{"as_of":"2026-08-10T06:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:af91e492be848638ef6b59a1f6bc2d9e14e9b6d9d69fb75c2b133496650314c4","coverage":[{"denominator":17,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":17,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:12:25.414652Z","state":"measured"},{"denominator":17,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":17,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.15970/citation-record","integrity":"/paper/2505.15970/integrity","json":"/paper/2505.15970/citation-record.json","paper":"/paper/2505.15970"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:12:27.175332Z","title":"Do convolutional neural networks learn class hierarchy? IEEE transactions on visualization and computer graphics, 24(1):152–162, 2017","venue":null,"work_id":"f7039d2b-3f3e-4c89-8c52-71f2498e0556","year":2017},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:23.930657Z"},"links":{"citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:4752f88a0b2631c1542cf3692c042b0239cce4e39eb67abf1c47cd527ae8005e","observation_id":"24ed551c-59c3-4c94-94ec-92fab0ca9e1e","resolution":{"observed_at":"2026-08-07T15:12:27.299910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T15:12:26.835460Z","title":"Generic attention- model explainability for interpreting bi-modal and encoder- decoder transformers","venue":null,"work_id":"dbc77044-94da-40b2-afa8-34877ee647fe","year":null},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:24.028157Z"},"links":{"citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:08b322731d26bbfe0d9d7c695e1f051651ffcb8f9cfcc3e8f4b030c705766d90","observation_id":"c47f8954-9b86-457c-8eb0-fe5e6f405b38","resolution":{"observed_at":"2026-08-07T15:12:27.016575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.08600","last_updated":"2023-10-04T13:17:38Z","snapshot_observed_at":"2026-07-06T16:19:05.495349Z","submitted_at":"2023-09-15T17:56:55Z","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.08600","snapshot_observed_at":"2026-08-07T15:12:24.225803Z","title":"Sparse autoencoders find highly interpretable features in language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:24.225803Z"},"links":{"cited_paper":"/paper/2309.08600","citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:ae7693b8f4bfe2a09786c2b7c9ed96786cd96b19d953f9e1ef458778d141f5a2","observation_id":"fda0ab0c-2157-408e-84ce-9184b46e8532","resolution":{"observed_at":"2026-08-07T15:12:24.225803Z","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":"2026-08-07T15:12:26.666811Z","title":"Daujotas","venue":null,"work_id":"dbc64ac0-7847-4881-b35b-1bf1547d1be4","year":2024},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:24.343280Z"},"links":{"citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:75bf88071ae575e6ed41437a1d3395ae302ec6e39a65fe6cfb9d3ec837111e9b","observation_id":"4f442003-4cf3-4819-b2ae-7eecc4976eae","resolution":{"observed_at":"2026-08-07T15:12:26.753098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T15:12:24.410087Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:24.410087Z"},"links":{"citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:e190fda9219c6b0cdf2293ea01053588657403fdb870f9a585d4f5d1493b059f","observation_id":"2055bb90-3b85-4c04-a513-608145eb72a0","resolution":{"observed_at":"2026-08-07T15:12:24.410087Z","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":"2026-08-07T15:12:26.506520Z","title":"Towards multimodal interpretability: Learn- ing sparse interpretable features in vision transform- ers","venue":null,"work_id":"e720b1f4-6a0e-4f21-a8ba-1036a1caaea2","year":2024},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:24.474062Z"},"links":{"citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:4f696ad5c450c585f29070ed430b157e1177d7c165f694753bdad14a07b76288","observation_id":"cc5e0f5c-7132-4fe3-8c6f-e1e57f15d118","resolution":{"observed_at":"2026-08-07T15:12:26.552148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04093","last_updated":"2024-06-06T14:10:12Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-06-06T14:10:12Z","title":"Scaling and evaluating sparse autoencoders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04093","snapshot_observed_at":"2026-08-07T15:12:24.567773Z","title":"Scaling and evaluating sparse autoencoders","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:24.567773Z"},"links":{"cited_paper":"/paper/2406.04093","citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:65e082eedf6ca95b99f8bc94c832249cb7b14a3871c55ccd181de0ccce2dfbb0","observation_id":"a875a42f-09d0-40dc-9bb1-c24fe8fa9de4","resolution":{"observed_at":"2026-08-07T15:12:24.567773Z","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":"2026-08-07T15:12:26.350481Z","title":"Sae- lens","venue":null,"work_id":"192650bf-b181-413d-9a2b-4325b4013c99","year":null},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:24.659788Z"},"links":{"citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:4edbd3c05133b8141c3f7a165637a5a57e2babc70f0f92d6c0d34716f0fad150","observation_id":"5894a23f-9255-42da-92b0-a209e060733c","resolution":{"observed_at":"2026-08-07T15:12:26.427018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-07T15:12:24.740434Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:24.740434Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:2cd176fe9e9a91c9150f470689f10ddbfc7eba8e8bd0d2e86f5ae77da1418c24","observation_id":"912370c2-dd42-4ea2-86b4-492e747a73e0","resolution":{"observed_at":"2026-08-07T15:12:24.740434Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19750","last_updated":"2025-03-30T23:55:03Z","snapshot_observed_at":"2026-07-06T19:39:51.480716Z","submitted_at":"2024-10-10T17:58:47Z","title":"The Geometry of Concepts: Sparse Autoencoder Feature Structure","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.19750","snapshot_observed_at":"2026-08-07T15:12:24.830380Z","title":"The geometry of con- cepts: Sparse autoencoder feature structure","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:24.830380Z"},"links":{"cited_paper":"/paper/2410.19750","citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:75f95438086b7e69a5b3441036a5f7da3f6099e27996375b340783b391eae2b5","observation_id":"eb580ed5-bbb6-4827-919e-cd10a4e64ce4","resolution":{"observed_at":"2026-08-07T15:12:24.830380Z","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":"2026-08-07T15:12:26.224869Z","title":"Zoom in: An in- troduction to circuits","venue":null,"work_id":"4a7f3031-6590-43af-9ed1-1211b51df8d8","year":2020},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:24.923695Z"},"links":{"citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:7bc973aa6cab7cf52326231bf39ac9e48d05a122d441826c1eb135bfb53d1cd7","observation_id":"bc7c2bac-9b01-44a1-897e-6838ad8d0b7d","resolution":{"observed_at":"2026-08-07T15:12:26.259200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-09T18:02:17.307812Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-07T15:12:25.002700Z","title":"Dinov2: Learning robust visual features without supervision","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:25.002700Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:033c74a3c8b68630f105fa168a350a5631d237c98c3deab84cd76ed46287d611","observation_id":"d671a085-8d74-4fa6-8bc1-860bc2e8a8c9","resolution":{"observed_at":"2026-08-07T15:12:25.002700Z","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":"2026-08-07T15:12:26.032191Z","title":"Category selectivity in human visual cortex: Beyond visual object recognition","venue":null,"work_id":"cde7ee66-011c-4125-a843-a2e36f5ef3bc","year":2017},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:25.094625Z"},"links":{"citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:e23bbdf5e1d45f8c2d25ea16a0edf3530882068b0174f56f6837b7c1dfe288ca","observation_id":"c9f846df-74a9-4af3-b1f0-4732b002dedb","resolution":{"observed_at":"2026-08-07T15:12:26.109732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16014","last_updated":"2024-04-30T17:54:04Z","snapshot_observed_at":"2026-08-02T10:59:21.418230Z","submitted_at":"2024-04-24T17:47:22Z","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16014","snapshot_observed_at":"2026-08-07T15:12:25.177430Z","title":"Improving dictionary learning with gated sparse autoencoders","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:25.177430Z"},"links":{"cited_paper":"/paper/2404.16014","citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:f0167892e75935e5875b753f3a5de81b3c87cd7d80dbdfac24ccaf34a462f1a5","observation_id":"4191669c-0b5d-4741-8024-10122b03189b","resolution":{"observed_at":"2026-08-07T15:12:25.177430Z","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":"2026-08-07T15:12:25.232862Z","title":"Berg, and Li Fei-Fei","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:25.232862Z"},"links":{"citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:9b531da9d0367809718d75e66a130701e5f2e164ce1ac201ccc27a8e416fab09","observation_id":"2e33d9ad-9726-4279-9b6b-5126395b2c64","resolution":{"observed_at":"2026-08-07T15:12:25.232862Z","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":"2026-08-07T15:12:25.323050Z","title":"Sparse autoencoders for scientifically rigorous interpre- tation of vision models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:25.323050Z"},"links":{"citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:9430cd554a0a073d72e5184ee85f60908497e259a6ffab0c1315c35b539f06ee","observation_id":"24370638-12a6-4538-ba2e-1d3f816f3ac9","resolution":{"observed_at":"2026-08-07T15:12:25.323050Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.14064","last_updated":"2024-12-02T00:42:44Z","snapshot_observed_at":"2026-08-06T19:11:17.226491Z","submitted_at":"2023-11-23T15:42:42Z","title":"HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding","version":3},"cited_work":{"arxiv_id":"2311.14064","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.14064","snapshot_observed_at":"2026-08-07T15:12:25.563904Z","title":"HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding","venue":"cs.CV","work_id":"d061711e-e858-4fa5-a8c7-b0ecf48cb892","year":2023},"citing_paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:25.414652Z"},"links":{"cited_paper":"/paper/2311.14064","citing_paper":"/paper/2505.15970"},"observation_digest":"sha256:9781886ba9d73c4f8a6d004219810c6f04f75b6a95bab36355c1b21e7ee3cf60","observation_id":"0bac0343-9213-4f0c-898b-c7ae0f3ca397","resolution":{"observed_at":"2026-08-07T15:12:25.643590Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.15970","last_updated":"2025-05-21T19:38:48Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T01:03:28.134257Z","submitted_at":"2025-05-21T19:38:48Z","title":"Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders"},"reference_resolution":{"displayed":17,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":1,"verified_fuzzy":7},"total_outbound_references":17},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 0 inbound Pith citation observations for arXiv:2505.15970."}