{"as_of":"2026-08-11T08:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b0ff0b3dcd95d981f720e05dbbe721e63ebb48aac80f0620cea2f95dcfc52b0b","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T04:22:17.756075Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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":"2026-08-06T04:22:29.079282Z","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":"2026-07-04T06:29:37.789296Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.03649","snapshot_observed_at":"2026-08-06T04:22:29.079282Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.03647","last_updated":"2025-08-05T16:57:16Z","snapshot_observed_at":"2026-08-10T01:43:38.917454Z","submitted_at":"2025-08-05T16:57:16Z","title":"Improving Q-Learning for Real-World Control: A Case Study in Series Hybrid Agricultural Tractors","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:29.079282Z"},"links":{"cited_paper":"/paper/2508.03649","citing_paper":"/paper/2508.03647"},"observation_digest":"sha256:ff6e5c481522d91c00efc8b5eb643129804127da7405a41ef08a9ed567d53e19","observation_id":"6ffa5912-0703-493f-9498-e0206b27f184","resolution":{"observed_at":"2026-08-06T04:22:29.079282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"cited_work":{"arxiv_id":"2508.03649","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.03649","snapshot_observed_at":"2026-07-04T06:29:37.789296Z","title":"Cross-model semantics in representation learning,","venue":null,"work_id":"c7e0030a-7ca4-41ff-88ce-57a04c0befa2","year":2025},"citing_paper":{"arxiv_id":"2606.21509","last_updated":"2026-06-19T15:02:58Z","snapshot_observed_at":"2026-08-07T05:37:10.646734Z","submitted_at":"2026-06-19T15:02:58Z","title":"A Stitch in Time Saves Nine: Preserving Policy Compatibility Under Perception Updates in End-to-End Autonomous Driving","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-26T14:25:15.901062Z"},"links":{"cited_paper":"/paper/2508.03649","citing_paper":"/paper/2606.21509"},"observation_digest":"sha256:7e0212e811fe5ab808c3f9b7433853a5bb3942d338c5effadf973e90e7a50ca7","observation_id":"40d5edfd-73d6-4529-a6d7-7b1a1c927d7b","resolution":{"observed_at":"2026-07-04T06:29:37.790899Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2508.03649/citation-record","integrity":"/paper/2508.03649/integrity","json":"/paper/2508.03649/citation-record.json","paper":"/paper/2508.03649"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.20237","last_updated":"2025-02-27T16:22:18Z","snapshot_observed_at":"2026-08-07T17:42:25.279898Z","submitted_at":"2025-02-27T16:22:18Z","title":"Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.20237","snapshot_observed_at":"2026-08-06T04:22:15.003712Z","title":"Teasing apart architecture and initial weights as sources of inductive bias in neural networks,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.003712Z"},"links":{"cited_paper":"/paper/2502.20237","citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:dbffba3b3eecb7d548a3c3b20dde72816361f0c7016d1733d0345589ccf2cc21","observation_id":"b18cb7cc-8d0e-4b71-b125-8d9ab408dc96","resolution":{"observed_at":"2026-08-06T04:22:15.003712Z","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":"2026-08-06T04:22:22.195048Z","title":"Controlling the inductive bias of wide neural networks by modifying the kernel’s spectrum,","venue":null,"work_id":"c8c3e305-a3d4-4ac8-8a0b-0316f29d6186","year":2024},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.071199Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:c40a2fcd97ac01af2140623ca951a4f18dcae548650fd574539f09cbfacd4c34","observation_id":"1487c88a-9b13-475a-935f-71395a8646bb","resolution":{"observed_at":"2026-08-06T04:22:22.260685Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.07512","last_updated":"2023-07-14T17:59:53Z","snapshot_observed_at":"2026-07-06T15:54:09.109682Z","submitted_at":"2023-07-14T17:59:53Z","title":"Expressive Monotonic Neural Networks","version":1},"cited_work":{"arxiv_id":"2307.07512","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.07512","snapshot_observed_at":"2026-08-06T04:22:19.044798Z","title":"Expressive Monotonic Neural Networks","venue":"cs.LG","work_id":"c838b016-4ad6-4d4c-a8f4-c8871176b847","year":2023},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.154592Z"},"links":{"cited_paper":"/paper/2307.07512","citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:db2855214fd360e7269cbc827bff03feb9bf56e1eb161eba4ea586b2312a3c0b","observation_id":"b5bd25ba-526f-4266-a69f-265af3cf9748","resolution":{"observed_at":"2026-08-06T04:22:19.093997Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15941","last_updated":"2024-06-22T21:14:24Z","snapshot_observed_at":"2026-08-10T07:28:36.009196Z","submitted_at":"2024-06-22T21:14:24Z","title":"Towards Exact Computation of Inductive Bias","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.15941","snapshot_observed_at":"2026-08-06T04:22:15.233882Z","title":"Towards exact computation of inductive bias,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.233882Z"},"links":{"cited_paper":"/paper/2406.15941","citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:f8a229c0706240739ba8944c8c7d83f3ea91cd2554701bf09b4132644c7207b9","observation_id":"a9b8217f-3b0f-4428-8c2c-acb5ea854cd5","resolution":{"observed_at":"2026-08-06T04:22:15.233882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.12224","last_updated":"2025-07-16T13:33:31Z","snapshot_observed_at":"2026-08-06T16:48:47.710572Z","submitted_at":"2025-07-16T13:33:31Z","title":"Optimizers Qualitatively Alter Solutions And We Should Leverage This","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.12224","snapshot_observed_at":"2026-08-06T04:22:15.304977Z","title":"Optimizers qualitatively alter solutions and we should leverage this,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.304977Z"},"links":{"cited_paper":"/paper/2507.12224","citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:93354812af31b1e0e3c7566a51999a9af1726cb9f67af5fa85bf7778fcc5eee7","observation_id":"125f7d68-abbc-497f-a761-6eddc3f384fd","resolution":{"observed_at":"2026-08-06T04:22:15.304977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.00127","last_updated":"2025-07-31T19:26:45Z","snapshot_observed_at":"2026-08-06T10:25:00.126025Z","submitted_at":"2025-07-31T19:26:45Z","title":"Structured Transformations for Stable and Interpretable Neural Computation","version":1},"cited_work":{"arxiv_id":"2508.00127","doi":null,"metadata_source":"pith","pith_arxiv_id":"2508.00127","snapshot_observed_at":"2026-08-06T04:22:18.902050Z","title":"Structured Transformations for Stable and Interpretable Neural Computation","venue":"cs.LG","work_id":"d9cfb907-e0d7-4416-9472-7eb9da4058ce","year":2025},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.382815Z"},"links":{"cited_paper":"/paper/2508.00127","citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:3d132be0e50852b78ef64aadee1934634492bf29a8866756d9e018eab57a1830","observation_id":"9d461b5d-1c0d-417a-b403-7f64070e81a0","resolution":{"observed_at":"2026-08-06T04:22:18.959432Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.02126","last_updated":"2025-08-23T10:57:32Z","snapshot_observed_at":"2026-08-06T05:12:02.279630Z","submitted_at":"2025-08-04T07:15:57Z","title":"Understanding Learning Dynamics Through Structured Representations","version":2},"cited_work":{"arxiv_id":"2508.02126","doi":null,"metadata_source":"pith","pith_arxiv_id":"2508.02126","snapshot_observed_at":"2026-08-06T04:22:18.774003Z","title":"Understanding Learning Dynamics Through Structured Representations","venue":"cs.LG","work_id":"7bcd25b5-57bf-411a-8f82-8a819d19f860","year":2025},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.452449Z"},"links":{"cited_paper":"/paper/2508.02126","citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:143915799e2b57d7f2ee595aaa65a1e4ac6e5862f59889de1302c4759c40b9b8","observation_id":"d8bc25a6-4e52-41e1-8212-a722553867c2","resolution":{"observed_at":"2026-08-06T04:22:18.833220Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:22.091766Z","title":"When representations align: Universality in represen- tation learning dynamics,","venue":null,"work_id":"3c94dda8-905e-420f-9810-8a404f24e755","year":2024},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.528955Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:c45672b153de9a79faa491a5fb6ca5e148941effc51cfa860b005d5cc0592042","observation_id":"94c742c5-2f20-439e-8906-96ea55f5830b","resolution":{"observed_at":"2026-08-06T04:22:22.132752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.12345","last_updated":"2023-01-29T03:59:33Z","snapshot_observed_at":"2026-08-04T10:52:46.997548Z","submitted_at":"2023-01-29T03:59:33Z","title":"Chemotactic motility-induced phase separation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.12345","snapshot_observed_at":"2026-08-06T04:22:15.614382Z","title":"Getting aligned on representational alignment,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.614382Z"},"links":{"cited_paper":"/paper/2301.12345","citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:1434865c412bd1664960f46c216d05adc1fe677885a429df7d6a1dfbfa2ce9bd","observation_id":"6e57b299-6423-44e8-8baf-4ec1e8a05998","resolution":{"observed_at":"2026-08-06T04:22:15.614382Z","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":"2026-08-06T04:22:21.955834Z","title":"On the symmetries of deep learning models and their internal representations,","venue":null,"work_id":"db09d19d-6f29-4bde-833a-dd4d8a42dd0a","year":2022},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.748944Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:f4f4b2b32c152ddc38ceb053df15d2f7ce9cdcf24ca4cb2e2e1c6a3db6766c41","observation_id":"11843770-5446-470b-a0fc-595a16bded72","resolution":{"observed_at":"2026-08-06T04:22:22.031120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:21.824171Z","title":"Human alignment of neural network representations,","venue":null,"work_id":"a0c05f9f-135c-4fa4-a5ce-434428924bc5","year":2022},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.806886Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:986b510211b76c090fe6304c9001150ebc43fc07ffb89d1242a8b51a1e7c7449","observation_id":"3a49f9c2-83b7-40d9-8713-50c5d58cd270","resolution":{"observed_at":"2026-08-06T04:22:21.874234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:21.675403Z","title":"Towards a learning theory of representation alignment,","venue":null,"work_id":"17df06f6-91d8-4c1e-a08f-cbf5fbee814f","year":2025},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.904460Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:8a4821c48914508495675d0021ce40ca0f857988c6f3678c28deec41718497b9","observation_id":"bcecd2e8-813c-4492-9cb7-b159958f2957","resolution":{"observed_at":"2026-08-06T04:22:21.758893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2501.56789","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T04:22:18.545047Z","title":"Connecting neural models’ latent geometries with relative geodesic representations,","venue":null,"work_id":"b61a9fc3-6280-4eb7-9584-644d48eb1dc4","year":2025},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:15.965046Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:e9abdce4bb14db318dace2cf60af2a31a33d8ae7f6ce6b48610629a95ac94768","observation_id":"be4b1e2c-3dd7-458e-98cd-2e27b800523c","resolution":{"observed_at":"2026-08-06T04:22:18.640327Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:21.534505Z","title":"Latent space translation via semantic alignment,","venue":null,"work_id":"ac281e57-de55-4d15-9157-910237dd9a38","year":2023},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:16.079437Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:d6a9f553bf7006a9ca8c854f699251a710dd26567c7d9ec3fa88830a545835f8","observation_id":"534c3e0d-123e-4bc3-8c6b-59b872ce0dbb","resolution":{"observed_at":"2026-08-06T04:22:21.590242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12345","last_updated":"2025-01-21T18:23:42Z","snapshot_observed_at":"2026-08-10T22:45:22.078899Z","submitted_at":"2025-01-21T18:23:42Z","title":"The doubly librating Plutinos","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12345","snapshot_observed_at":"2026-08-06T04:22:16.174692Z","title":"Model alignment search,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:16.174692Z"},"links":{"cited_paper":"/paper/2501.12345","citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:4432abdc9c0d28399f47c35b9c8d36a7f35cf6455c4d7010f121d791dbadc89c","observation_id":"7038155d-cc5b-42da-85f5-244999836edf","resolution":{"observed_at":"2026-08-06T04:22:16.174692Z","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":"2026-08-06T04:22:21.376246Z","title":"Tracing representation progression: Analyzing and enhanc- ing layer-wise similarity,","venue":null,"work_id":"e01fbd39-57d8-4711-8cee-97831e4bb0a3","year":2024},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:16.286009Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:18fedaad3e1e092359da3bb99481395c18a25ee5622b0ba868fb63618b9e2106","observation_id":"7667fcc2-1278-48ed-a2a6-436ceb728add","resolution":{"observed_at":"2026-08-06T04:22:21.469652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2401.98765","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T04:22:18.210967Z","title":"Aligning machine and human visual representations across abstraction levels,","venue":null,"work_id":"d57bd455-ddc0-436a-b63d-60dbe7654c3d","year":2024},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:16.344645Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:b8312a61e210562622f205296c413947cb5b072e1e50fe503f5336ec02ded680","observation_id":"7670c4b3-a7cf-4f6e-9825-e61c61733c95","resolution":{"observed_at":"2026-08-06T04:22:18.328285Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:21.217914Z","title":"The neural race reduction: Dynamics of abstraction in gated networks,","venue":null,"work_id":"57e90422-2454-44ef-8ac2-26717b640e4f","year":2022},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:16.378575Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:6b50c40d4d28aa7e68d648091d34160beff487bd8e6b79b8b5eff5e8ded9fd2d","observation_id":"e8adf811-6473-42f9-ba2d-4e4118e8827a","resolution":{"observed_at":"2026-08-06T04:22:21.308074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:20.953591Z","title":"The platonic representation hypothesis,","venue":null,"work_id":"12c63969-1432-4d51-b762-fd045a904531","year":2024},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:16.462867Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:efa7693e7145965c3f510d62b107cec0d5a2fa90e13935fe7c2d2f164aa3f4b4","observation_id":"4d5e0db8-8c9c-4a41-b57b-a96009b3575b","resolution":{"observed_at":"2026-08-06T04:22:21.084702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:16.604665Z","title":"Universal sparse autoencoders: Interpretable cross- model concept alignment,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:16.604665Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:0f871e0add15140dc89f17befc2b11cbe45458a7cd7d49f80f8e99496558819d","observation_id":"2a044c06-b8a1-43d0-b856-3cb392f29479","resolution":{"observed_at":"2026-08-06T04:22:16.604665Z","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":"2026-08-06T04:22:20.736883Z","title":"On the direct alignment of latent spaces","venue":null,"work_id":"1c9291ee-ea33-4bad-88e5-c17072814f7d","year":2023},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:16.669374Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:b5642ab4668e1234b9c53ea6ea38c867b72dfe5e80bb0215b7a6b78f13c81660","observation_id":"5e5fee92-59ca-480e-b59b-66d8443b1559","resolution":{"observed_at":"2026-08-06T04:22:20.811358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:20.597585Z","title":"Similarity of neural network models: A survey of functional and representational measures,","venue":null,"work_id":"da94aabf-ae13-4c7b-8693-e6f8da1ef4f4","year":2023},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:16.763636Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:0fc628a188952d90c4008aba47c822e33e41219138a1dfe33e7b286c4871d143","observation_id":"ab46314f-96fa-4ead-8504-0e5c9f009dcc","resolution":{"observed_at":"2026-08-06T04:22:20.654380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:16.869825Z","title":"Understanding the emergence of multimodal representation alignment,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:16.869825Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:6b3dbc4ce50b9ba057ea0d8e51962a9366e85a7c00838339f76216b66a720d58","observation_id":"60d9f198-788c-49fe-a9e3-077fef66b9ab","resolution":{"observed_at":"2026-08-06T04:22:16.869825Z","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":"2026-08-06T04:22:20.341355Z","title":"From bricks to bridges: Product of invariances to enhance latent space communication,","venue":null,"work_id":"97329c95-b7dc-4222-bb73-e4c1eb2d524c","year":2023},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:16.986060Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:90c51f68efd13d72d49711eeb750f24a129a08d50f8c593ee4bbbc47510d20b0","observation_id":"82a53fe7-1c95-4add-b810-dd5204ca879e","resolution":{"observed_at":"2026-08-06T04:22:20.461018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:20.095286Z","title":"Rosetta neurons: Mining the common units in a model zoo,","venue":null,"work_id":"954d42b5-704a-4a82-abfa-c3b2b172b598","year":2023},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:17.091914Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:969869fb3f53c7958a4dbd22c3c8b60912511845b79fd138f90ba56d05708401","observation_id":"4b844151-1a3d-4a31-8b72-6494ffca89a9","resolution":{"observed_at":"2026-08-06T04:22:20.203347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:19.908237Z","title":"Relative representations enable zero-shot latent space communication,","venue":null,"work_id":"38f05dc1-651f-4f8b-b2ea-0136a34afd2c","year":2022},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:17.197980Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:ce8290dbc31f01902cf7af69db4d1e1263d2d52c8411635a4167f300068836b9","observation_id":"7f78e153-b146-4f3b-949f-970c1407c410","resolution":{"observed_at":"2026-08-06T04:22:20.003561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:19.673466Z","title":"Text-to-concept (and back) via cross-model alignment,","venue":null,"work_id":"d2679295-3417-4eb2-bec8-6cfccfada6dc","year":2023},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:17.252439Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:6997c3b15d4c4c4ccf88fd86166c9a6063d058cf0f7f723530dea52115d1482a","observation_id":"be5944a8-d989-445b-9f2e-5d261edae577","resolution":{"observed_at":"2026-08-06T04:22:19.794349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:19.509064Z","title":"Equivariant deep weight space alignment,","venue":null,"work_id":"ad0087c5-9b64-4c06-8d51-e1c717edd136","year":2023},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:17.365904Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:27954b558ab14b263644eb6b1c9e99e6c62c57cfe1654a41c98ef998012941fc","observation_id":"95f17125-9871-4208-8373-fbd1602b6880","resolution":{"observed_at":"2026-08-06T04:22:19.588637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.12345","last_updated":"2025-08-31T14:11:57Z","snapshot_observed_at":"2026-08-07T17:01:10.163191Z","submitted_at":"2025-03-16T03:51:06Z","title":"General Table Question Answering via Answer-Formula Joint Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.12345","snapshot_observed_at":"2026-08-06T04:22:17.451676Z","title":"Multimodal representation alignment for cross-modal informa- tion retrieval,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:17.451676Z"},"links":{"cited_paper":"/paper/2503.12345","citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:1beb3f00d05adcfbbc89ce3f5e381994da6054ad66363c01715a4c0ad1ef0281","observation_id":"b64afc5f-459c-4cf1-9d75-c7df2d778d7c","resolution":{"observed_at":"2026-08-06T04:22:17.451676Z","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":"2026-08-06T04:22:19.399098Z","title":"Latent functional maps,","venue":null,"work_id":"57da0914-2659-4d3e-bcad-6ba9471a298c","year":2024},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:17.581709Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:4dff77ea4bddda3ecfc6915eb8706f90f84f4dd005f93adc4bd7983f844ebe2d","observation_id":"1e62a43e-033e-460f-9992-987aaddd3150","resolution":{"observed_at":"2026-08-06T04:22:19.448632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:19.282665Z","title":"How do transformers learn topic structure: Towards a mechanis- tic understanding,","venue":null,"work_id":"057f2832-8afc-4ebc-8929-49f65974e6a9","year":2023},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:17.668343Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:99ba2bcb8d2bc7703d3a3d6131a06bfde9a841d3c28fbe9b8e1b2a9ca14e6d20","observation_id":"e02e974d-be4b-43c0-8fb6-b968a66df1e1","resolution":{"observed_at":"2026-08-06T04:22:19.338678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-06T04:22:19.166226Z","title":"Git re-basin: Merging models modulo permutation symmetries,","venue":null,"work_id":"64e27ca6-b4c2-4f9f-896f-802941d52b30","year":2022},"citing_paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T04:22:17.756075Z"},"links":{"citing_paper":"/paper/2508.03649"},"observation_digest":"sha256:5ad61faa1447348ca77e366595cc65dd98969912b3d45c57e76c34c5b1aff8d3","observation_id":"d78ac824-fe29-4aa0-909e-6b6195a82bf0","resolution":{"observed_at":"2026-08-06T04:22:19.221255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.03649","last_updated":"2025-08-05T16:57:24Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T04:22:14.596374Z","submitted_at":"2025-08-05T16:57:24Z","title":"Cross-Model Semantics in Representation Learning"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":5,"verified_fuzzy":19},"total_outbound_references":32},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 2 inbound Pith citation observations for arXiv:2508.03649."}