{"as_of":"2026-08-08T11:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0647c9027d36e7e1696e71474fdb5af5c6107e661e18a291dafae16bb425cac8","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":9,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":9,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":9,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":9,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:59:34.563333Z","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":"2026-06-30T08:04:28.747447Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2210.09545","last_updated":"2022-10-18T02:44:38Z","snapshot_observed_at":"2026-08-05T13:58:01.838826Z","submitted_at":"2022-10-18T02:44:38Z","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","version":1},"cited_work":{"arxiv_id":"2210.09545","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2210.09545","snapshot_observed_at":"2026-06-30T08:04:28.747447Z","title":"messages","venue":null,"work_id":"12b68f9c-23b0-49f9-b26e-bf100da80eb9","year":2022},"citing_paper":{"arxiv_id":"2309.10253","last_updated":"2024-06-27T16:01:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-19T02:19:48Z","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","version":4},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-05-15T06:25:20.966510Z"},"links":{"cited_paper":"/paper/2210.09545","citing_paper":"/paper/2309.10253"},"observation_digest":"sha256:9d3b03889903ae9219da66c5204f7fe772074e488b2a27959edf5d69584a7be6","observation_id":"f769a2be-802e-49d2-a148-cb62a1571138","resolution":{"observed_at":"2026-05-15T06:25:21.156152Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":{"arxiv_id":"2210.09545","last_updated":"2022-10-18T02:44:38Z","snapshot_observed_at":"2026-08-05T13:58:01.838826Z","submitted_at":"2022-10-18T02:44:38Z","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.09545","snapshot_observed_at":"2026-08-07T05:59:34.563333Z","title":"arXiv preprint arXiv:2210.09545(2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06518","last_updated":"2025-06-06T20:32:43Z","snapshot_observed_at":"2026-08-07T05:52:43.506241Z","submitted_at":"2025-06-06T20:32:43Z","title":"A Systematic Review of Poisoning Attacks Against Large Language Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T05:59:34.563333Z"},"links":{"cited_paper":"/paper/2210.09545","citing_paper":"/paper/2506.06518"},"observation_digest":"sha256:78ae42f11d62e297759fc3891bfb5c090763bd933ba1a0717db907599863e69d","observation_id":"66ceb03c-a844-4b5a-8429-cb423a7a5078","resolution":{"observed_at":"2026-08-07T05:59:34.563333Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.09545","last_updated":"2022-10-18T02:44:38Z","snapshot_observed_at":"2026-08-05T13:58:01.838826Z","submitted_at":"2022-10-18T02:44:38Z","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.09545","snapshot_observed_at":"2026-08-06T16:24:30.487336Z","title":"Fine-mixing: Mitigating backdoors in fine-tuned language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.13629","last_updated":"2025-07-18T03:41:18Z","snapshot_observed_at":"2026-08-07T10:03:57.005879Z","submitted_at":"2025-07-18T03:41:18Z","title":"Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques","version":1},"reference_index":181,"source":"pdf_text","source_observed_at":"2026-08-06T16:24:30.487336Z"},"links":{"cited_paper":"/paper/2210.09545","citing_paper":"/paper/2507.13629"},"observation_digest":"sha256:453f3056eca551ef2e8da7e93111246982b565154d3338d3c76aca968dec009a","observation_id":"18ef200f-a70b-47a0-9df2-6a583814239e","resolution":{"observed_at":"2026-08-06T16:24:30.487336Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.09545","last_updated":"2022-10-18T02:44:38Z","snapshot_observed_at":"2026-08-05T13:58:01.838826Z","submitted_at":"2022-10-18T02:44:38Z","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.09545","snapshot_observed_at":"2026-08-05T14:42:31.551978Z","title":"Fine-mixing: Mitigating back- doors in fine-tuned language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.21004","last_updated":"2025-08-28T17:05:18Z","snapshot_observed_at":"2026-08-07T06:34:15.037429Z","submitted_at":"2025-08-28T17:05:18Z","title":"Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T14:42:31.551978Z"},"links":{"cited_paper":"/paper/2210.09545","citing_paper":"/paper/2508.21004"},"observation_digest":"sha256:a0dbb624153e70d2198e7ebce55ca66d87e0665343a67d2acefbc0693113a1df","observation_id":"1dc43788-7721-4823-9d0f-612704c4b474","resolution":{"observed_at":"2026-08-05T14:42:31.551978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.09545","last_updated":"2022-10-18T02:44:38Z","snapshot_observed_at":"2026-08-05T13:58:01.838826Z","submitted_at":"2022-10-18T02:44:38Z","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","version":1},"cited_work":{"arxiv_id":"2210.09545","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2210.09545","snapshot_observed_at":"2026-06-30T08:04:28.747447Z","title":"messages","venue":null,"work_id":"12b68f9c-23b0-49f9-b26e-bf100da80eb9","year":2022},"citing_paper":{"arxiv_id":"2511.13789","last_updated":"2025-11-16T15:26:50Z","snapshot_observed_at":"2026-07-06T22:36:08.495952Z","submitted_at":"2025-11-16T15:26:50Z","title":"Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-17T22:01:09.858921Z"},"links":{"cited_paper":"/paper/2210.09545","citing_paper":"/paper/2511.13789"},"observation_digest":"sha256:411dd22f0cb26a530d4dcac62d4797129dc21fae0d24d79d0af464511af390de","observation_id":"62a5fc8b-95a8-434c-a918-a514f3b50bbe","resolution":{"observed_at":"2026-05-17T22:02:08.627638Z","resolver_source":"arxiv_id","status":"verified_exact"},"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":{"arxiv_id":"2210.09545","last_updated":"2022-10-18T02:44:38Z","snapshot_observed_at":"2026-08-05T13:58:01.838826Z","submitted_at":"2022-10-18T02:44:38Z","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.09545","snapshot_observed_at":"2026-08-03T18:08:07.581777Z","title":"InACL, pages 1441–1451","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.06899","last_updated":"2026-06-18T07:18:15Z","snapshot_observed_at":"2026-08-08T07:35:15.892357Z","submitted_at":"2025-12-07T15:51:56Z","title":"Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T18:08:07.581777Z"},"links":{"cited_paper":"/paper/2210.09545","citing_paper":"/paper/2512.06899"},"observation_digest":"sha256:03a7275af7a1eb412420eb0cbab2bd479a83d945ce73be125d729f8b3c170bbd","observation_id":"680ba610-dad7-4b01-9447-52f6936411cf","resolution":{"observed_at":"2026-08-03T18:08:07.581777Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.09545","last_updated":"2022-10-18T02:44:38Z","snapshot_observed_at":"2026-08-05T13:58:01.838826Z","submitted_at":"2022-10-18T02:44:38Z","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","version":1},"cited_work":{"arxiv_id":"2210.09545","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2210.09545","snapshot_observed_at":"2026-06-30T08:04:28.747447Z","title":"messages","venue":null,"work_id":"12b68f9c-23b0-49f9-b26e-bf100da80eb9","year":2022},"citing_paper":{"arxiv_id":"2605.12529","last_updated":"2026-04-15T10:56:08Z","snapshot_observed_at":"2026-08-01T15:54:04.993991Z","submitted_at":"2026-04-15T10:56:08Z","title":"BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-14T21:01:10.756844Z"},"links":{"cited_paper":"/paper/2210.09545","citing_paper":"/paper/2605.12529"},"observation_digest":"sha256:ec5aafc39ac84d7724c7ce2689eade406724686413f8956b75272f4a1d015273","observation_id":"26e22186-fe39-4dba-b99b-97c81c1c6e82","resolution":{"observed_at":"2026-05-14T21:02:58.931015Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":{"arxiv_id":"2210.09545","last_updated":"2022-10-18T02:44:38Z","snapshot_observed_at":"2026-08-05T13:58:01.838826Z","submitted_at":"2022-10-18T02:44:38Z","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","version":1},"cited_work":{"arxiv_id":"2210.09545","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2210.09545","snapshot_observed_at":"2026-06-30T08:04:28.747447Z","title":"messages","venue":null,"work_id":"12b68f9c-23b0-49f9-b26e-bf100da80eb9","year":2022},"citing_paper":{"arxiv_id":"2606.29239","last_updated":"2026-08-03T15:22:02Z","snapshot_observed_at":"2026-08-06T23:31:35.878215Z","submitted_at":"2026-06-28T07:06:46Z","title":"Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-06-30T07:47:18.350953Z"},"links":{"cited_paper":"/paper/2210.09545","citing_paper":"/paper/2606.29239"},"observation_digest":"sha256:af3a42848235cf4ca426e15860a70ac2f9238873fc239ddfcfdb790a40102041","observation_id":"80a1cb2f-a269-4774-828b-dbbc367d7bb9","resolution":{"observed_at":"2026-06-30T08:04:28.749090Z","resolver_source":"arxiv_id","status":"verified_exact"},"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":{"arxiv_id":"2210.09545","last_updated":"2022-10-18T02:44:38Z","snapshot_observed_at":"2026-08-05T13:58:01.838826Z","submitted_at":"2022-10-18T02:44:38Z","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.09545","snapshot_observed_at":"2026-08-04T04:39:06.938899Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.29239","last_updated":"2026-08-03T15:22:02Z","snapshot_observed_at":"2026-08-06T23:31:35.878215Z","submitted_at":"2026-06-28T07:06:46Z","title":"Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-04T04:39:06.938899Z"},"links":{"cited_paper":"/paper/2210.09545","citing_paper":"/paper/2606.29239"},"observation_digest":"sha256:c89a7e285176bccd0a13eb31e71c5fc48a868078500e53d133a43ab26b4506b7","observation_id":"31690c6c-4c21-4b05-a511-bc5304e931fd","resolution":{"observed_at":"2026-08-04T04:39:06.938899Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2210.09545/citation-record","integrity":"/paper/2210.09545/integrity","json":"/paper/2210.09545/citation-record.json","paper":"/paper/2210.09545"},"outbound":[],"paper":{"arxiv_id":"2210.09545","last_updated":"2022-10-18T02:44:38Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T13:58:01.838826Z","submitted_at":"2022-10-18T02:44:38Z","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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 0 of 0 outbound references and 9 inbound Pith citation observations for arXiv:2210.09545."}