{"as_of":"2026-08-08T06:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d25571177aa7c9611ac05bbac7d204e0e9ec960425b89a831ad66c4d47b0a4f8","coverage":[{"denominator":13,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":13,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:14:00.876685Z","state":"measured"},{"denominator":13,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":13,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2506.03370/citation-record","integrity":"/paper/2506.03370/integrity","json":"/paper/2506.03370/citation-record.json","paper":"/paper/2506.03370"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:04.654096Z","title":"A theorem on probabilistic constant depth computations","venue":null,"work_id":"6d540a4c-dbab-4afc-9bc4-6b1025d33090","year":1984},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:13:59.169348Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:82b95dfae1293735809b5906108b1b4b365e7d1e242a8d8ac84d9126735f392d","observation_id":"58b8991f-a410-400c-85ed-014e7a996932","resolution":{"observed_at":"2026-08-07T11:14:04.863776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:04.368750Z","title":"Logical Languages Accepted by Transformer Encoders with Hard Attention, October 2023","venue":null,"work_id":"67c6427e-6b41-4a78-a496-940b81b95863","year":2023},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T11:13:59.276652Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:b121fd2f2f2aa4840d79fbd0be147466b9b7d10b8fd329ed440aee512f8bbc18","observation_id":"60de64b8-851e-487c-a1c8-08b33f214424","resolution":{"observed_at":"2026-08-07T11:14:04.534788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:04.059338Z","title":"Brzozowski and R","venue":null,"work_id":"7bf0b1cb-f68b-4713-9492-1606c8e3ff93","year":1978},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T11:13:59.433025Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:abe8469843e0e8c1f89967a45aaea1c71948f2a3050a82d3ea5d7b8040deeceb","observation_id":"13dfd690-76f8-4a88-9041-bf2e70eeab69","resolution":{"observed_at":"2026-08-07T11:14:04.227723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:03.692358Z","title":"First-order definable languages","venue":null,"work_id":"940911f3-438a-44aa-8f8d-efa8542a98b2","year":2008},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T11:13:59.575120Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:903b419d48b5ef811225f0a38716b33ccdcd355ec6887ecdb0088a282f6ea77a","observation_id":"c37835d1-3174-4302-be7e-21d0fe742371","resolution":{"observed_at":"2026-08-07T11:14:03.878847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:03.418182Z","title":"Computing approximate majority in ac0, 2023","venue":null,"work_id":"626fbf1c-ae46-4e8b-83e9-5e459d94ee1c","year":2023},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T11:13:59.707984Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:9badbd8077b9106dc9d2b981bbbd44291f1fa72cb0d1eee849ec59ca1029afc2","observation_id":"a50dd50c-9719-4a66-a990-7452ebbfe6cb","resolution":{"observed_at":"2026-08-07T11:14:03.593338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:03.069539Z","title":"Theoretical limitations of self-attention in neural sequence models.Transactions of the Asso- ciation for Computational Linguistics, 8:156–171, 2020","venue":null,"work_id":"a2b434cb-16b1-409d-93f5-84205a15786f","year":2020},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T11:13:59.848385Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:1774fab6466fccf4d9cce8ffb8e7e651d91dc3c9c18563b312a11394148be1e8","observation_id":"fb2f1390-0a2c-4dde-b1ed-a3bb98055e23","resolution":{"observed_at":"2026-08-07T11:14:03.235531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:02.772123Z","title":"Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity, April 2022","venue":null,"work_id":"3946ba1d-bc96-47ac-bc17-df921b26c698","year":2022},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:13:59.969748Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:fa3911a53be606d70c70cc065e706bda7f1560de23e6b4082ebae2dba50c0685","observation_id":"11812967-d25a-4139-9133-6f67bd8f897c","resolution":{"observed_at":"2026-08-07T11:14:02.913027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:02.459907Z","title":"Logical languages accepted by transformer encoders with hard attention, 2023","venue":null,"work_id":"06441a71-cadd-443d-b273-cb7cc21db07d","year":2023},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T11:14:00.109279Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:a58b15a27db05cce51f6d6d0bf18ea47921226a9c5e5acaf42128b511eb823f0","observation_id":"f177d7d5-e391-4aba-be5b-5fdd15822af2","resolution":{"observed_at":"2026-08-07T11:14:02.616828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:02.210437Z","title":"Temporal logic with past is exponentially more succinct, concurrency column.Bull","venue":null,"work_id":"1d7d488c-c460-463c-81f9-f941f0b325ba","year":2003},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:14:00.283268Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:90eeacb0cb2367a3875a06fe26e7b6953b6155fbb2ecb181e1af3e6cee380b8f","observation_id":"ce674e52-3e62-4e90-92a8-a41d68f81abd","resolution":{"observed_at":"2026-08-07T11:14:02.328152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:01.923971Z","title":null,"venue":null,"work_id":"823a5b71-1ef6-40ba-ada1-a79f50bca9fa","year":2021},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T11:14:00.407572Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:ada952110eca2f65d124781d43c3874132dafa1b497cbe81f739a9f22b5ab5cc","observation_id":"78432bbc-de10-4795-b600-d5db6d39f209","resolution":{"observed_at":"2026-08-07T11:14:02.047227Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:01.625938Z","title":"Thinking Like Transformers","venue":null,"work_id":"fa12ef9c-a22b-4766-b1c3-50f073cc66e8","year":null},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T11:14:00.586181Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:4077ff2934555981e5d871478b72ed260043b219b9d2bec3cf6429c578693a06","observation_id":"eb371ab5-1b1b-4c69-92fa-0f1ba2de0452","resolution":{"observed_at":"2026-08-07T11:14:01.794736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:01.284858Z","title":"Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages, May 2024","venue":null,"work_id":"37a59ec1-0c0e-44d4-bf57-e30fe73a0c65","year":2024},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:14:00.705347Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:7402e11987a4bae5f459e2eeb82b7a58c938e39a57bcb0e532aa30ee012cbfe5","observation_id":"c3709c9b-9ec1-4e6d-9be2-8d5929f5e05b","resolution":{"observed_at":"2026-08-07T11:14:01.490730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:14:01.021170Z","title":"Self-attention networks can process bounded hierarchical languages","venue":null,"work_id":"127dbafb-fd39-436d-83de-c789d5a139fa","year":2021},"citing_paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T11:14:00.876685Z"},"links":{"citing_paper":"/paper/2506.03370"},"observation_digest":"sha256:12287277bc38ed7680f0038f1cdbd7bd6a6429019d32b095120b9578a3e5094e","observation_id":"07d8d2ea-89e9-4964-885e-ed0c1538f269","resolution":{"observed_at":"2026-08-07T11:14:01.154027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.03370","last_updated":"2025-06-03T20:28:51Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T11:02:25.090043Z","submitted_at":"2025-06-03T20:28:51Z","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize"},"reference_resolution":{"displayed":13,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":1,"verified_exact":0,"verified_fuzzy":12},"total_outbound_references":13},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2506.03370."}