{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OV6P2JTV7LJPILFH6UXU4QI52A","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e6c8d5e5a812be39a8d8a0da79f389eafe196787038db3dc44cf29431659897d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-08T12:50:52Z","title_canon_sha256":"8ca16ca16ac778a2a73492f3ad4f744c08b705095d09c9592cb55b11a4a06d3b"},"schema_version":"1.0","source":{"id":"2604.07035","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.07035","created_at":"2026-05-20T01:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2604.07035v2","created_at":"2026-05-20T01:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.07035","created_at":"2026-05-20T01:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"OV6P2JTV7LJP","created_at":"2026-05-20T01:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"OV6P2JTV7LJPILFH","created_at":"2026-05-20T01:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"OV6P2JTV","created_at":"2026-05-20T01:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:30b50218cd307230327105fbba0b031f0214e917db00f4db9fc3710af6a60442","target":"graph","created_at":"2026-05-20T01:05:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"These results show that sparse activation alone does not guarantee the best practical operating point: observed accuracy-efficiency tradeoffs depend jointly on architecture, prompting protocol, and task composition."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the four chosen benchmarks and three prompting strategies are representative enough of real-world reasoning workloads to support general claims about accuracy-efficiency tradeoffs."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Gemma-4-E4B with few-shot chain-of-thought reaches the highest weighted accuracy of 0.675 at 14.9 GB VRAM, while the larger Gemma-4-26B-A4B MoE model scores 0.663 but uses 48.1 GB."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Accuracy-efficiency tradeoffs in reasoning LLMs depend jointly on architecture, prompting protocol, and task rather than sparse activation alone."}],"snapshot_sha256":"455f26886c7e9c24405dc6418b419b58d2eafe09b327f5aac3e5575be5729663"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.07035/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open reasoning language models are often compared under mixed sample sizes, partially standardized prompts, and accuracy-centered summaries, which makes practical model selection difficult to interpret. We present a unified evaluation of seven open reasoning language model configurations across four benchmarks: ARC-Challenge, GSM8K, MATH levels 1 to 3, and TruthfulQA MC1. We test zero-shot, chain-of-thought (CoT), and few-shot CoT prompting on the same 238-example subset for every model--dataset--strategy condition, yielding a complete 7 x 4 x 3 design with 84 conditions and 19,992 evaluated e","authors_text":"Ge Wang, Md Motaleb Hossen Manik","cross_cats":[],"headline":"Accuracy-efficiency tradeoffs in reasoning LLMs depend jointly on architecture, prompting protocol, and task rather than sparse activation alone.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-08T12:50:52Z","title":"Unified Deployment-Aware Evaluation of Open Reasoning Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.07035","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T17:44:59.556352Z","id":"93e4922e-cb2b-4db0-bdc4-28d92264b317","model_set":{"reader":"grok-4.3"},"one_line_summary":"Gemma-4-E4B with few-shot chain-of-thought reaches the highest weighted accuracy of 0.675 at 14.9 GB VRAM, while the larger Gemma-4-26B-A4B MoE model scores 0.663 but uses 48.1 GB.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Accuracy-efficiency tradeoffs in reasoning LLMs depend jointly on architecture, prompting protocol, and task rather than sparse activation alone.","strongest_claim":"These results show that sparse activation alone does not guarantee the best practical operating point: observed accuracy-efficiency tradeoffs depend jointly on architecture, prompting protocol, and task composition.","weakest_assumption":"That the four chosen benchmarks and three prompting strategies are representative enough of real-world reasoning workloads to support general claims about accuracy-efficiency tradeoffs."}},"verdict_id":"93e4922e-cb2b-4db0-bdc4-28d92264b317"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3931293f5406cd0414edfe45fb8739bd51df82d1858080589e120b9f76624833","target":"record","created_at":"2026-05-20T01:05:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e6c8d5e5a812be39a8d8a0da79f389eafe196787038db3dc44cf29431659897d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-08T12:50:52Z","title_canon_sha256":"8ca16ca16ac778a2a73492f3ad4f744c08b705095d09c9592cb55b11a4a06d3b"},"schema_version":"1.0","source":{"id":"2604.07035","kind":"arxiv","version":2}},"canonical_sha256":"757cfd2675fad2f42ca7f52f4e411dd01459177b3dd47ff7c13db0f7d27b9898","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"757cfd2675fad2f42ca7f52f4e411dd01459177b3dd47ff7c13db0f7d27b9898","first_computed_at":"2026-05-20T01:05:12.591934Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:12.591934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ifJ7NWMpNo+OzgY0LXYmlYq5/s7cKNxOvbW2I36LkQFhDN2cfOmdJdabSLEs8ILzDXZmYoaOSt5jHdrGfuGjAw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:12.592716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.07035","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3931293f5406cd0414edfe45fb8739bd51df82d1858080589e120b9f76624833","sha256:30b50218cd307230327105fbba0b031f0214e917db00f4db9fc3710af6a60442"],"state_sha256":"2611c80233eb25b57fecf2d9f4aa7c916013036688276d6e6c378c1808da7b10"}