{"as_of":"2026-08-09T11:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fca62bca154f2c30325a1fa6b54f1b7366fbb4adcd040435aa678c6d261c9085","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T08:27:42.318740Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T10:13:22.669056Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-01T14:05:46.811014Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"cited_work":{"arxiv_id":"2601.17178","doi":null,"metadata_source":"pith","pith_arxiv_id":"2601.17178","snapshot_observed_at":"2026-07-01T14:05:46.811014Z","title":"TrojanGYM: A detector- in-the-loop LLM for adaptive RTL hardware Trojan insertion","venue":"cs.CR","work_id":"ecc5da66-3fa6-4f4d-a12a-22857e897173","year":2026},"citing_paper":{"arxiv_id":"2605.10807","last_updated":"2026-06-04T15:08:08Z","snapshot_observed_at":"2026-07-06T23:22:42.512039Z","submitted_at":"2026-05-11T16:31:14Z","title":"LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-12T03:57:51.577486Z"},"links":{"cited_paper":"/paper/2601.17178","citing_paper":"/paper/2605.10807"},"observation_digest":"sha256:ace2e6c435eec16a2b2caa921b591005a790808f5001cc460f9f93fd3eb31a0b","observation_id":"cf27f86d-59e7-4ce8-a63b-7f3db6fe648c","resolution":{"observed_at":"2026-06-23T04:13:44.037980Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"cited_work":{"arxiv_id":"2601.17178","doi":null,"metadata_source":"pith","pith_arxiv_id":"2601.17178","snapshot_observed_at":"2026-07-01T14:05:46.811014Z","title":"TrojanGYM: A detector- in-the-loop LLM for adaptive RTL hardware Trojan insertion","venue":"cs.CR","work_id":"ecc5da66-3fa6-4f4d-a12a-22857e897173","year":2026},"citing_paper":{"arxiv_id":"2605.10807","last_updated":"2026-06-04T15:08:08Z","snapshot_observed_at":"2026-07-06T23:22:42.512039Z","submitted_at":"2026-05-11T16:31:14Z","title":"LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-14T21:12:08.821202Z"},"links":{"cited_paper":"/paper/2601.17178","citing_paper":"/paper/2605.10807"},"observation_digest":"sha256:676750997e9ea8be73b243a12c19fa73bd3851846411a90fd0bcb78799c4e9e0","observation_id":"812cde26-71c7-4116-b5df-7bd29e2e140b","resolution":{"observed_at":"2026-06-23T04:13:44.037980Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"cited_work":{"arxiv_id":"2601.17178","doi":null,"metadata_source":"pith","pith_arxiv_id":"2601.17178","snapshot_observed_at":"2026-07-01T14:05:46.811014Z","title":"TrojanGYM: A detector- in-the-loop LLM for adaptive RTL hardware Trojan insertion","venue":"cs.CR","work_id":"ecc5da66-3fa6-4f4d-a12a-22857e897173","year":2026},"citing_paper":{"arxiv_id":"2605.10807","last_updated":"2026-06-04T15:08:08Z","snapshot_observed_at":"2026-07-06T23:22:42.512039Z","submitted_at":"2026-05-11T16:31:14Z","title":"LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-21T08:58:25.469021Z"},"links":{"cited_paper":"/paper/2601.17178","citing_paper":"/paper/2605.10807"},"observation_digest":"sha256:e12f5288634807e1341944bc3be65a59781abdd030b8c6da79139aeaef95b9a7","observation_id":"848bdbb9-b9fb-458a-8c6f-9f0fbb239357","resolution":{"observed_at":"2026-06-23T04:13:44.037980Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"cited_work":{"arxiv_id":"2601.17178","doi":null,"metadata_source":"pith","pith_arxiv_id":"2601.17178","snapshot_observed_at":"2026-07-01T14:05:46.811014Z","title":"TrojanGYM: A detector- in-the-loop LLM for adaptive RTL hardware Trojan insertion","venue":"cs.CR","work_id":"ecc5da66-3fa6-4f4d-a12a-22857e897173","year":2026},"citing_paper":{"arxiv_id":"2605.10807","last_updated":"2026-06-04T15:08:08Z","snapshot_observed_at":"2026-07-06T23:22:42.512039Z","submitted_at":"2026-05-11T16:31:14Z","title":"LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-30T22:18:09.663488Z"},"links":{"cited_paper":"/paper/2601.17178","citing_paper":"/paper/2605.10807"},"observation_digest":"sha256:2ec40905306c52ca77d212db43313becd063e8b2df24ed8106a2d7c29510f1ed","observation_id":"1ab5e979-061e-4155-93b6-f7f20f78af06","resolution":{"observed_at":"2026-07-01T14:05:46.812375Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.17178","snapshot_observed_at":"2026-08-06T10:13:22.669056Z","title":"TrojanGYM: A detector-in-the-loop LLM for adaptive RTL hardware Trojan insertion,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.05063","last_updated":"2026-08-05T17:09:13Z","snapshot_observed_at":"2026-08-08T23:13:52.254894Z","submitted_at":"2026-08-05T17:09:13Z","title":"Hardware Design and Security in the Era of Chiplets and LLMs","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T10:13:22.669056Z"},"links":{"cited_paper":"/paper/2601.17178","citing_paper":"/paper/2608.05063"},"observation_digest":"sha256:190d4ee1bf5192d66d765f43ecbb1f293e96f534aa4a6aea1a50867fb7a43074","observation_id":"596b3393-bc63-4202-910b-a7718bb178f9","resolution":{"observed_at":"2026-08-06T10:13:22.669056Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2601.17178/citation-record","integrity":"/paper/2601.17178/integrity","json":"/paper/2601.17178/citation-record.json","paper":"/paper/2601.17178"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T08:27:42.142958Z","title":"Hardware trojan detection using path delay fingerprint,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.142958Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:066c30be2a92372338e3db433bec0c0c070672e91bf44dcd9316e20bcbbd49bb","observation_id":"499e9a8a-3e2f-4946-814e-2284bdc03dca","resolution":{"observed_at":"2026-08-03T08:27:42.142958Z","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":"2026-08-03T08:27:42.148341Z","title":"Scalable detection of hardware trojans using ATPG-based activation of rare events,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.148341Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:372b29ea45303e2076991990c9fdbcdecf334b09ae63e9c46a5f8b80f3efbdf0","observation_id":"dc1c1d6c-1366-4311-984b-eaf40e8c81b7","resolution":{"observed_at":"2026-08-03T08:27:42.148341Z","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":"2026-08-03T08:27:42.153465Z","title":"Gnn4tj: Graph neural networks for hardware trojan detection at register transfer level,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.153465Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:f4fa875d251d7532939a883dc8b2fdbabb4fb7d3f618c58bbdc7e3f10f25fd26","observation_id":"2f0a1ce0-f9d6-4f39-8ae0-bdb2fea916b5","resolution":{"observed_at":"2026-08-03T08:27:42.153465Z","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":"2026-08-03T08:27:42.158576Z","title":"HW2VEC: A graph learning tool for automating hardware security,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.158576Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:b206347e1a74ec64e152c5838f42bcc66f965e99b5951ce579b6690c50ec9915","observation_id":"fdcf136d-af8d-4189-996a-675ea0d5a13e","resolution":{"observed_at":"2026-08-03T08:27:42.158576Z","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":"2026-08-03T08:27:42.163402Z","title":"Graph neural networks for integrated circuit design, reliability, and security: Survey and tool,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.163402Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:f7b78c7f4aedebad277241284b72f14c55a4479bf587dd922b4231d4ddbbd6f8","observation_id":"6615f884-f048-4f28-a237-4cc5d18d2b0f","resolution":{"observed_at":"2026-08-03T08:27:42.163402Z","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":"2026-08-03T08:27:42.168448Z","title":"Trust-hub chip-level trojan benchmarks,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.168448Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:43a9d7b987da22770c819628fa28b94abbf4dc4f36aa6c34ae3c5192d2c6ab51","observation_id":"53aa64e9-97fb-421e-a776-cc7a6e43c10e","resolution":{"observed_at":"2026-08-03T08:27:42.168448Z","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":"2026-08-03T08:27:42.173150Z","title":"Sand: A self-supervised and adaptive nas-driven framework for hardware trojan detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.173150Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:a45c3bd9eb3f5bbdaf3afa704d746647f2451353569da351fe02175c29561f4b","observation_id":"54352cc4-21f8-4ae5-8048-90c754fdaf53","resolution":{"observed_at":"2026-08-03T08:27:42.173150Z","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":"2026-08-03T08:27:42.179129Z","title":"Attrition: Attacking static hardware trojan detection techniques using reinforcement learn- ing,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.179129Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:8152c8d609e7e7023bef52b91e5fc4d9359a55ef36fd645acbf9056e7d7d7663","observation_id":"90729a0c-573d-42bc-b3e6-6109fd8ca2f7","resolution":{"observed_at":"2026-08-03T08:27:42.179129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15184","last_updated":"2024-12-08T22:10:15Z","snapshot_observed_at":"2026-07-06T18:19:04.614208Z","submitted_at":"2024-05-24T03:37:32Z","title":"TrojanForge: Generating Adversarial Hardware Trojan Examples Using Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15184","snapshot_observed_at":"2026-08-03T08:27:42.184229Z","title":"Trojanforge: Adversarial hardware trojan examples with reinforcement learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.184229Z"},"links":{"cited_paper":"/paper/2405.15184","citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:0e791fcb7d5f1fdba8c481262e79af49d823e84be527aee1ef4dca445ef0d068","observation_id":"6e4028e1-2a5c-4a6f-a9ad-4d206001d12f","resolution":{"observed_at":"2026-08-03T08:27:42.184229Z","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":"2026-08-03T08:27:42.190160Z","title":"Netdetox: Adversarial and efficient evasion of hardware- security gnns via rl-llm orchestration,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.190160Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:6a2ee75663cd955a6c3258947083427c18cfb0c042fa36c4674f072eb954e2cb","observation_id":"e1652a65-7dcf-4f67-ad5f-a6380690d62b","resolution":{"observed_at":"2026-08-03T08:27:42.190160Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.08580","last_updated":"2022-04-18T22:36:13Z","snapshot_observed_at":"2026-07-06T13:01:26.958634Z","submitted_at":"2022-04-18T22:36:13Z","title":"Automatic Hardware Trojan Insertion using Machine Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.08580","snapshot_observed_at":"2026-08-03T08:27:42.196152Z","title":"Auto- matic hardware trojan insertion using machine learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.196152Z"},"links":{"cited_paper":"/paper/2204.08580","citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:e413ab1258703ca86b7efdf8ee3d1ac225b1d334414c5ebed0a7d26ad9ea8256","observation_id":"d6daadef-eec9-4483-ab6f-7e37b50e68e3","resolution":{"observed_at":"2026-08-03T08:27:42.196152Z","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":"2026-08-03T08:27:42.201508Z","title":"An automated configurable trojan insertion framework for dynamic trust benchmarks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.201508Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:6ed2f4da29ce3de15472f105b2a5a50ce37e8fbf1cff5a773a7de0d0a0effefa","observation_id":"2e5f7ae7-9976-4d17-8a3c-caa78d5ea4ae","resolution":{"observed_at":"2026-08-03T08:27:42.201508Z","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":"2026-08-03T08:27:42.207009Z","title":"Taint: Tool for automated insertion of trojans,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.207009Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:75ccf5f2adcb1e7eb75b0438a076c9cef32aa9a167b546d4a4432f40219f8f75","observation_id":"94c57602-0acc-49b4-aeac-d57d0cedefe3","resolution":{"observed_at":"2026-08-03T08:27:42.207009Z","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":"2026-08-03T08:27:42.213267Z","title":"Feint: Automated framework for efficient insertion of templates/trojans into fpgas,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.213267Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:b7727fbdb2d84d3f49f11cb600d74fe55fb51b26d40b51b22c89b7ee6eea47ad","observation_id":"c627bb8e-0b8d-4017-8f95-0a01789bff8d","resolution":{"observed_at":"2026-08-03T08:27:42.213267Z","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":"2026-08-03T08:27:42.218655Z","title":"Verigen: A large language model for verilog code generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.218655Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:0bbe2c67a5df957f9a79014455a8b855b750cf0037525cc0615f9c8456f714c8","observation_id":"815eb94f-39e0-4534-88b6-01c246061e9f","resolution":{"observed_at":"2026-08-03T08:27:42.218655Z","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":"2026-08-03T08:27:42.223169Z","title":"Llms and the future of chip design: Unveiling security risks and building trust,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.223169Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:531183c249868665f43dd3ed5953752bec726c6fe542e08e820077bb04405bb6","observation_id":"efabe223-fe81-467d-b67c-7d2b92b3ad16","resolution":{"observed_at":"2026-08-03T08:27:42.223169Z","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":"2026-08-03T08:27:42.229119Z","title":"Lockforge: Automating paper-to-code for logic locking with multi- agent reasoning llms,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.229119Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:8ad9ffbfa80249549a0c41fa47dbc7b4ffaf31176b09a1b1c3770a59212df6b3","observation_id":"f7298ec9-3e16-473f-9a8c-5bd110d51238","resolution":{"observed_at":"2026-08-03T08:27:42.229119Z","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":"2026-08-03T08:27:42.234434Z","title":"Chip-chat: Chal- lenges and opportunities in conversational hardware design,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.234434Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:5a65416aca23dc4db9efc56f5d631e82f7fb12ef24805fdd1b4669a98f8bc855","observation_id":"96c046c4-4493-4b00-b58d-3fdba5d37074","resolution":{"observed_at":"2026-08-03T08:27:42.234434Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.15697","last_updated":"2025-05-28T09:28:39Z","snapshot_observed_at":"2026-08-08T06:04:11.364613Z","submitted_at":"2025-05-28T09:28:39Z","title":"DeepRTL2: A Versatile Model for RTL-Related Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.15697","snapshot_observed_at":"2026-08-03T08:27:42.239186Z","title":"Deeprtl2: A versatile model for rtl-related tasks,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.239186Z"},"links":{"cited_paper":"/paper/2506.15697","citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:ba94792b396cf071d95ba168732670608ca2fd2a0ffe0200bd02da3e332a54a0","observation_id":"a7f30305-1458-4a63-b28c-cfdb46d53e12","resolution":{"observed_at":"2026-08-03T08:27:42.239186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.13572","last_updated":"2025-06-12T13:18:06Z","snapshot_observed_at":"2026-08-07T16:58:08.744209Z","submitted_at":"2025-03-17T12:26:49Z","title":"VeriContaminated: Assessing LLM-Driven Verilog Coding for Data Contamination","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.13572","snapshot_observed_at":"2026-08-03T08:27:42.243958Z","title":"Vericontaminated: Assessing llm- driven verilog coding for data contamination,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.243958Z"},"links":{"cited_paper":"/paper/2503.13572","citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:c42f991e214e67c277ea34d265f5f02a3119e4940b1aeee2dc2a205c5f0e9207","observation_id":"0ac6c3d6-7e0c-476b-9761-e443274c728b","resolution":{"observed_at":"2026-08-03T08:27:42.243958Z","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":"2026-08-03T08:27:42.248819Z","title":"Gllamor: Graph-based logic locking by large language models for enhanced robustness,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.248819Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:e608a7743f407a5b326209c323bf19932ce3a245e776d754141b3ba4fea8f732","observation_id":"03d9f9d4-6958-4ad4-9555-d60eff837e66","resolution":{"observed_at":"2026-08-03T08:27:42.248819Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.13116","last_updated":"2025-06-17T20:35:13Z","snapshot_observed_at":"2026-08-07T16:58:07.004396Z","submitted_at":"2025-03-17T12:38:03Z","title":"VeriLeaky: Navigating IP Protection vs Utility in Fine-Tuning for LLM-Driven Verilog Coding","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.13116","snapshot_observed_at":"2026-08-03T08:27:42.253279Z","title":"Verileaky: Navigating ip protection vs utility in fine-tuning for llm-driven verilog coding,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.253279Z"},"links":{"cited_paper":"/paper/2503.13116","citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:dc6bd65807562f416cafaab81ddea7b7bc3d313d043b3c562a9dcc38b568ae32","observation_id":"982ddc5e-a566-405b-a35d-1d0eb7bf9e33","resolution":{"observed_at":"2026-08-03T08:27:42.253279Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.12352","last_updated":"2024-07-17T07:13:06Z","snapshot_observed_at":"2026-07-06T18:47:37.971415Z","submitted_at":"2024-07-17T07:13:06Z","title":"SENTAUR: Security EnhaNced Trojan Assessment Using LLMs Against Undesirable Revisions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.12352","snapshot_observed_at":"2026-08-03T08:27:42.258152Z","title":"SENTAUR: Security enhanced trojan assessment using LLMs against undesirable revisions,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.258152Z"},"links":{"cited_paper":"/paper/2407.12352","citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:c19517aa8eba356ca64decb3f75bdfaed729d120717dddbcbd7ec322175cf934","observation_id":"38d14b54-9841-4eba-8148-1d083bd58498","resolution":{"observed_at":"2026-08-03T08:27:42.258152Z","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":"10.3390/data9060082","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Hardware trojan dataset of RISC-V and Web3 generated with ChatGPT-4,","venue":"Data","work_id":"77544ba0-43b9-4500-bcab-71c9c50c4d58","year":2024},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.263106Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:9b50513e22b2e963b5279f234c019f8a22a985d9726575536471b337930c2d3d","observation_id":"d048fb4e-1537-4924-9906-9a008c734862","resolution":{"observed_at":"2026-08-03T08:29:44.074159Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-03T08:27:42.267572Z","title":"Unleashing ghost: An llm-powered framework for automated hardware trojan design,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.267572Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:70c378c973c77bec9754a464bb181923d00fb8270b86a2c3dc7024df16f305ae","observation_id":"cfd055e3-041e-4392-a2a9-4c727aa18455","resolution":{"observed_at":"2026-08-03T08:27:42.267572Z","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":"2026-08-03T08:27:42.272409Z","title":"Dtjrtl: A configurable framework for automated hardware trojan insertion at rtl,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.272409Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:ae814078f1598ad80c7b18de39161787201a9cf5704947f1722fd94defddee53","observation_id":"85615c42-45d2-4ee7-8df0-3465f66fca2c","resolution":{"observed_at":"2026-08-03T08:27:42.272409Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.09592","last_updated":"2024-03-20T20:28:48Z","snapshot_observed_at":"2026-08-08T16:08:20.331173Z","submitted_at":"2023-05-16T16:42:07Z","title":"Trojan Playground: A Reinforcement Learning Framework for Hardware Trojan Insertion and Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.09592","snapshot_observed_at":"2026-08-03T08:27:42.276959Z","title":"Trojan playground: a reinforcement learning framework for hardware trojan insertion and detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.276959Z"},"links":{"cited_paper":"/paper/2305.09592","citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:6677d0c03dbdf898ac0dd012447d542480729c84c0b2e10ca72b51533240aa55","observation_id":"cabf6074-42cf-4ee2-9d16-d53a97e9d8a6","resolution":{"observed_at":"2026-08-03T08:27:42.276959Z","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":"2026-08-03T08:27:42.282693Z","title":"{AttackGNN}:{Red-Teaming}{GNNs}in hardware security using reinforcement learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.282693Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:549b80c7be1be14bd90a48ecee36ec92e148bb235e91616753c59a05a671b179","observation_id":"0aa4f397-b386-436b-a3c8-a623aac1b844","resolution":{"observed_at":"2026-08-03T08:27:42.282693Z","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":"2026-08-03T08:27:42.286951Z","title":"Trojansaint: Gate-level netlist sampling-based inductive learning for hardware trojan detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.286951Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:6446d0327ac87d9524c33e9e2f095b410f736d59cae9283ca47c3c952755662e","observation_id":"133b9f77-9f67-44ea-bfa2-a0c85669389e","resolution":{"observed_at":"2026-08-03T08:27:42.286951Z","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":"2026-08-03T08:27:42.291622Z","title":"Rtl-breaker: Assessing the security of llms against backdoor attacks on hdl code generation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.291622Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:b16040cc8f5f3b782e0957a7e408e78f5091c7511d21fcae6556e8ee3a339ff4","observation_id":"8f0a26e0-4b31-4808-86aa-1a36601fd917","resolution":{"observed_at":"2026-08-03T08:27:42.291622Z","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":"2026-08-03T08:27:42.295836Z","title":"Salad: Systematic as- sessment of machine unlearing on llm-aided hardware design,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.295836Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:82d54b4ecbb3518e9cdc10e17f7e51647e9d41b24457977fab7089227410d184","observation_id":"6ee7e2e5-46f2-439a-ae33-ea806bde4736","resolution":{"observed_at":"2026-08-03T08:27:42.295836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.07636","last_updated":"2024-12-10T16:16:22Z","snapshot_observed_at":"2026-07-06T20:04:43.926718Z","submitted_at":"2024-12-10T16:16:22Z","title":"TrojanWhisper: Evaluating Pre-trained LLMs to Detect and Localize Hardware Trojans","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.07636","snapshot_observed_at":"2026-08-03T08:27:42.300254Z","title":"Tro- janwhisper: Evaluating pre-trained llms to detect and localize hardware trojans,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.300254Z"},"links":{"cited_paper":"/paper/2412.07636","citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:08692424c0b196f80a181cbcf298a7b5717c618b9bfdd58cd5a8bbd5e6db9245","observation_id":"220ba3ef-e75e-43fa-af9f-2691dccdfd58","resolution":{"observed_at":"2026-08-03T08:27:42.300254Z","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":"2026-08-03T08:27:42.305063Z","title":"Netlam: An automated llm framework to generate and evaluate stealthy hardware trojans,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.305063Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:57e87db965322b085e07319c410825eabc511fcbcfaea7ec8ac5d9c69952c4c9","observation_id":"c4dcaca7-3c43-4666-a8e9-5e2c76cc5a20","resolution":{"observed_at":"2026-08-03T08:27:42.305063Z","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":"2026-08-03T08:27:42.309357Z","title":"Latent: Leveraging automated test pattern generation for hardware trojan detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.309357Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:1b5cd90ad65a2b1325cceaf99584eed2baeb572c160b03dc62fbf96a188fb693","observation_id":"08e89058-e501-43aa-a4e9-dfc8c037fb0b","resolution":{"observed_at":"2026-08-03T08:27:42.309357Z","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":"2026-08-03T08:27:42.313919Z","title":"Trojanloc: Llm-based framework for rtl trojan localization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.313919Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:7b22ee6417e8eac06c739ecb6a879829a2bde897cb70d64d1041c4b8f790c83e","observation_id":"2c74c824-ed85-4b9f-934e-4bc690a84f99","resolution":{"observed_at":"2026-08-03T08:27:42.313919Z","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":"2026-08-03T08:27:42.318740Z","title":"Verigen: A large language model for verilog code generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T08:27:42.318740Z"},"links":{"citing_paper":"/paper/2601.17178"},"observation_digest":"sha256:2efa29706ca52c28f1d76a53eb19f10d42684e93a040ceadd3e8a3f18eecfc77","observation_id":"09e9c4e5-ff47-45dd-b5ec-d3e748016bf2","resolution":{"observed_at":"2026-08-03T08:27:42.318740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2601.17178","last_updated":"2026-06-22T11:58:15Z","latest_version":2,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-08T06:04:38.302492Z","submitted_at":"2026-01-23T21:11:44Z","title":"TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":35,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":36},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 5 inbound Pith citation observations for arXiv:2601.17178."}