{"as_of":"2026-08-10T02:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:640b0b9b2b88753b49debca650ac9ac68dc15d7c3f278cc49bb78a2cd68b6e3e","coverage":[{"denominator":60,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":60,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T07:22:09.743961Z","state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2510.27313/citation-record","integrity":"/paper/2510.27313/integrity","json":"/paper/2510.27313/citation-record.json","paper":"/paper/2510.27313"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T07:22:01.796716Z","title":"Towards tracing knowledge in language models back to the training data","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:01.796716Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:e1945bf2e74138a7dfdcb8f2594778b593d15c60e1eb794a5291e09b45d5147e","observation_id":"7057e73c-ff38-4ddb-b10a-56800f576849","resolution":{"observed_at":"2026-08-04T07:22:01.796716Z","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":"2026-08-04T07:22:01.934159Z","title":"Smollm-blazingly fast and remarkably powerful","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:01.934159Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:cf1360a1b9ab4fd38017f313d59afbef2d9467bc08b456d780f34b89630e4067","observation_id":"7f038324-75d4-4b73-b3b2-c76b90d0f3f1","resolution":{"observed_at":"2026-08-04T07:22:01.934159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.02737","last_updated":"2025-02-04T21:43:16Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-04T21:43:16Z","title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.02737","snapshot_observed_at":"2026-08-04T07:22:02.168632Z","title":"Smollm2: When smol goes big -- data-centric training of a small language model, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:02.168632Z"},"links":{"cited_paper":"/paper/2502.02737","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:2ffe658b7f5fc9c7c0983024c32239bc24d57cd1dd336646b63ca93395d00587","observation_id":"35f6c891-fe8d-4d93-8836-898eaf4272b8","resolution":{"observed_at":"2026-08-04T07:22:02.168632Z","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":"2026-08-04T07:22:02.364747Z","title":"If influence functions are the answer, then what is the question? Advances in Neural Information Processing Systems, 35: 0 17953--17967, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:02.364747Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:bc795e94cdf61a27369918467b2327460aefbe99c2e7c659cf50aedd7c948c55","observation_id":"63354f86-9774-4da2-b903-bc4f1837d279","resolution":{"observed_at":"2026-08-04T07:22:02.364747Z","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":"2026-08-04T07:22:02.464999Z","title":"Training data attribution via approximate unrolling","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:02.464999Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:1bd99586af26727ccc18d86e2336152c87f64459586b633df6cb7c6a2e3c86f0","observation_id":"e4685868-1c64-4cef-b683-d65c686b5aa9","resolution":{"observed_at":"2026-08-04T07:22:02.464999Z","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":"2026-08-04T07:22:02.584535Z","title":"Influence functions in deep learning are fragile","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:02.584535Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:da78bc045985aa5b5af6d8b983c688f934beeb7293afbeaa63e45a8533005394","observation_id":"20068405-b99d-4949-9a26-54f06608887b","resolution":{"observed_at":"2026-08-04T07:22:02.584535Z","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":"2026-08-04T07:22:02.744747Z","title":"Quantifying memorization across neural language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:02.744747Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:cdb9a8eb40e4feeb3dc038a81190a216aac6f789c96ed163cd9cb458e61d8fcb","observation_id":"ec2e9b65-39c7-4484-aaa4-b816a7a102d5","resolution":{"observed_at":"2026-08-04T07:22:02.744747Z","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":"2026-08-04T07:22:02.873525Z","title":"Scalable influence and fact tracing for large language model pretraining","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:02.873525Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:084b3a52bce4b66fd5c32f9ff8065dd48687514dafedf16d75213f36059c07ae","observation_id":"a96cdbc7-e339-4bdc-91a4-c458dc9c38b4","resolution":{"observed_at":"2026-08-04T07:22:02.873525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.13954","last_updated":"2024-05-22T19:39:05Z","snapshot_observed_at":"2026-08-03T22:27:29.954497Z","submitted_at":"2024-05-22T19:39:05Z","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.13954","snapshot_observed_at":"2026-08-04T07:22:02.954855Z","title":"What is your data worth to gpt? llm-scale data valuation with influence functions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:02.954855Z"},"links":{"cited_paper":"/paper/2405.13954","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:5c74d030c25cbbe089405e8caf38e7c6095a378b38b777b0cfcab1b048c86758","observation_id":"040c75cf-a3d6-4bb2-9784-bd68fe2671aa","resolution":{"observed_at":"2026-08-04T07:22:02.954855Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-07T01:45:38.840969Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-04T07:22:03.067482Z","title":"Training verifiers to solve math word problems","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:03.067482Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:5e0ef1b1184adebaad68c8ff9719ef346d943ff13b0309804c023ef9b9cfb216","observation_id":"e4b58db7-455c-47c1-a886-aa56d6b8c92c","resolution":{"observed_at":"2026-08-04T07:22:03.067482Z","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":"2026-08-04T07:22:03.204839Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:03.204839Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:f3763266a02567411900fe66a3b93f93ba35ebc13eb7af3de6a397eea32723ce","observation_id":"4c49077d-d6f4-4060-8ac8-b786c58b9285","resolution":{"observed_at":"2026-08-04T07:22:03.204839Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08281","last_updated":"2025-10-23T09:36:08Z","snapshot_observed_at":"2026-07-31T05:45:37.385210Z","submitted_at":"2024-01-16T11:12:36Z","title":"The Faiss library","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08281","snapshot_observed_at":"2026-08-04T07:22:03.345841Z","title":"The faiss library","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:03.345841Z"},"links":{"cited_paper":"/paper/2401.08281","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:5a235cb3deac8c313c30b790f975180dbba212d53ffbd4511fb83ef922467d25","observation_id":"d389c756-da16-40ed-b2d5-81761da4db20","resolution":{"observed_at":"2026-08-04T07:22:03.345841Z","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":"2026-08-04T07:22:03.512579Z","title":"Mmteb: Massive multilingual text embedding benchmark","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:03.512579Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:69173fc069be7cd341c54f46fdb99245d3e17679f29f1b8c2cca38ea24c42bdf","observation_id":"76b5ece1-fbf5-479d-9e12-0ed11568203b","resolution":{"observed_at":"2026-08-04T07:22:03.512579Z","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":"2026-08-04T07:22:03.617449Z","title":"Revisiting the fragility of influence functions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:03.617449Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:fa5d3e529f5911d36b1d7bb3d53f78f17260b5aadf3224f45d3356f5a2e30616","observation_id":"7f6512ee-ca37-45ff-9cdf-c6c86f179395","resolution":{"observed_at":"2026-08-04T07:22:03.617449Z","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":"2026-08-04T07:22:03.688721Z","title":"What neural networks memorize and why: Discovering the long tail via influence estimation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:03.688721Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:8aa1dd3cc508d04bb2d28fb154cb2a6ecbcbc66c016eea5fba29dbc0b373ca33","observation_id":"a5007c6e-2973-4308-94e3-a09c20c1ad8c","resolution":{"observed_at":"2026-08-04T07:22:03.688721Z","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":"2026-08-04T07:22:03.757380Z","title":"The language model evaluation harness, 07 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:03.757380Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:740358bec87a5e3ae231a6794efe311277d0f5774258a5dc2712c21847d53d81","observation_id":"83933c59-d09f-4010-b430-5b7555497179","resolution":{"observed_at":"2026-08-04T07:22:03.757380Z","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":"2026-08-04T07:22:03.854759Z","title":"A closer look at the limitations of instruction tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:03.854759Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:fbda06cbd514d847959ebdb62934db8134bed8abb789820804d81bbfccc6cb40","observation_id":"99040118-967d-43d6-accb-6da2b4ee0637","resolution":{"observed_at":"2026-08-04T07:22:03.854759Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.03405","last_updated":"2025-09-03T15:31:18Z","snapshot_observed_at":"2026-08-09T20:29:21.483677Z","submitted_at":"2025-09-03T15:31:18Z","title":"LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.03405","snapshot_observed_at":"2026-08-04T07:22:04.015766Z","title":"Lment: A suite for analyzing knowledge in language models from pretraining data to representations, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:04.015766Z"},"links":{"cited_paper":"/paper/2509.03405","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:1d5b85fff55402128ef4d59c122d7ed30f10b972af55574bd2ddb6547e3fcfa3","observation_id":"1bf76fea-cc1e-482c-a64d-c3574953aa30","resolution":{"observed_at":"2026-08-04T07:22:04.015766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03296","last_updated":"2023-08-07T04:47:42Z","snapshot_observed_at":"2026-08-09T11:08:40.708986Z","submitted_at":"2023-08-07T04:47:42Z","title":"Studying Large Language Model Generalization with Influence Functions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03296","snapshot_observed_at":"2026-08-04T07:22:04.219818Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:04.219818Z"},"links":{"cited_paper":"/paper/2308.03296","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:0683812bb553e1a72c3c33819ea016dbeca9fee0aadf27bafa1f5d4eca80509c","observation_id":"461b36d8-226a-4d1b-abb1-df2ce0f1774d","resolution":{"observed_at":"2026-08-04T07:22:04.219818Z","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":"2026-08-04T07:22:04.369134Z","title":"Fastif: Scalable influence functions for efficient model interpretation and debugging","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:04.369134Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:3e3bd09193e9d57328c1e3f262fc62bc93d4f08e523e13cbf0bdce0648efe448","observation_id":"131b9465-304e-4455-8292-cb760feb1186","resolution":{"observed_at":"2026-08-04T07:22:04.369134Z","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":"2026-08-04T07:22:04.512506Z","title":"Lighteval: A lightweight framework for llm evaluation, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:04.512506Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:7d382967b8419deb9630e8a0bd38a351c9bf45b796c697a2bb93aa3eda509bf8","observation_id":"53b20509-aeb8-4a65-bf96-5cd9742f8c8c","resolution":{"observed_at":"2026-08-04T07:22:04.512506Z","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":"2026-08-04T07:22:04.654817Z","title":"Training data influence analysis and estimation: a survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:04.654817Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:8c18289e4a21fd4b18f05b671745898c28de3c18a572ff8aec245b187d407e08","observation_id":"6ac03696-b350-4c37-af00-40c497c1bca7","resolution":{"observed_at":"2026-08-04T07:22:04.654817Z","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":"2026-08-04T07:22:04.860327Z","title":"The influence curve and its role in robust estimation","venue":null,"work_id":null,"year":1974},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:04.860327Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:4155049e36a9d98f320562955b9b63ab929a1e405de299ddc41c1ff635028094","observation_id":"02caca92-0bde-415e-9bce-7b53fcb0b00a","resolution":{"observed_at":"2026-08-04T07:22:04.860327Z","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":"2026-08-04T07:22:05.019500Z","title":"Data cleansing for models trained with sgd","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:05.019500Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:498461f5fc07968f49658fb436513b4b33b5d1bd88e061329d8725d0df754302","observation_id":"4eb12f7c-1cc5-4817-934a-1a23760d773a","resolution":{"observed_at":"2026-08-04T07:22:05.019500Z","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":"2026-08-04T07:22:05.204029Z","title":"Most influential subset selection: Challenges, promises, and beyond","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:05.204029Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:80579ea218d63df3f0f0e2612da88dcbc59ee45deb24f97fca6a16a006b3de65","observation_id":"2bef80c5-9478-488e-a413-fe6fc6283ae2","resolution":{"observed_at":"2026-08-04T07:22:05.204029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.16430","last_updated":"2025-04-23T05:32:37Z","snapshot_observed_at":"2026-08-07T16:00:00.424817Z","submitted_at":"2025-04-23T05:32:37Z","title":"MAGIC: Near-Optimal Data Attribution for Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.16430","snapshot_observed_at":"2026-08-04T07:22:05.367970Z","title":"Magic: Near-optimal data attribution for deep learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:05.367970Z"},"links":{"cited_paper":"/paper/2504.16430","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:7041b26414fb2f2a231025e6b7f528d600a1fd3a6ff1bd852ac80e5e99a45ae3","observation_id":"589b7f10-d0f3-4193-a0e8-645a5b32c470","resolution":{"observed_at":"2026-08-04T07:22:05.367970Z","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":"2026-08-04T07:22:05.518800Z","title":"Understanding black-box predictions via influence functions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:05.518800Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:58ca55984802a77770555a401f00fdd7d79782b7b405beea199273b2e99a76eb","observation_id":"08c3f432-415e-4edb-860f-d4c4a5b54425","resolution":{"observed_at":"2026-08-04T07:22:05.518800Z","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":"2026-08-04T07:22:05.695810Z","title":"Rouge: A package for automatic evaluation of summaries","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:05.695810Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:20d4b6262a8e93242a98eef86837c425ca73240486ac15fb470237c573ae5978","observation_id":"9a495442-1670-410f-8cd5-23663daaff3a","resolution":{"observed_at":"2026-08-04T07:22:05.695810Z","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":"2026-08-04T07:22:05.851123Z","title":"Truthfulqa: Measuring how models mimic human falsehoods","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:05.851123Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:8aa839ceaadec60c3b8e2337b2930c440c1db81cf3bb3a2a96a2d33d37958024","observation_id":"6391549b-e3f9-478d-9648-b27916ef2a8c","resolution":{"observed_at":"2026-08-04T07:22:05.851123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.07096","last_updated":"2025-07-08T00:56:11Z","snapshot_observed_at":"2026-08-07T16:07:06.415558Z","submitted_at":"2025-04-09T17:59:35Z","title":"OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.07096","snapshot_observed_at":"2026-08-04T07:22:06.014745Z","title":"Olmotrace: Tracing language model outputs back to trillions of training tokens","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:06.014745Z"},"links":{"cited_paper":"/paper/2504.07096","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:27fe09ff2f0e3e00bb5b1572a9cf005fd50cb23a4e9089d04a7991e360987f07","observation_id":"bf831371-c2d7-4d56-9a17-20d0d8f0e699","resolution":{"observed_at":"2026-08-04T07:22:06.014745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.17377","last_updated":"2025-04-07T17:59:50Z","snapshot_observed_at":"2026-08-08T02:05:38.594754Z","submitted_at":"2024-01-30T19:03:49Z","title":"Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.17377","snapshot_observed_at":"2026-08-04T07:22:06.164775Z","title":"Infini-gram: Scaling unbounded n-gram language models to a trillion tokens, 2025 b","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:06.164775Z"},"links":{"cited_paper":"/paper/2401.17377","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:64289a1e8b766b503468b72062e1d3b06e684997d3b7de234f010753eccc31fb","observation_id":"e0264989-7d06-43ef-9954-c1e87a805a77","resolution":{"observed_at":"2026-08-04T07:22:06.164775Z","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":"2026-08-04T07:22:06.294755Z","title":"How much do language models copy from their training data? evaluating linguistic novelty in text generation using raven","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:06.294755Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:1e5e79ec96360c68667bf8ad85a828006552f765ff21a1d8b15ff9a69406b1f9","observation_id":"1745a09c-6c79-4b38-9c5f-01be15b4e9f6","resolution":{"observed_at":"2026-08-04T07:22:06.294755Z","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":"2026-08-04T07:22:06.464750Z","title":"Evaluating n-gram novelty of language models using rusty-dawg","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:06.464750Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:158cec4cb2aa662875cf2ea78b43f985c2cde2d6077ef01ba8e6a06e1a403072","observation_id":"593920ad-9bbf-4e20-a63a-cb03f5570159","resolution":{"observed_at":"2026-08-04T07:22:06.464750Z","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":"2026-08-04T07:22:06.613245Z","title":"Waka: Data attribution using k-nearest neighbors and membership privacy principles","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:06.613245Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:8754de86d0d124273f87bf2ebd9217ec06d13a5f114a859b572bd361de5f80f0","observation_id":"4686c351-8a9e-458a-a114-c5a534eee020","resolution":{"observed_at":"2026-08-04T07:22:06.613245Z","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":"2026-08-04T07:22:06.804164Z","title":"Mteb: Massive text embedding benchmark","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:06.804164Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:0cd9166efabca9c4efbaef26cddf87a66323059810acbf57a766e4870266c1f0","observation_id":"4684a11d-3f47-48e9-9de7-5743fb4f933a","resolution":{"observed_at":"2026-08-04T07:22:06.804164Z","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":"2026-08-04T07:22:06.976803Z","title":"A bayesian approach to analysing training data attribution in deep learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:06.976803Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:d6fb8f589278ae4999a8b1cc0439eede1d498d358ca3774377c3fcf129479902","observation_id":"39e7ade9-47c0-4fe1-bfb9-68c94b734ff5","resolution":{"observed_at":"2026-08-04T07:22:06.976803Z","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":"2026-08-04T07:22:07.124909Z","title":"Trak: Attributing model behavior at scale","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:07.124909Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:1d2e9ba83f1812a24fecd226cf0902e0f6ecea252ddb619a0cc6fb192a225616","observation_id":"bc2e9998-3794-4be8-9746-aacc08d230db","resolution":{"observed_at":"2026-08-04T07:22:07.124909Z","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":"10.1145/3589324","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Near-duplicate sequence search at scale for large language model memorization evaluation","venue":"Proceedings of the ACM on Management of Data","work_id":"9a236a7d-383e-4cf3-bfc3-768846a8e492","year":2023},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:07.169383Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:2d803d52800abbfd00935f9a8cc37405f87f323645cbbc675310e9f6995789b3","observation_id":"55c58e19-6020-463c-b76a-e345abcd93f1","resolution":{"observed_at":"2026-08-04T07:23:22.122647Z","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":"2026-08-04T07:22:07.235275Z","title":"Estimating training data influence by tracing gradient descent","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:07.235275Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:c15b2ccbac369544ba0e23930ac84def7d2a3b263141aac6e24d2b1d2c3c4081","observation_id":"31c86b42-3a1e-4292-a232-796566de75c2","resolution":{"observed_at":"2026-08-04T07:22:07.235275Z","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":"2026-08-04T07:22:07.322577Z","title":"Scaling up membership inference: When and how attacks succeed on large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:07.322577Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:597be8f17ed1a23e0e73ab860a0eef5aa26926b967d06de5b22cbffdc90b6304","observation_id":"5e49d205-5c62-4ffd-8030-b4b548b16189","resolution":{"observed_at":"2026-08-04T07:22:07.322577Z","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":"2026-08-04T07:22:07.408257Z","title":"Learning or self-aligning? rethinking instruction fine-tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:07.408257Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:c487589e74b2495108f5ec4e2edbc13c640be21cf60d4c2338281d1bdbca9ab4","observation_id":"e76fdc55-e775-4fc9-aa64-aef91271b77d","resolution":{"observed_at":"2026-08-04T07:22:07.408257Z","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":"2026-08-04T07:22:07.480652Z","title":"Colbertv2: Effective and efficient retrieval via lightweight late interaction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:07.480652Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:429257e0f9e4702e1386c554f2479a941b4a4dbfb8fb28862f824c0020fe12e0","observation_id":"25f11077-c65a-43b1-a5e0-7bb54ae5b02d","resolution":{"observed_at":"2026-08-04T07:22:07.480652Z","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":"2026-08-04T07:22:07.663656Z","title":"Scaling up influence functions","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:07.663656Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:127c282c61e91d83e6124a87633fb18fe272aecad13bd6b099842c7f68cd2e61","observation_id":"9741e13f-1344-41e7-bd04-463cb7a45330","resolution":{"observed_at":"2026-08-04T07:22:07.663656Z","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":"2026-08-04T07:22:07.721184Z","title":"Rewritelm: an instruction-tuned large language model for text rewriting","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:07.721184Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:f3c82bcecef4fc37116ba000662612da00188ed44c14f34719a5f3f8bdac30aa","observation_id":"a5d6752d-0d45-4374-8dbc-c2103a1a3b04","resolution":{"observed_at":"2026-08-04T07:22:07.721184Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16829","last_updated":"2024-02-26T18:55:15Z","snapshot_observed_at":"2026-08-08T19:37:22.377743Z","submitted_at":"2024-02-26T18:55:15Z","title":"GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16829","snapshot_observed_at":"2026-08-04T07:22:07.934203Z","title":"Solatorio","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:07.934203Z"},"links":{"cited_paper":"/paper/2402.16829","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:a97359647c92e73df8861a00137794f03780d4e9766808d4885a1c00f1cc26eb","observation_id":"eea290b2-8ed0-4287-9509-6ce53d81ee13","resolution":{"observed_at":"2026-08-04T07:22:07.934203Z","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":"2026-08-04T07:22:08.063837Z","title":"pes2o (pretraining efficiently on s2orc) dataset","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:08.063837Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:0014ac61a078ecd112d9f542db894aff6c3d283a2892bb2ecf20f52b6a2b0f3c","observation_id":"59bdb7ce-799f-4fd4-b849-f0b11da4061e","resolution":{"observed_at":"2026-08-04T07:22:08.063837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00159","last_updated":"2024-06-06T18:46:40Z","snapshot_observed_at":"2026-08-08T04:07:59.311599Z","submitted_at":"2024-01-31T20:29:50Z","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00159","snapshot_observed_at":"2026-08-04T07:22:08.190319Z","title":"Peters, Abhilasha Ravichander, Kyle Richardson, Zejiang Shen, Emma Strubell, Nishant Subramani, Oyvind Tafjord, Pete Walsh, Luke Zettlemoyer, Noah A","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:08.190319Z"},"links":{"cited_paper":"/paper/2402.00159","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:ba34d39313ce881035509e06488e192350e025b5b7a7bfea79363de180c3be77","observation_id":"77038309-dd55-4453-9c4a-f328728db090","resolution":{"observed_at":"2026-08-04T07:22:08.190319Z","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":"2026-08-04T07:22:08.307626Z","title":"Enhancing training data attribution with representational optimization, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:08.307626Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:c3bb5af7b8c48b639363f233d39284ddf177eeaf4cb27281895158685c76efcc","observation_id":"284b8b2a-8dea-4483-844d-f84cacc9eeab","resolution":{"observed_at":"2026-08-04T07:22:08.307626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.14740","last_updated":"2025-07-19T20:18:51Z","snapshot_observed_at":"2026-08-08T04:14:02.730591Z","submitted_at":"2025-07-19T20:18:51Z","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.14740","snapshot_observed_at":"2026-08-04T07:22:08.451533Z","title":"Better training data attribution via better inverse hessian-vector products","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:08.451533Z"},"links":{"cited_paper":"/paper/2507.14740","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:4e586a06715edf4d1b2cdc2756b8b0a1d9e8a6fa8892fe071c920aff2977fda5","observation_id":"374aeb14-73c7-4a0f-82e9-2db62305992b","resolution":{"observed_at":"2026-08-04T07:22:08.451533Z","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":"2026-08-04T07:22:08.570579Z","title":"Capturing the temporal dependence of training data influence","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:08.570579Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:d95f59a788c9f2d04a60115c2c04779abb857b3994390ff9f4c08c3c596340db","observation_id":"e855cc4b-71e1-4927-bd4b-fba3e83088e8","resolution":{"observed_at":"2026-08-04T07:22:08.570579Z","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":"2026-08-04T07:22:08.765688Z","title":"Generalization vs memorization: Tracing language models’ capabilities back to pretraining data","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:08.765688Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:4a55024b93112dfcd8bf68b579f907b5359d46ef4e091e72c8137b5fac58a120","observation_id":"1cc1e034-90b1-4c14-8af9-df8117f01c3c","resolution":{"observed_at":"2026-08-04T07:22:08.765688Z","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":"2026-08-04T07:22:08.905551Z","title":"Memhunter: Automated and verifiable memorization detection at dataset-scale in llms, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:08.905551Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:e68d3f6eb5942b41a19f823087a7fc69217f164adc07eb6fb3212c72d8bef2a8","observation_id":"e2b8d048-e9ec-45d0-82cd-50c2b27a36e5","resolution":{"observed_at":"2026-08-04T07:22:08.905551Z","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":"2026-08-04T07:22:09.007497Z","title":"Less: Selecting influential data for targeted instruction tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:09.007497Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:904e80da4cefdd5e65f24ec0abf68434632922c1256b101d0c72fa543d55a1ea","observation_id":"3dd82ca8-7d3a-4e97-ad8a-e71168aea809","resolution":{"observed_at":"2026-08-04T07:22:09.007497Z","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":"2026-08-04T07:22:09.134693Z","title":"Representer point selection for explaining deep neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:09.134693Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:1da94a936f600498c8ef4b0c97dc37a4f2deeb50666a8eece7d9f78122fcb342","observation_id":"555818bc-d506-49e7-b6c2-064d26891fd8","resolution":{"observed_at":"2026-08-04T07:22:09.134693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.02936","last_updated":"2025-02-12T04:41:34Z","snapshot_observed_at":"2026-08-06T22:02:50.460833Z","submitted_at":"2024-04-03T04:25:01Z","title":"Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.02936","snapshot_observed_at":"2026-08-04T07:22:09.311136Z","title":"Min-k URL https://arxiv.org/abs/2404.02936","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:09.311136Z"},"links":{"cited_paper":"/paper/2404.02936","citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:559f9d1d89ca932a2ea5c6c23af19c06415cd2b6ee6f3dbe7d673948bf844fe0","observation_id":"36584a79-e6c1-4784-b819-5ccbfe15c863","resolution":{"observed_at":"2026-08-04T07:22:09.311136Z","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":"2026-08-04T07:22:09.391718Z","title":"Pretraining data detection for large language models: A divergence-based calibration method","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:09.391718Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:5a0d1c3a518033e39c906a4316742ba6007727eca0d413cfb91ff2a1d4ad2854","observation_id":"b4ebc04b-00d3-41ad-b172-acf127c4636d","resolution":{"observed_at":"2026-08-04T07:22:09.391718Z","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":"2026-08-04T07:22:09.446894Z","title":"Dense text retrieval based on pretrained language models: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:09.446894Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:191e4a59d6193791abadec7bceb403a480d316edbfbf9aa7598de87eda607692","observation_id":"e4a0e93a-eff6-4032-8e72-7ba3b99d4679","resolution":{"observed_at":"2026-08-04T07:22:09.446894Z","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":"2026-08-04T07:22:09.559811Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:09.559811Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:3f7e3ec73853a0743eae45c6575bb5cb1735e8315000a67784e4a25f2782b0d5","observation_id":"0d7d3ae1-df83-4c7e-9a8f-38dd8c5992b3","resolution":{"observed_at":"2026-08-04T07:22:09.559811Z","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":"2026-08-04T07:22:09.650722Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:09.650722Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:2d3f8b69137fc0d4e7ae77ba282e0e1e4754d699f99e04bb4329a95939830388","observation_id":"57f96633-8b27-4546-b6ed-29af55462054","resolution":{"observed_at":"2026-08-04T07:22:09.650722Z","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":"2026-08-04T07:22:09.743961Z","title":"Most training‑data attribution (TDA) methods ask which training examples causally influence a given output, often using leave‑one‑out tests","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity","version":3},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-04T07:22:09.743961Z"},"links":{"citing_paper":"/paper/2510.27313"},"observation_digest":"sha256:dd5825b923937ee66aaf9722a566f1495a0eb5b400d9a033840c0564eb921ecd","observation_id":"8502a74d-6fba-49ea-a891-f303784f564b","resolution":{"observed_at":"2026-08-04T07:22:09.743961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2510.27313","last_updated":"2026-08-02T16:40:30Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T04:38:26.888452Z","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity"},"reference_resolution":{"displayed":60,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":59,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":60},"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 10 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 0 inbound Pith citation observations for arXiv:2510.27313."}