{"as_of":"2026-08-10T15:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1fe7879479ef4d8f20a1bdc483cf68ec713dc0e6ea944f812feb75da6459b101","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":13,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":13,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":13,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":13,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:37:03.004066Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T03:26:29.004239Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":"2503.20641","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-07-02T03:26:29.004239Z","title":"arXiv preprint arXiv:2503.20641 , year=","venue":null,"work_id":"1789511e-499e-429e-90c0-e596f76c819a","year":2025},"citing_paper":{"arxiv_id":"2408.07666","last_updated":"2025-12-31T04:06:49Z","snapshot_observed_at":"2026-08-07T23:28:24.025478Z","submitted_at":"2024-08-14T16:58:48Z","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","version":5},"reference_index":256,"source":"pdf_text","source_observed_at":"2026-05-17T22:16:04.386706Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2408.07666"},"observation_digest":"sha256:bbc40cadd885aa06a34219004d8ba2de1aa80bb6502b9cb13c0fca8937dab522","observation_id":"0baf9318-dc02-45c4-b54d-e2d0cb351326","resolution":{"observed_at":"2026-05-17T22:16:04.768478Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-08-07T14:37:03.004066Z","title":"Unlocking efficient long-to-short llm reasoning with model merging.arXiv preprint arXiv:2503.20641, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.18298","last_updated":"2025-05-23T18:44:46Z","snapshot_observed_at":"2026-08-08T01:06:17.935169Z","submitted_at":"2025-05-23T18:44:46Z","title":"Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:37:03.004066Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2505.18298"},"observation_digest":"sha256:227200b613e073468fee913ce27cdbd31b67b05538352955d62c57cfac1ab431","observation_id":"b3f68f8b-fa53-436f-93dc-151615958a5f","resolution":{"observed_at":"2026-08-07T14:37:03.004066Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-08-07T13:08:42.297824Z","title":"Unlocking efficient long-to-short llm reasoning with model merging.arXiv preprint arXiv:2503.20641, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.22635","last_updated":"2025-05-28T17:51:10Z","snapshot_observed_at":"2026-08-08T01:10:15.066342Z","submitted_at":"2025-05-28T17:51:10Z","title":"Learning Composable Chains-of-Thought","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T13:08:42.297824Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2505.22635"},"observation_digest":"sha256:dad8402d71febfcb3f35401452e2560b4c9d359fc29361c3af0862e32ede8e91","observation_id":"1afad7da-1f0d-4265-b3ea-2c729940ee0a","resolution":{"observed_at":"2026-08-07T13:08:42.297824Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-08-06T20:46:22.633913Z","title":"Unlocking efficient long-to-short llm reasoning with model merging, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.01887","last_updated":"2025-07-02T16:57:01Z","snapshot_observed_at":"2026-08-09T05:10:28.392368Z","submitted_at":"2025-07-02T16:57:01Z","title":"MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:22.633913Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2507.01887"},"observation_digest":"sha256:1897ad9c485e75d31b5e6f85bfb88a689db377c93c5ec2ce498bd6da9fadc129","observation_id":"7d73ab5a-79c6-4af0-9257-b52489e2e304","resolution":{"observed_at":"2026-08-06T20:46:22.633913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-08-06T20:43:12.588405Z","title":"Unlocking efficient long-to-short llm reasoning with model merging.arXiv preprint arXiv:2503.20641, 2025c","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.02076","last_updated":"2025-07-02T18:27:42Z","snapshot_observed_at":"2026-08-08T01:09:25.758170Z","submitted_at":"2025-07-02T18:27:42Z","title":"Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T20:43:12.588405Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2507.02076"},"observation_digest":"sha256:a61f8d5453770f21e5025273ca14484c7dabe66c5b7cf5e6aaf81b8452ae8afb","observation_id":"b7e9225e-7221-469c-b540-fcaf5c94295f","resolution":{"observed_at":"2026-08-06T20:43:12.588405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-08-06T17:54:17.864071Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09662","last_updated":"2025-07-13T14:51:59Z","snapshot_observed_at":"2026-08-07T01:15:50.475193Z","submitted_at":"2025-07-13T14:51:59Z","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","version":1},"reference_index":203,"source":"arxiv_source","source_observed_at":"2026-08-06T17:54:17.864071Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2507.09662"},"observation_digest":"sha256:1233850a214ecfe798092520d067fafa3835a185c788bfb78da593746efa7569","observation_id":"60321640-9d35-46df-bd7f-a8b89bb24edb","resolution":{"observed_at":"2026-08-06T17:54:17.864071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-08-05T13:48:22.954670Z","title":"Unlocking efficient long-to-short llm reasoning with model merging","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.04474","last_updated":"2025-08-30T01:54:55Z","snapshot_observed_at":"2026-08-07T06:30:02.472113Z","submitted_at":"2025-08-30T01:54:55Z","title":"Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T13:48:22.954670Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2509.04474"},"observation_digest":"sha256:cf1e6248e0b9f62c535a213ac427069bdc48f57fefb00e9f3d107fd5b37b36c9","observation_id":"178cae99-eb4f-45a1-9c87-f08a431ad679","resolution":{"observed_at":"2026-08-05T13:48:22.954670Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-08-04T23:10:21.374870Z","title":"Unlocking efficient long-to-short llm reasoning with model merging,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.06795","last_updated":"2025-09-08T15:24:33Z","snapshot_observed_at":"2026-08-06T11:18:33.345942Z","submitted_at":"2025-09-08T15:24:33Z","title":"Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-04T23:10:21.374870Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2509.06795"},"observation_digest":"sha256:914c86acf0c56efc031cc9932bd1e9abaa39b2ed169f465afaad79a5d0fc40d3","observation_id":"f3d5fd41-eda2-4055-adc1-979b3f42a4c4","resolution":{"observed_at":"2026-08-04T23:10:21.374870Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":"2503.20641","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-07-02T03:26:29.004239Z","title":"arXiv preprint arXiv:2503.20641 , year=","venue":null,"work_id":"1789511e-499e-429e-90c0-e596f76c819a","year":2025},"citing_paper":{"arxiv_id":"2604.04120","last_updated":"2026-04-05T13:43:12Z","snapshot_observed_at":"2026-08-09T18:28:25.950067Z","submitted_at":"2026-04-05T13:43:12Z","title":"Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-13T17:16:47.284564Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2604.04120"},"observation_digest":"sha256:efad4695bb180b9d7db2ba0ec70495489add045e73485c8a04dbe92d186cd2ee","observation_id":"1f8f8e13-5489-4187-9142-05aeaca121ac","resolution":{"observed_at":"2026-05-13T17:18:01.274611Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":"2503.20641","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-07-02T03:26:29.004239Z","title":"arXiv preprint arXiv:2503.20641 , year=","venue":null,"work_id":"1789511e-499e-429e-90c0-e596f76c819a","year":2025},"citing_paper":{"arxiv_id":"2605.06111","last_updated":"2026-05-07T12:24:53Z","snapshot_observed_at":"2026-07-06T23:18:36.537416Z","submitted_at":"2026-05-07T12:24:53Z","title":"Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-08T09:11:20.733960Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2605.06111"},"observation_digest":"sha256:759031c15e1d5e9c735227a52b4871a54c29ffbe7d482d87d589aa75c514d88d","observation_id":"769da997-c45d-4c57-b5ca-b69fbe1954b3","resolution":{"observed_at":"2026-05-11T20:26:10.401670Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":"2503.20641","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-07-02T03:26:29.004239Z","title":"arXiv preprint arXiv:2503.20641 , year=","venue":null,"work_id":"1789511e-499e-429e-90c0-e596f76c819a","year":2025},"citing_paper":{"arxiv_id":"2605.12384","last_updated":"2026-05-12T16:47:40Z","snapshot_observed_at":"2026-07-06T23:24:03.984179Z","submitted_at":"2026-05-12T16:47:40Z","title":"Scalable Token-Level Hallucination Detection in Large Language Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-13T05:49:23.534294Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2605.12384"},"observation_digest":"sha256:7b4b787dce1e61c14826acbeabd38ba53f699170029bc40f980f76e997a1b12f","observation_id":"d37f5513-0d37-4354-90bf-5b456c5a4655","resolution":{"observed_at":"2026-05-13T05:52:22.412518Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":"2503.20641","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-07-02T03:26:29.004239Z","title":"arXiv preprint arXiv:2503.20641 , year=","venue":null,"work_id":"1789511e-499e-429e-90c0-e596f76c819a","year":2025},"citing_paper":{"arxiv_id":"2605.18083","last_updated":"2026-05-18T08:59:08Z","snapshot_observed_at":"2026-07-06T23:28:59.503300Z","submitted_at":"2026-05-18T08:59:08Z","title":"A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\\Delta$ Integration into Upcycled MoE","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-05-20T11:09:22.027588Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2605.18083"},"observation_digest":"sha256:54683caf32a875d2717ac4f8fcbd7760797b664fa5f820030007a5e696debb20","observation_id":"ce2b4be7-395b-429d-8b74-42b815b11757","resolution":{"observed_at":"2026-05-20T11:13:13.569817Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","version":2},"cited_work":{"arxiv_id":"2503.20641","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.20641","snapshot_observed_at":"2026-07-02T03:26:29.004239Z","title":"arXiv preprint arXiv:2503.20641 , year=","venue":null,"work_id":"1789511e-499e-429e-90c0-e596f76c819a","year":2025},"citing_paper":{"arxiv_id":"2606.03344","last_updated":"2026-06-02T08:54:37Z","snapshot_observed_at":"2026-08-02T15:32:07.510420Z","submitted_at":"2026-06-02T08:54:37Z","title":"RogueMerge: Robust and Unified Attacks against LLM Model Merging","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-06-28T10:05:10.309553Z"},"links":{"cited_paper":"/paper/2503.20641","citing_paper":"/paper/2606.03344"},"observation_digest":"sha256:c0bd0cfc37eab92460fa2e4c6574cbdfa63a8748d441568783ce0cdb873c52b0","observation_id":"2dea40d5-f75f-4472-a8c0-5cd072c000eb","resolution":{"observed_at":"2026-07-02T03:26:29.005982Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.20641/citation-record","integrity":"/paper/2503.20641/integrity","json":"/paper/2503.20641/citation-record.json","paper":"/paper/2503.20641"},"outbound":[],"paper":{"arxiv_id":"2503.20641","last_updated":"2025-05-23T02:41:43Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T16:35:15.231599Z","submitted_at":"2025-03-26T15:34:37Z","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 13 inbound Pith citation observations for arXiv:2503.20641."}