{"as_of":"2026-08-23T21:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f9a1419da5bec6f28e4c6485757b05f7928dc8d87b765db511060849b3e56d37","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T03:06:58.993747Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2606.05781/citation-record","integrity":"/paper/2606.05781/integrity","json":"/paper/2606.05781/citation-record.json","paper":"/paper/2606.05781"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T03:06:58.993747Z","title":"Language models are few-shot learners,","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:c6ef3421f875efdaa56147a92e4234b0b8db4f169b6f00762321ed5dde262687","observation_id":"f7fc1299-5cff-4e29-b237-1749f9b54e51","resolution":{"observed_at":"2026-06-28T03:06:58.993747Z","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":"2026-06-28T03:06:58.993747Z","title":"LoRA: Low-rank adaptation of large language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:d220c0d21301544b84cf46dbfd97da6373b279d98b1e86a7b39f69ea9ef4063f","observation_id":"aa065ad5-9d4c-4daf-87e1-cf7b5061e0fd","resolution":{"observed_at":"2026-06-28T03:06:58.993747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":"2407.21783","doi":"10.1016/s0749-0720(15","metadata_source":"pith","pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"The Llama 3 Herd of Models","venue":"cs.AI","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","year":2024},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:94abc829408d20ab1b150a10e2ebaee1869b0aab98cfd304a4d8a484e8ac6e08","observation_id":"3d8b5b7b-309b-409a-85a3-15e625a53c45","resolution":{"observed_at":"2026-07-02T11:46:55.501348Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-28T03:06:58.993747Z","title":"Lost in the middle: How language models use long contexts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:f274f184d29257f5d4ddf2054b101fec11c4ea7ca0aaf95d9f3dc01e7a3ca39b","observation_id":"f2617c66-357e-4ccc-af96-06f516940b0d","resolution":{"observed_at":"2026-06-28T03:06:58.993747Z","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":"2026-06-28T03:06:58.993747Z","title":"QLoRA: Efficient finetuning of quantized language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:c42724a9e9ec2017dc901e4f24cb86f5ae37d1aa3159e8bd682d7db7d27c0142","observation_id":"26b4eaa3-6336-42ea-834f-b7093fe3d024","resolution":{"observed_at":"2026-06-28T03:06:58.993747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.16092","last_updated":"2026-06-08T08:40:57Z","snapshot_observed_at":"2026-08-16T15:20:27.587232Z","submitted_at":"2023-06-28T10:48:34Z","title":"Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture","version":3},"cited_work":{"arxiv_id":"2306.16092","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.16092","snapshot_observed_at":"2026-07-04T00:59:19.876727Z","title":"Chatlaw: A multi-agent collaborative legal assistant with knowledge graph enhanced mixture-of-experts large language model","venue":"cs.CL","work_id":"f5ba1d7c-9e47-4362-b2db-a7b7f84f0c8f","year":2023},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"cited_paper":"/paper/2306.16092","citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:ab40b583388a33c9b988d4c59dda0fdcdd360790c368182981a4c5b40ae9a7cd","observation_id":"a6bb77fb-d655-44ed-bca0-e066129047fb","resolution":{"observed_at":"2026-07-02T11:46:55.498365Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-28T03:06:58.993747Z","title":"Large language models encode clinical knowledge,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:76417f485342545a300a55226531c684848e3716d0de596f1c75376ddbd7b4bf","observation_id":"ec335da2-77a7-4f0c-b713-b66fa2489901","resolution":{"observed_at":"2026-06-28T03:06:58.993747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.17564","last_updated":"2023-12-21T06:21:11Z","snapshot_observed_at":"2026-08-14T12:54:48.492396Z","submitted_at":"2023-03-30T17:30:36Z","title":"BloombergGPT: A Large Language Model for Finance","version":3},"cited_work":{"arxiv_id":"2303.17564","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.17564","snapshot_observed_at":"2026-07-10T09:06:59.093499Z","title":"BloombergGPT: A Large Language Model for Finance","venue":"cs.LG","work_id":"04e9adc6-bece-4ff4-a0f6-e836d88414a7","year":2023},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"cited_paper":"/paper/2303.17564","citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:79bbf03a3e4f3dfe3363388d087c00386d004f460f4b207fb7139bc3ad34784d","observation_id":"001bca34-12b1-4d03-920f-630bca58ca08","resolution":{"observed_at":"2026-07-02T11:46:55.506307Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-28T03:06:58.993747Z","title":"Self-instruct: Aligning language models with self- generated instructions,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:c7836c74cc913b3ac66147df381592db8bde8320ed59a916e6dc09cd30d805dc","observation_id":"6d635bce-007b-4e00-bc07-6cb007590301","resolution":{"observed_at":"2026-06-28T03:06:58.993747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09702","last_updated":"2023-08-19T21:27:51Z","snapshot_observed_at":"2026-08-16T18:10:05.404630Z","submitted_at":"2023-07-19T01:14:49Z","title":"Efficient Guided Generation for Large Language Models","version":4},"cited_work":{"arxiv_id":"2307.09702","doi":"10.48550/arxiv.2307.09702","metadata_source":"pith","pith_arxiv_id":"2307.09702","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Efficient Guided Generation for Large Language Models","venue":"cs.CL","work_id":"eed83982-64d7-41e1-b7ec-21167ca473d5","year":2023},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"cited_paper":"/paper/2307.09702","citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:a86366d94f638c9b2f2e30c102d8604be0dd4e9797a4494ed71072e64571ff23","observation_id":"b612e150-35f1-4672-bee3-d9614379171c","resolution":{"observed_at":"2026-07-02T11:46:55.495185Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-05-22T13:23:27.209789+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-22T13:23:27.209789+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-28T03:06:58.993747Z","title":"SimCSE: Simple contrastive learning of sentence embeddings,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:c3eec9cb72af5a79d9ac69d9f6746f7b81b1282e1333fc39488c220cced6da3f","observation_id":"a4c304b4-b96e-4cda-88ee-a3448a0fc612","resolution":{"observed_at":"2026-06-28T03:06:58.993747Z","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":"2026-06-28T03:06:58.993747Z","title":"A survey of data augmentation approaches for NLP,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:56a00fb65ea0410415feef6f50ef3440d3fe58d9169d575842f7ada590ca1914","observation_id":"e05859d7-d5fc-4ed7-a710-0d518b0e6053","resolution":{"observed_at":"2026-06-28T03:06:58.993747Z","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":"2026-06-28T03:06:58.993747Z","title":"Independent LLM benchmarks: Speed, quality, and price,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:71f13f9ed6973758be4263434821d987a7e3d8c2e121a5c6a8e063fc4d256cc2","observation_id":"0a2b2e0e-c502-4326-8634-0746971aa1bf","resolution":{"observed_at":"2026-06-28T03:06:58.993747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":"2302.13971","doi":"10.48550/arxiv.2302.13971","metadata_source":"pith","pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"LLaMA: Open and Efficient Foundation Language Models","venue":"cs.CL","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","year":2023},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:685bf39ddf887873daab6df3f914aa8c9018b763529bd24e6ce8a501fb88f85d","observation_id":"25887294-b55d-4944-8ad6-55973f071cc0","resolution":{"observed_at":"2026-07-02T11:46:55.503847Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-08T16:08:17.350515+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-08T16:08:17.350515+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-06-28T03:06:58.993747Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T03:06:58.993747Z"},"links":{"citing_paper":"/paper/2606.05781"},"observation_digest":"sha256:056c848de4d98a22f843cba93f922a2c140b4870052bf41a30751eb23d2eeee5","observation_id":"f6b2d20f-9117-47d0-b5ab-fe273761c023","resolution":{"observed_at":"2026-06-28T03:06:58.993747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.05781","last_updated":"2026-06-06T01:31:00Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T12:18:46.654254Z","submitted_at":"2026-06-04T07:09:37Z","title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":5,"verified_fuzzy":0},"total_outbound_references":15},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2606.05781."}