204.13807, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.000282Z"},"links":{"cited_paper":"/paper/2204.13807","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:02a327fa043dc20e91f0851f4ecf7483359feddd2f188415bcef92e6f8838777","observation_id":"a94a36d2-667e-4d46-861a-a450fe187753","resolution":{"observed_at":"2026-08-15T18:33:23.000282Z","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":"2026-08-15T18:33:23.067556Z","title":"Discovering and validating ai errors with crowdsourced failure reports","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.067556Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:f953b4e70f47990ee9aad93aa394148ccd9c27fc66b353c74d86f1abde32ce86","observation_id":"bf94b759-3514-4d1f-a04c-d5aac5f74637","resolution":{"observed_at":"2026-08-15T18:33:23.067556Z","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":"2026-08-15T18:33:23.112411Z","title":"Generative artificial intelligence in creative contexts: a systematic review and future research agenda","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.112411Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:30a06292963a8b3919202de281b90389af317a3d2d0615cd12683640459433f2","observation_id":"763e0925-04b4-42a8-8bf5-6ca474bec4e6","resolution":{"observed_at":"2026-08-15T18:33:23.112411Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.00974","last_updated":"2023-11-29T21:50:06Z","snapshot_observed_at":"2026-08-16T15:27:22.518960Z","submitted_at":"2023-06-01T17:59:00Z","title":"Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.00974","snapshot_observed_at":"2026-08-15T18:33:23.128482Z","title":"Discovering failure modes of text-guided diffusion models via adversarial search.arXiv preprint arXiv:2306.00974, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.128482Z"},"links":{"cited_paper":"/paper/2306.00974","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:518375a7c8d0f67aa045281b3dbfc881d81819ea06da62cea67812abe1f1b5ee","observation_id":"7239a24b-92c2-4a6f-964b-230c12b39753","resolution":{"observed_at":"2026-08-15T18:33:23.128482Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.17066","last_updated":"2024-11-26T03:06:52Z","snapshot_observed_at":"2026-08-15T20:53:13.565510Z","submitted_at":"2024-11-26T03:06:52Z","title":"Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.17066","snapshot_observed_at":"2026-08-15T18:33:23.136521Z","title":"Relations, negations, and numbers: Looking for logic in generative text-to-image models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.136521Z"},"links":{"cited_paper":"/paper/2411.17066","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:ca47b0c003a20d12ef71be3aa526b155a3a485b7e0c3e46cd6588c00c99d4670","observation_id":"8c8c7bcc-e0ad-405e-b032-af87ffd03753","resolution":{"observed_at":"2026-08-15T18:33:23.136521Z","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":"2026-08-15T18:33:23.176933Z","title":"HandRefiner: Re- fining malformed hands in generated images by diffusion-based conditional inpainting","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.176933Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:085417e06d5f4f7b12db33851e5c85204430bf7c92a05f60b215367a553fa138","observation_id":"9a5801f5-75cc-4e5b-b73a-e33eb3716944","resolution":{"observed_at":"2026-08-15T18:33:23.176933Z","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":"2026-08-15T18:33:23.219023Z","title":"HanDiffuser: Text-to-image generation with realistic hand appearances","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.219023Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:a048fa1b42715a7841117264f611ccf9407aaa5c6f8558ad0134f546f8bc8b79","observation_id":"9355aecc-e75b-4d64-8874-57a32efb0089","resolution":{"observed_at":"2026-08-15T18:33:23.219023Z","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":"2026-08-15T18:33:23.297920Z","title":"Layout-agnostic scene text image synthesis with diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.297920Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:60360c5e0f0cd3f8442e691a37fc789f8f072509d14851efe3f3e24e77ff68b7","observation_id":"22a1ae46-7e84-49e2-981e-9cd6dc223087","resolution":{"observed_at":"2026-08-15T18:33:23.297920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.13730","last_updated":"2025-03-17T21:36:31Z","snapshot_observed_at":"2026-08-16T12:49:11.408067Z","submitted_at":"2025-03-17T21:36:31Z","title":"TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmark","version":1},"cited_work":{"arxiv_id":"2503.13730","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.13730","snapshot_observed_at":"2026-08-15T18:33:28.574272Z","title":"TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmark","venue":"cs.CV","work_id":"14b31401-5511-45d2-8667-b42f68beec8d","year":2025},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.344012Z"},"links":{"cited_paper":"/paper/2503.13730","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:5d23e41872a19199bf59105d829eb378a723279b279c77b4f16ec16fa321ff1b","observation_id":"18efadc1-4b30-4088-856f-8beabf1c8dd6","resolution":{"observed_at":"2026-08-15T18:33:28.631972Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T18:33:23.351542Z","title":"Text-to-image diffusion models cannot count, and prompt refinement cannot help","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.351542Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:d938fa44198b165c273ce8cfcfb13e2e8a611c5573452a201bb4bff9664e0c19","observation_id":"738b6139-8566-4f80-b0fd-7a03ac1ec247","resolution":{"observed_at":"2026-08-15T18:33:23.351542Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.00005","last_updated":"2022-07-29T02:59:38Z","snapshot_observed_at":"2026-08-16T16:42:33.351238Z","submitted_at":"2022-07-29T02:59:38Z","title":"Testing Relational Understanding in Text-Guided Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.00005","snapshot_observed_at":"2026-08-15T18:33:23.358089Z","title":"Testing relational understanding in text-guided image generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.358089Z"},"links":{"cited_paper":"/paper/2208.00005","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:26a53687f1aa60c94a11f5007b3aa2d6dfd8f6577f5b960f3c7a3c0a84d28e73","observation_id":"142b95eb-967f-472d-87c6-685f55ea4239","resolution":{"observed_at":"2026-08-15T18:33:23.358089Z","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":"2026-08-15T18:33:23.364488Z","title":"Blindspot: Hidden biases of good people","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.364488Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:08011882e765dc1dda5c705a0db7a359d07ed64e6180e4506244e4f49769f155","observation_id":"ffeeb73b-ae1e-4be2-9450-fec44fa592e6","resolution":{"observed_at":"2026-08-15T18:33:23.364488Z","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":"2026-08-15T18:33:23.415410Z","title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.415410Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:419a7b7827e99ce0ca5c85225cc6a0634e31d4eb2be5c43bf0f7f7732a5079a0","observation_id":"f488886a-a8cc-498f-a30c-5ac98830754f","resolution":{"observed_at":"2026-08-15T18:33:23.415410Z","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":"2026-08-15T18:33:23.500318Z","title":"A study of the evaluation metrics for generative images containing combinational creativity","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.500318Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:08132df165e0cac21ddebfcb820b0ce51fdbd9896471f534a1dbc465be71bc54","observation_id":"ab1abbaf-6f03-45bd-b167-cef766eda60e","resolution":{"observed_at":"2026-08-15T18:33:23.500318Z","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":"2026-08-15T18:33:23.552184Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.552184Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:5cf42fd2991d7fb4d6cc9aedd3e0016887dfec813c9615311af7ec579a742a70","observation_id":"e42e6034-5890-48f9-bece-42a40141a3eb","resolution":{"observed_at":"2026-08-15T18:33:23.552184Z","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":"2026-08-15T18:33:23.588084Z","title":"Clipscore: A reference-free evaluation metric for image captioning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.588084Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:40489fb1f6accf6a6ebe6c83ecbad72fc419eee1ee75e5937481be756426a76d","observation_id":"3a6fb29c-0f5f-4e26-b02f-81519bcaeea2","resolution":{"observed_at":"2026-08-15T18:33:23.588084Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.16171","last_updated":"2024-12-12T10:04:33Z","snapshot_observed_at":"2026-08-17T13:15:40.492502Z","submitted_at":"2024-11-25T08:00:21Z","title":"Image Generation Diversity Issues and How to Tame Them","version":2},"cited_work":{"arxiv_id":"2411.16171","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.16171","snapshot_observed_at":"2026-08-15T18:33:28.420573Z","title":"Image Generation Diversity Issues and How to Tame Them","venue":"cs.CV","work_id":"ba35de04-db20-4dfb-a3d2-1c6427941a39","year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.599579Z"},"links":{"cited_paper":"/paper/2411.16171","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:af1269c055bbfff59084922ca061db2d8c9edcc10588621e32a90f84faf26eb3","observation_id":"76d981a2-766b-4e69-85c3-7b5e1a911103","resolution":{"observed_at":"2026-08-15T18:33:28.428735Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T18:33:23.607946Z","title":"Anomaly score: Evaluating generative models and individual generated images based on complexity and vulnerability","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.607946Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:819bd0826834efeb60c968c2608e559d0293fa1120a15ecca056db751b5c34dc","observation_id":"9ab62e29-01b4-4676-bb16-8f6073b271c9","resolution":{"observed_at":"2026-08-15T18:33:23.607946Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.01844","last_updated":"2016-04-24T20:03:35Z","snapshot_observed_at":"2026-08-18T11:21:48.196667Z","submitted_at":"2015-11-05T18:22:44Z","title":"A note on the evaluation of generative models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.01844","snapshot_observed_at":"2026-08-15T18:33:23.614873Z","title":"A note on the evaluation of generative models","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.614873Z"},"links":{"cited_paper":"/paper/1511.01844","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:28f20e81d2d12eed8bb169aae88115338e061a18809ac096f6ecc50965551059","observation_id":"0b1bc46e-dfab-468e-a93d-7bfd06477a69","resolution":{"observed_at":"2026-08-15T18:33:23.614873Z","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":"2026-08-15T18:33:23.622722Z","title":"Reliable fidelity and diversity metrics for generative models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.622722Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:e0bd489f1361047aa93ec63cab3b52f6cd9e63b29c4eace47d575a93ee37ef0b","observation_id":"8328dc55-c33f-4532-95c6-52e2199a18eb","resolution":{"observed_at":"2026-08-15T18:33:23.622722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.12112","last_updated":"2022-11-22T09:27:53Z","snapshot_observed_at":"2026-08-16T16:14:16.127867Z","submitted_at":"2022-11-22T09:27:53Z","title":"Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.12112","snapshot_observed_at":"2026-08-15T18:33:23.673214Z","title":"Human evaluation of text-to-image models on a multi-task benchmark","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.673214Z"},"links":{"cited_paper":"/paper/2211.12112","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:d213d9519265d8efd76fe92d670b893d60290056b9d9b6c4ee3ae45bb2574ba2","observation_id":"8148ee44-c185-445d-adfb-6b4437f0173f","resolution":{"observed_at":"2026-08-15T18:33:23.673214Z","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":"2026-08-15T18:33:23.740755Z","title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.740755Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:26ee9cfa68dc90d719ae4de38f8a5e0c2189883c73a7abe1856765c395221da1","observation_id":"aec9a3bb-2fb0-4ff0-bad6-209fccab286d","resolution":{"observed_at":"2026-08-15T18:33:23.740755Z","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":"2026-08-15T18:33:23.764374Z","title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.764374Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:6268588ffff7a146c4fb69aee391b9b0c7db93bcbdc81c5dd637f314b7b4d634","observation_id":"484dda56-7a7b-4d8e-b40e-61722ff2b054","resolution":{"observed_at":"2026-08-15T18:33:23.764374Z","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":"2026-08-15T18:33:23.772199Z","title":"Seeing what a GAN cannot generate","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.772199Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:d3c98f3a554c663d82c686dfc5a6815c2a813aa0bd16d271cac5ec26f96ce257","observation_id":"96aef2c8-7ba1-45c1-83c3-b73bf3c2e998","resolution":{"observed_at":"2026-08-15T18:33:23.772199Z","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":"2026-08-15T18:33:23.779436Z","title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.779436Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:e6afbd14f1a8a6fcee086d19783a1ecc7efe990521f4d982ab52bd13bcf55998","observation_id":"e3267aa8-e6e2-4e54-a336-ff94c62e1113","resolution":{"observed_at":"2026-08-15T18:33:23.779436Z","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":"2026-08-15T18:33:23.853434Z","title":"Axiomatic attribution for deep networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.853434Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:cb25a9110dec0d8b29ec2f3bcb57f7ee425f9eb894d8267d9df75b19a1279467","observation_id":"f18ce2c4-361a-47be-a929-3ee40f922382","resolution":{"observed_at":"2026-08-15T18:33:23.853434Z","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":"2026-08-15T18:33:23.888453Z","title":"Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.888453Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:b86e3fbfd7ba032bd61786827cc89bb4f82a2931c4527f2e721da532e90b1f94","observation_id":"d23988e4-13a9-4cf3-bb31-326b3c687859","resolution":{"observed_at":"2026-08-15T18:33:23.888453Z","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":"2026-08-15T18:33:23.897581Z","title":"Sanity checks for saliency maps","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.897581Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:8b529f11ca74640ea7c9efcffaeaec8256c08ceab4f72bcaf8a58dae593d03a2","observation_id":"57cdcb95-d44e-4ed0-9de8-7e8e7dbe45d7","resolution":{"observed_at":"2026-08-15T18:33:23.897581Z","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":"2026-08-15T18:33:23.988090Z","title":"Interpretation of neural networks is fragile","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:23.988090Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:ab94ee2c8d793c61968d9a29a388aa6ed7f951529ce8a6c24571ca05c2d22953","observation_id":"de6d1643-ca20-4e4c-9bbc-09a30a7e4e0a","resolution":{"observed_at":"2026-08-15T18:33:23.988090Z","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":"2026-08-15T18:33:24.022190Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.022190Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:b96c3bfa93d8448550195105eda9643eaabc423713fa7709031531d445f7b308","observation_id":"a229a3d6-c7cd-4406-96bb-37fdf09f4953","resolution":{"observed_at":"2026-08-15T18:33:24.022190Z","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":"2026-08-15T18:33:24.044994Z","title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.044994Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:09e30ddcf3eaf03a9b94ad53e0a2ae55352875c7cfb02bbf5a347ad7daa3a7af","observation_id":"ae9908be-2b88-41ab-9151-63d7f695553f","resolution":{"observed_at":"2026-08-15T18:33:24.044994Z","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":"2026-08-15T18:33:24.051015Z","title":"Network dissec- tion: Quantifying interpretability of deep visual representations","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.051015Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:f8f763c736f854e5e692d9c0ce2149eec6a718a2eed7ab2cd14925d67a0c8636","observation_id":"bf506858-a230-4d99-8dda-3bec12dd0844","resolution":{"observed_at":"2026-08-15T18:33:24.051015Z","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":"2026-08-15T18:33:24.056752Z","title":"Craft: Concept recursive activation factorization for explainability","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.056752Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:3b492909227605d4cd2c5a947ca3a83f2d49fa27c9eab63cba50db7bf2881192","observation_id":"9acdc07e-d552-48b9-a92a-724fe1d91399","resolution":{"observed_at":"2026-08-15T18:33:24.056752Z","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":"2026-08-15T18:33:24.062338Z","title":"Understanding video transformers via universal concept discovery","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.062338Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:96ce6caa80728be97dcacac78d33eba02fde472265436612dd4b1ea1e4b7fc05","observation_id":"2626aa0d-686d-449f-80d9-584bac746125","resolution":{"observed_at":"2026-08-15T18:33:24.062338Z","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":"2026-08-15T18:33:24.114677Z","title":"Sparse autoencoders find highly interpretable features in language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.114677Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:1c0b96501f7d278926b68d07722c674bd2343a834961ed5dc6bb11783ba56c65","observation_id":"6fa1018b-2fe4-49d9-947e-6aecf72d3002","resolution":{"observed_at":"2026-08-15T18:33:24.114677Z","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":"2026-08-15T18:33:24.184942Z","title":"Towards monosemanticity: Decomposing language models with dictionary learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.184942Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:ec4466aed28b0b009176dbaa96004b6c59573a6247548ce2ed891dcf04e8d313","observation_id":"13445960-c2ca-466e-a26a-7e71aa1fa8bb","resolution":{"observed_at":"2026-08-15T18:33:24.184942Z","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":"2026-08-15T18:33:24.215459Z","title":"A holistic approach to unifying automatic concept extraction and concept importance estimation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.215459Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:8f59f456e34ed130355361d1c8181343a0a5dcc1035d92828ece97e7114c0dcb","observation_id":"26a4bb2f-dedf-4028-99f7-c78d8758ce06","resolution":{"observed_at":"2026-08-15T18:33:24.215459Z","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":"2026-08-15T18:33:24.230818Z","title":"A is for absorption: Studying feature splitting and absorption in sparse autoencoders","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.230818Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:187f0af3829709a8ec20d030d7e70a7c071147fd954dc879f3efa971391c9c0e","observation_id":"f7196a3d-b097-427d-8bab-498a8f589b58","resolution":{"observed_at":"2026-08-15T18:33:24.230818Z","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":"2026-08-15T18:33:24.238588Z","title":"Relational composition in neural networks: A survey and call to action","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.238588Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:31953b42a038fe073bc4e22bb766f270daa13d92d7d55363c03631fdf5f74448","observation_id":"2b4e9208-e078-4d82-b127-98eacd3a34f1","resolution":{"observed_at":"2026-08-15T18:33:24.238588Z","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":"2026-08-15T18:33:24.248444Z","title":"Towards unifying interpretability and control: Evaluation via intervention","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.248444Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:62e20ed56c20c20e5238c28a4fdbe440d7bc439e81731160fd8403052f577ab2","observation_id":"c07af7cc-3d07-49e0-8628-e00b269a68ee","resolution":{"observed_at":"2026-08-15T18:33:24.248444Z","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":"2026-08-15T18:33:24.303830Z","title":"Archetypal SAE: Adaptive and stable dictionary learning for concept extraction in large vision models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.303830Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:2b5f65bfb5f48e5d62da7e1793afbc8eb9ab36c66772859a2fa98f2fb73d5fb2","observation_id":"2815a0b4-533c-4cfa-8748-1d12383bc195","resolution":{"observed_at":"2026-08-15T18:33:24.303830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.09333","last_updated":"2025-04-07T18:03:40Z","snapshot_observed_at":"2026-08-14T01:12:10.974028Z","submitted_at":"2025-01-16T07:07:41Z","title":"Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.09333","snapshot_observed_at":"2026-08-15T18:33:24.363074Z","title":"Prompt-CAM: A simpler interpretable transformer for fine-grained analysis","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.363074Z"},"links":{"cited_paper":"/paper/2501.09333","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:53d44f155b748d72c808182cd1b5f966abe22941692b67c8fb200cd04e642fe5","observation_id":"0f28e8aa-6510-4f27-a9e4-ccec007d8cbc","resolution":{"observed_at":"2026-08-15T18:33:24.363074Z","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":"2026-08-15T18:33:24.419998Z","title":"GAN dissection: Visualizing and understanding generative adversarial networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.419998Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:51d2f0dee41f762716392f339b19599d66538d8f050786b6802ce4583759571b","observation_id":"e6cfaf60-a5cd-42b3-9009-d867ac9dc7cb","resolution":{"observed_at":"2026-08-15T18:33:24.419998Z","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":"2026-08-15T18:33:24.455734Z","title":"What the DAAM: Interpreting stable diffusion using cross attention","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.455734Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:4ecaf8da3ae6dae25b8d9aa7301a61869bb04bf3ab84731e6a252ac5510b86b1","observation_id":"72842019-5626-49ad-9ce4-5431335e78e0","resolution":{"observed_at":"2026-08-15T18:33:24.455734Z","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":"2026-08-15T18:33:24.462688Z","title":"Qualitative failures of image generation models and their application in detecting deepfakes","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.462688Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:9596b4b049c5774a1773b3646808f1521a0712c12f028e4a800fa5110b365347","observation_id":"396c2a20-cb5f-4df9-97e5-706a1d5b92d3","resolution":{"observed_at":"2026-08-15T18:33:24.462688Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-08-15T12:50:58.405488Z","submitted_at":"2022-04-13T01:10:33Z","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.06125","snapshot_observed_at":"2026-08-15T18:33:24.468612Z","title":"Hierarchical text-conditional image generation with CLIP latents","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.468612Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:b90f3b70ee25d89740dea20e6b6ca6dbc3f4a749c722c597418a53529630abf0","observation_id":"816d4ac2-58d9-4291-acc3-bedfc53749a6","resolution":{"observed_at":"2026-08-15T18:33:24.468612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13456","last_updated":"2021-02-10T18:17:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-11-26T19:39:10Z","title":"Score-Based Generative Modeling through Stochastic Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13456","snapshot_observed_at":"2026-08-15T18:33:24.475458Z","title":"Score-based generative modeling through stochastic differential equations","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.475458Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:60c9b9e113a43f72ba56a64e323bae57bd1a2463cff80ec30b6170ab8a57c337","observation_id":"6db6f65f-3b2e-4fd9-9dcd-0f11ade1f305","resolution":{"observed_at":"2026-08-15T18:33:24.475458Z","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":"2026-08-15T18:33:24.481506Z","title":"Consistency models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.481506Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:7e4c202f914a2ebc0c0e21ba3c4b3ea868fbe2d60baa477704cb5536389069c8","observation_id":"131f2991-6d0e-44ea-81a5-9beee39a87a2","resolution":{"observed_at":"2026-08-15T18:33:24.481506Z","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":"2026-08-15T18:33:24.569218Z","title":"Improved denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.569218Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:9974d8dc745404aafe81ff2df9d12d1859453df12c666f14f2c513fc79bd68cb","observation_id":"230f8b6b-1a4f-4356-ab10-edf0df4f1532","resolution":{"observed_at":"2026-08-15T18:33:24.569218Z","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":"2026-08-15T18:33:24.670178Z","title":"Video diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.670178Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:fa247daadc90f5e717ea01430047a6aaa7d8553bff24442eb82ec41e70727d99","observation_id":"9c9817a8-ef66-41f4-89f6-92788bc1c898","resolution":{"observed_at":"2026-08-15T18:33:24.670178Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13311","last_updated":"2023-10-11T06:28:41Z","snapshot_observed_at":"2026-08-16T15:30:58.074613Z","submitted_at":"2023-05-22T17:59:45Z","title":"VDT: General-purpose Video Diffusion Transformers via Mask Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13311","snapshot_observed_at":"2026-08-15T18:33:24.715527Z","title":"VDT: General-purpose video diffusion transformers via mask modeling","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.715527Z"},"links":{"cited_paper":"/paper/2305.13311","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:3055f23ed232b80e96b09a797006d2df54797c1c67b0bd4c1d052380fecdb937","observation_id":"1c89dfc9-b965-4dcd-8f9c-03bd02f17ebb","resolution":{"observed_at":"2026-08-15T18:33:24.715527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.06571","last_updated":"2023-08-12T13:53:10Z","snapshot_observed_at":"2026-08-14T13:59:50.878772Z","submitted_at":"2023-08-12T13:53:10Z","title":"ModelScope Text-to-Video Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.06571","snapshot_observed_at":"2026-08-15T18:33:24.735030Z","title":"ModelScope text-to-video technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.735030Z"},"links":{"cited_paper":"/paper/2308.06571","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:ec4b66e33ab8b7e34075b7134ad045fad7e51eec7da42e72c2e9e0562dae3dd5","observation_id":"f2a100be-e907-4666-b9aa-0fc786035038","resolution":{"observed_at":"2026-08-15T18:33:24.735030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04725","last_updated":"2024-02-08T18:08:57Z","snapshot_observed_at":"2026-08-17T14:04:31.230742Z","submitted_at":"2023-07-10T17:34:16Z","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.04725","snapshot_observed_at":"2026-08-15T18:33:24.751864Z","title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.751864Z"},"links":{"cited_paper":"/paper/2307.04725","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:b86b742b42672e71f1bebc6116cecd43a20c5d3e8e6ca6e98273d36c8f0f776c","observation_id":"dc68f085-c1c4-4780-9e81-7cc00e77c78c","resolution":{"observed_at":"2026-08-15T18:33:24.751864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12706","last_updated":"2024-03-19T13:08:54Z","snapshot_observed_at":"2026-08-16T14:08:24.768726Z","submitted_at":"2024-03-19T13:08:54Z","title":"AnimateDiff-Lightning: Cross-Model Diffusion Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.12706","snapshot_observed_at":"2026-08-15T18:33:24.769557Z","title":"AnimateDiff-Lightning: Cross-model diffusion distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.769557Z"},"links":{"cited_paper":"/paper/2403.12706","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:d38ff5315badae5897d7514012f7f60ee549eab2dfaa90dd2efc08b29205c00e","observation_id":"fcc86b88-6899-49d4-b50d-4ffeac2085b4","resolution":{"observed_at":"2026-08-15T18:33:24.769557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.15868","last_updated":"2022-05-29T19:02:15Z","snapshot_observed_at":"2026-08-12T19:21:15.526321Z","submitted_at":"2022-05-29T19:02:15Z","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.15868","snapshot_observed_at":"2026-08-15T18:33:24.776424Z","title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.776424Z"},"links":{"cited_paper":"/paper/2205.15868","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:c4535629d3bbf93cc8176fa8e9a3204928a5ed94197de80279ec0925c41e2e3a","observation_id":"cfbd9dbe-b01e-4dfe-ae85-691bc24dc638","resolution":{"observed_at":"2026-08-15T18:33:24.776424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.19512","last_updated":"2023-10-30T13:12:40Z","snapshot_observed_at":"2026-08-13T01:39:12.659510Z","submitted_at":"2023-10-30T13:12:40Z","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.19512","snapshot_observed_at":"2026-08-15T18:33:24.781838Z","title":"VideoCrafter1: Open diffusion models for high-quality video generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.781838Z"},"links":{"cited_paper":"/paper/2310.19512","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:9856d49d7f2a6ed8691df0f1a760f14cf6f867a75757b5d5fc010a966cb5f023","observation_id":"521dc25f-1697-4af5-9538-64e77e458891","resolution":{"observed_at":"2026-08-15T18:33:24.781838Z","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":"2026-08-15T18:33:24.787805Z","title":"Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.787805Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:fa48ad120eab3a254fe21b58b5c1a611c83ce47ecb0dd352918307b2cdd5812b","observation_id":"31d1dc30-278e-438d-858a-fa15ec4de45a","resolution":{"observed_at":"2026-08-15T18:33:24.787805Z","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":"2026-08-15T18:33:24.870472Z","title":"Magic3D: High-resolution text-to-3d content creation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.870472Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:24ecf98c6a7936f5c8adf07c0e41558e897ea324d2ca58d4b846d002dac7d229","observation_id":"2c08b538-256a-4c06-9468-02edc36e557e","resolution":{"observed_at":"2026-08-15T18:33:24.870472Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.02463","last_updated":"2023-05-03T23:59:13Z","snapshot_observed_at":"2026-08-12T18:09:04.196531Z","submitted_at":"2023-05-03T23:59:13Z","title":"Shap-E: Generating Conditional 3D Implicit Functions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.02463","snapshot_observed_at":"2026-08-15T18:33:24.944024Z","title":"Shap-E: Generating conditional 3d implicit functions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.944024Z"},"links":{"cited_paper":"/paper/2305.02463","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:246f48c950ed2160f953a5368aded68a54785f737a6a9fe19de892b2f07b2813","observation_id":"ea612781-1c10-43fc-a2c5-6a350117191e","resolution":{"observed_at":"2026-08-15T18:33:24.944024Z","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":"2026-08-15T18:33:24.973933Z","title":"Score jacobian chaining: Lifting pretrained 2d diffusion models for 3d generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.973933Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:9790f46b469c1514e6c623ce2a9df409f0dc092dee8ea6434e1604bfbcec6288","observation_id":"d4cf1d53-7d0f-4d97-b2e7-4143686c5587","resolution":{"observed_at":"2026-08-15T18:33:24.973933Z","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":"2026-08-15T18:33:24.980516Z","title":"Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.980516Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:190feae68310e7346854d3e5a66e37b437136929fb7aa7029aee2a344eeefe82","observation_id":"7f33ae7d-4840-4e36-89d1-5db350df25ff","resolution":{"observed_at":"2026-08-15T18:33:24.980516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-08-11T15:38:14.931716Z","submitted_at":"2020-10-06T06:15:51Z","title":"Denoising Diffusion Implicit Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02502","snapshot_observed_at":"2026-08-15T18:33:24.992206Z","title":"Denoising diffusion implicit models","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.992206Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:f9f573ff75227d7e86152e71b90055d13c80f6417112654a7178e5ceeb8d552b","observation_id":"e685852c-4089-4562-af3f-d3309ce84d02","resolution":{"observed_at":"2026-08-15T18:33:24.992206Z","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":"2026-08-15T18:33:24.998749Z","title":"Stable Diffusion 2.0 Release, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:24.998749Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:1d9a840f9ed0927391fc82e1f1e48a64f257c68dd362452e7ac68e73b528f3f5","observation_id":"bb1ae87e-3846-4de1-9d1d-1d7349e525eb","resolution":{"observed_at":"2026-08-15T18:33:24.998749Z","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":"2026-08-15T18:33:25.004763Z","title":"Introducing Stable Diffusion 3, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.004763Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:927b5945f366b0c581e858b0db87caa9079fdc7a5ffe57ad2b73587501e7bd16","observation_id":"a1bf2a8d-cfc5-42b0-a0a4-0e30e2d958ed","resolution":{"observed_at":"2026-08-15T18:33:25.004763Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01952","last_updated":"2023-07-04T23:04:57Z","snapshot_observed_at":"2026-08-14T22:54:08.184266Z","submitted_at":"2023-07-04T23:04:57Z","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01952","snapshot_observed_at":"2026-08-15T18:33:25.011962Z","title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.011962Z"},"links":{"cited_paper":"/paper/2307.01952","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:143d19cebb62db7b40ea5a8652919e6286e70420d216267793ad8a6a039c2cbb","observation_id":"833d4d16-685c-4492-ad50-3a575f5a3093","resolution":{"observed_at":"2026-08-15T18:33:25.011962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.00983","last_updated":"2023-06-01T17:59:51Z","snapshot_observed_at":"2026-08-16T15:27:22.560184Z","submitted_at":"2023-06-01T17:59:51Z","title":"StyleDrop: Text-to-Image Generation in Any Style","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.00983","snapshot_observed_at":"2026-08-15T18:33:25.018215Z","title":"StyleDrop: Text-to-image generation in any style","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.018215Z"},"links":{"cited_paper":"/paper/2306.00983","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:dbf16fef4800e993fdf5ba491a622a7810bd45175630cc608a88a5feaaf99517","observation_id":"c552e18c-2a06-4041-a4b7-1fdbbdb7a0ca","resolution":{"observed_at":"2026-08-15T18:33:25.018215Z","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":"2026-08-15T18:33:25.027064Z","title":"Arbitrary style guidance for enhanced diffusion-based text-to-image generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.027064Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:64778e2a05003bcbcc57ee835c9cce622a7323521c9a2b18e42a0e9a40de5701","observation_id":"6e3a92f4-b73f-4e88-b283-cc30cbd12d3a","resolution":{"observed_at":"2026-08-15T18:33:25.027064Z","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":"2026-08-15T18:33:25.087626Z","title":"Adding conditional control to text-to-image diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.087626Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:71a62780ec7d4744271bbf5e3d36f7d0b4b571008eafd095fe13bf15ed30f8c9","observation_id":"bc2ab56e-49d3-40b0-82ef-29613818485b","resolution":{"observed_at":"2026-08-15T18:33:25.087626Z","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":"2026-08-15T18:33:25.163342Z","title":"DreamBooth: Fine tuning text-to-image diffusion models for subject-driven generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.163342Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:902d6666b8b68b7c2816f208cc82f9677881a83410b4ef5b85dc87c82e127a87","observation_id":"c1777202-08a9-4f25-8e0b-1016536e45ca","resolution":{"observed_at":"2026-08-15T18:33:25.163342Z","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":"2504.07392","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:33:27.958536Z","title":"Id-booth: Identity-consistent face generation with diffusion models","venue":null,"work_id":"ed56f3f9-13d4-4755-a69c-5a1fb97d5eda","year":2025},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.240978Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:366f704487e885b016e5241ddc6457949f4a46f563ffde7e9d71f9812e91d707","observation_id":"5f4f0b60-8dbb-4cd6-8ce3-3a032a255901","resolution":{"observed_at":"2026-08-15T18:33:27.995939Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03502","last_updated":"2023-10-05T12:29:41Z","snapshot_observed_at":"2026-08-16T14:54:49.206254Z","submitted_at":"2023-10-05T12:29:41Z","title":"Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03502","snapshot_observed_at":"2026-08-15T18:33:25.260932Z","title":"Kandinsky: An improved text-to-image synthesis with image prior and latent diffusion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.260932Z"},"links":{"cited_paper":"/paper/2310.03502","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:dfbb2e983acf367dc1857e38fad5f196c769384f652eb27e7377372bd2b75d4f","observation_id":"72416d79-9f08-4960-ae4d-aa4be1688a43","resolution":{"observed_at":"2026-08-15T18:33:25.260932Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00426","last_updated":"2023-12-29T16:42:08Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-30T16:18:00Z","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00426","snapshot_observed_at":"2026-08-15T18:33:25.267579Z","title":"Pixart-α: Fast training of diffusion transformer for photorealistic text-to-image synthesis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.267579Z"},"links":{"cited_paper":"/paper/2310.00426","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:5cad093455e3e4643f1c4a971dde953a33ae1c073fcefb08984acb9715976934","observation_id":"2ec9da0b-f35c-4fe5-b8f2-6867e2794c25","resolution":{"observed_at":"2026-08-15T18:33:25.267579Z","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":"2026-08-15T18:33:25.274173Z","title":"DeepFloyd IF: A Powerful Open-Source Text-to-Image Model, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.274173Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:cea4bc406fd89e86b77f5328f80a4369f4d57b479d45d240a5d44af0ce9cb4a0","observation_id":"0c3d7e5e-e187-4dad-bdd7-8cc39dad3930","resolution":{"observed_at":"2026-08-15T18:33:25.274173Z","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":"2026-08-15T18:33:25.280303Z","title":"Announcing Black Forest Labs, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.280303Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:6e2e0aef5230a267cd32f8f7d98ef624671e5c2c2d27bf223a4f51c0421e3391","observation_id":"c75b6423-e15b-42ce-985a-1c3cb46000db","resolution":{"observed_at":"2026-08-15T18:33:25.280303Z","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":"2026-08-15T18:33:25.309868Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.309868Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:2d0d58c8183652de3aac2d68ab99114291a73bf4928c921c7c1ba3d2ad383c28","observation_id":"35e9ccd5-3cf0-4d5b-99a2-620bf6fe26db","resolution":{"observed_at":"2026-08-15T18:33:25.309868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10789","last_updated":"2022-06-22T01:11:29Z","snapshot_observed_at":"2026-08-14T02:29:38.306439Z","submitted_at":"2022-06-22T01:11:29Z","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.10789","snapshot_observed_at":"2026-08-15T18:33:25.391904Z","title":"Scaling autoregressive models for content-rich text-to-image generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.391904Z"},"links":{"cited_paper":"/paper/2206.10789","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:ed49bc2b8ada5bbd0e870acfb6e0a7659b629cae90a93aa85c31aeb920d8535d","observation_id":"ffa28fea-949d-48c8-8cad-c4c3fca4ff1d","resolution":{"observed_at":"2026-08-15T18:33:25.391904Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1712.00409","last_updated":"2017-12-01T17:13:14Z","snapshot_observed_at":"2026-08-14T02:46:56.838057Z","submitted_at":"2017-12-01T17:13:14Z","title":"Deep Learning Scaling is Predictable, Empirically","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.00409","snapshot_observed_at":"2026-08-15T18:33:25.520016Z","title":"Deep learning scaling is predictable, empirically","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.520016Z"},"links":{"cited_paper":"/paper/1712.00409","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:609a722fec61352e9d04db8f32c5b7dc5ad1b2fade1605512487d108a4804d44","observation_id":"9b406070-bf53-4646-a923-e473159d086c","resolution":{"observed_at":"2026-08-15T18:33:25.520016Z","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":"2026-08-15T18:33:25.553567Z","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.553567Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:1d5961f432000045307bf927c4923b6b444625d4e857737e9017afd308c16e22","observation_id":"e87cdaef-56d8-4493-86bc-21ea6e6078e3","resolution":{"observed_at":"2026-08-15T18:33:25.553567Z","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":"2026-08-15T18:33:25.558830Z","title":"Common crawl corpus","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.558830Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:93dd2f9118ec841af4e86773fc9b835c83ee7f2024061ef3a80eb053bdb20e10","observation_id":"1f152598-3726-4196-87c0-27637ef0df29","resolution":{"observed_at":"2026-08-15T18:33:25.558830Z","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":"2026-08-15T18:33:30.884227Z","title":"COYO-700M: Image-text pair dataset, 2022","venue":null,"work_id":"be13e0e8-f03d-4f26-be4f-db08739f4d15","year":2022},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.564369Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:8c07a972bbc81b801e7eb37296502068f6e42fd2c03218e39f1ba4a4c83c8375","observation_id":"c4fe50d8-6ccb-4fe9-b17a-9b0b81476642","resolution":{"observed_at":"2026-08-15T18:33:30.908054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T18:33:30.818183Z","title":"Conceptual Captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning","venue":null,"work_id":"bb855681-28c0-4461-8ebb-bd54b5befbe2","year":2018},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.571477Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:3a0338aacec8bf507e457cd07dde45e39dca7bbf522a3b508c68e8ccc44c6a6a","observation_id":"718690a0-d9d1-4d86-8404-7cd4cb05ac01","resolution":{"observed_at":"2026-08-15T18:33:30.843698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T18:33:30.792585Z","title":"Into the LAION’s den: Investigating hate in multimodal datasets","venue":null,"work_id":"23d2c575-d5e9-4aab-b41e-d9e04e229a3d","year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.578886Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:cc1645102e180d3814e6cd7d9a2475064711f0cc28bf07fc198ff21910698e3d","observation_id":"de735147-3211-40e4-a2aa-48094493b42a","resolution":{"observed_at":"2026-08-15T18:33:30.800656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T18:33:30.771690Z","title":"The dark side of dataset scaling: Evaluating racial classification in multimodal models","venue":null,"work_id":"edffabb0-64c2-4efe-9fdd-b15328561ba9","year":2024},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.605146Z"},"links":{"citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:350c89afb909efb37a61507ccc5c985876329e51f6836fd94a0a8d820734ba8b","observation_id":"3ebced64-79d2-4c65-a924-8c64a7abddc6","resolution":{"observed_at":"2026-08-15T18:33:30.779233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.00755","last_updated":"2023-11-15T08:51:11Z","snapshot_observed_at":"2026-08-16T15:11:32.111030Z","submitted_at":"2023-08-01T18:00:08Z","title":"The Bias Amplification Paradox in Text-to-Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.00755","snapshot_observed_at":"2026-08-15T18:33:25.708005Z","title":"The bias amplification paradox in text-to- image generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.708005Z"},"links":{"cited_paper":"/paper/2308.00755","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:a271d475b66b2baed9d04771ad48dc718498c4adaba7fd026b7331087ec66191","observation_id":"96c61e2b-100e-415b-8dc5-07f24501f699","resolution":{"observed_at":"2026-08-15T18:33:25.708005Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.01963","last_updated":"2021-10-05T11:47:27Z","snapshot_observed_at":"2026-08-17T20:03:41.214987Z","submitted_at":"2021-10-05T11:47:27Z","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.01963","snapshot_observed_at":"2026-08-15T18:33:25.803378Z","title":"Multimodal datasets: Misog- yny, pornography, and malignant stereotypes","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-15T18:33:25.803378Z"},"links":{"cited_paper":"/paper/2110.01963","citing_paper":"/paper/2506.19708"},"observation_digest":"sha256:1f3a2427cd531380e548877f7fed345ed4e4e4dfd536a8191af5ba61804a22a7","observation_id":"87570b4a-ab18-481e-bc99-c95500a713ac","resolution":{"observed_at":"2026-08-15T18:33:25.803378Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.19708","last_updated":"2025-06-24T15:15:15Z","latest_version":1,"primary_category":"cs.GR","snapshot_observed_at":"2026-08-17T21:05:01.309881Z","submitted_at":"2025-06-24T15:15:15Z","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":93,"verified_exact":3,"verified_fuzzy":4},"total_outbound_references":142},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 100 of 142 outbound references and 2 inbound Pith citation observations for arXiv:2506.19708."}