{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6V67FFXIGVOIS6ZJZX7P2KKV53","short_pith_number":"pith:6V67FFXI","canonical_record":{"source":{"id":"2505.22113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T08:41:14Z","cross_cats_sorted":[],"title_canon_sha256":"c3dc980f13cca392bf478380e0fbed839f00e31edd992b17dd8fe5f7be1cc17b","abstract_canon_sha256":"eac1df0e4c62575bc8d62bf218eec990598b80763fa333ae7d00936a2e7bba77"},"schema_version":"1.0"},"canonical_sha256":"f57df296e8355c897b29cdfefd2955eeeea95fd9a2902ea0a7c5c908e29525c7","source":{"kind":"arxiv","id":"2505.22113","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22113","created_at":"2026-07-05T11:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22113v1","created_at":"2026-07-05T11:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22113","created_at":"2026-07-05T11:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"6V67FFXIGVOI","created_at":"2026-07-05T11:11:10Z"},{"alias_kind":"pith_short_16","alias_value":"6V67FFXIGVOIS6ZJ","created_at":"2026-07-05T11:11:10Z"},{"alias_kind":"pith_short_8","alias_value":"6V67FFXI","created_at":"2026-07-05T11:11:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6V67FFXIGVOIS6ZJZX7P2KKV53","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T08:41:14Z","cross_cats_sorted":[],"title_canon_sha256":"c3dc980f13cca392bf478380e0fbed839f00e31edd992b17dd8fe5f7be1cc17b","abstract_canon_sha256":"eac1df0e4c62575bc8d62bf218eec990598b80763fa333ae7d00936a2e7bba77"},"schema_version":"1.0"},"canonical_sha256":"f57df296e8355c897b29cdfefd2955eeeea95fd9a2902ea0a7c5c908e29525c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:10.113417Z","signature_b64":"jRB5gkM+fA7j+9hzauoFUX/m+6u3rmGEruoFjia6gl++AlE3moGq770lMk6YXmRRbnnejfaZR63rgZu3oZy7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f57df296e8355c897b29cdfefd2955eeeea95fd9a2902ea0a7c5c908e29525c7","last_reissued_at":"2026-07-05T11:11:10.112904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:10.112904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22113","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vVy38mRZ0VfB7waDXe2dfA5NwuO6UvlvhkjjhYoT3oe4qT9m28zaqLAXrFiFtDgi3rncmRt755kBe5oqS/jpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:52:53.413714Z"},"content_sha256":"c7cae5d7ab852c2348ad44700e4dc7f85fea35916c6cf27a8f9fbcc0cdc82105","schema_version":"1.0","event_id":"sha256:c7cae5d7ab852c2348ad44700e4dc7f85fea35916c6cf27a8f9fbcc0cdc82105"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6V67FFXIGVOIS6ZJZX7P2KKV53","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"THINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yi Chang, Yuan Wu, Zhiyuan Li","submitted_at":"2025-05-28T08:41:14Z","abstract_excerpt":"Large reasoning models (LRMs) have achieved impressive performance in complex tasks, often outperforming conventional large language models (LLMs). However, the prevalent issue of overthinking severely limits their computational efficiency. Overthinking occurs when models generate excessive and redundant tokens that contribute little to accurate outcomes, especially in simple tasks, resulting in a significant waste of computational resources. To systematically investigate this issue, we introduce Think-Bench, a benchmark designed to evaluate the reasoning efficiency of LRMs. We also propose no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22113","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.22113/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vYTD1fTFlNu5KGFc0zrV8lqTWumJAd6uM/CM7GQlQTxji2OKyWPFLz1oqetxGy0D4rFQ2B4RyT7nZhjHf9qQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:52:53.414236Z"},"content_sha256":"20daf765e20dacc852bceb3bc07ea42d3965441331e826ffc18c4093d85de864","schema_version":"1.0","event_id":"sha256:20daf765e20dacc852bceb3bc07ea42d3965441331e826ffc18c4093d85de864"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6V67FFXIGVOIS6ZJZX7P2KKV53/bundle.json","state_url":"https://pith.science/pith/6V67FFXIGVOIS6ZJZX7P2KKV53/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6V67FFXIGVOIS6ZJZX7P2KKV53/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T16:52:53Z","links":{"resolver":"https://pith.science/pith/6V67FFXIGVOIS6ZJZX7P2KKV53","bundle":"https://pith.science/pith/6V67FFXIGVOIS6ZJZX7P2KKV53/bundle.json","state":"https://pith.science/pith/6V67FFXIGVOIS6ZJZX7P2KKV53/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6V67FFXIGVOIS6ZJZX7P2KKV53/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6V67FFXIGVOIS6ZJZX7P2KKV53","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":"eac1df0e4c62575bc8d62bf218eec990598b80763fa333ae7d00936a2e7bba77","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T08:41:14Z","title_canon_sha256":"c3dc980f13cca392bf478380e0fbed839f00e31edd992b17dd8fe5f7be1cc17b"},"schema_version":"1.0","source":{"id":"2505.22113","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22113","created_at":"2026-07-05T11:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22113v1","created_at":"2026-07-05T11:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22113","created_at":"2026-07-05T11:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"6V67FFXIGVOI","created_at":"2026-07-05T11:11:10Z"},{"alias_kind":"pith_short_16","alias_value":"6V67FFXIGVOIS6ZJ","created_at":"2026-07-05T11:11:10Z"},{"alias_kind":"pith_short_8","alias_value":"6V67FFXI","created_at":"2026-07-05T11:11:10Z"}],"graph_snapshots":[{"event_id":"sha256:20daf765e20dacc852bceb3bc07ea42d3965441331e826ffc18c4093d85de864","target":"graph","created_at":"2026-07-05T11:11:10Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.22113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large reasoning models (LRMs) have achieved impressive performance in complex tasks, often outperforming conventional large language models (LLMs). However, the prevalent issue of overthinking severely limits their computational efficiency. Overthinking occurs when models generate excessive and redundant tokens that contribute little to accurate outcomes, especially in simple tasks, resulting in a significant waste of computational resources. To systematically investigate this issue, we introduce Think-Bench, a benchmark designed to evaluate the reasoning efficiency of LRMs. We also propose no","authors_text":"Yi Chang, Yuan Wu, Zhiyuan Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T08:41:14Z","title":"THINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22113","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c7cae5d7ab852c2348ad44700e4dc7f85fea35916c6cf27a8f9fbcc0cdc82105","target":"record","created_at":"2026-07-05T11:11:10Z","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":"eac1df0e4c62575bc8d62bf218eec990598b80763fa333ae7d00936a2e7bba77","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T08:41:14Z","title_canon_sha256":"c3dc980f13cca392bf478380e0fbed839f00e31edd992b17dd8fe5f7be1cc17b"},"schema_version":"1.0","source":{"id":"2505.22113","kind":"arxiv","version":1}},"canonical_sha256":"f57df296e8355c897b29cdfefd2955eeeea95fd9a2902ea0a7c5c908e29525c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f57df296e8355c897b29cdfefd2955eeeea95fd9a2902ea0a7c5c908e29525c7","first_computed_at":"2026-07-05T11:11:10.112904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:10.112904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jRB5gkM+fA7j+9hzauoFUX/m+6u3rmGEruoFjia6gl++AlE3moGq770lMk6YXmRRbnnejfaZR63rgZu3oZy7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:10.113417Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22113","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7cae5d7ab852c2348ad44700e4dc7f85fea35916c6cf27a8f9fbcc0cdc82105","sha256:20daf765e20dacc852bceb3bc07ea42d3965441331e826ffc18c4093d85de864"],"state_sha256":"8ba373c5b0d3ec521689add3dffc10a5515d5d526fd4bd9ccb61cb757dc17ac7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jl+7KarmceoQkIoMJho2AvbssLff9kUqTCHC7s7gyRa6pTWq+AcVzkTzy8lun+PKhsCGVedsleBAnegCFTFHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:52:53.419775Z","bundle_sha256":"d8d837a81f5aa76f09a39b30ee6d273eca6f48ad00553fea674fff33ec8ae94a"}}