{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6PMSN6WREZROONKLEYFH3QJD5X","short_pith_number":"pith:6PMSN6WR","canonical_record":{"source":{"id":"2511.05722","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-07T21:29:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"205afd00d63fa64a9ae7565926d1afbf2e4f080561bb8214aa3756aed825a92f","abstract_canon_sha256":"4a75516bb1bc25cac2804383cb3723e9650b8de60d7707c5430fb2cc24f3ad71"},"schema_version":"1.0"},"canonical_sha256":"f3d926fad12662e7354b260a7dc123edc1d77b9cb39aec03958b6325bdc861ae","source":{"kind":"arxiv","id":"2511.05722","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.05722","created_at":"2026-06-04T01:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2511.05722v3","created_at":"2026-06-04T01:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.05722","created_at":"2026-06-04T01:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"6PMSN6WREZRO","created_at":"2026-06-04T01:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"6PMSN6WREZROONKL","created_at":"2026-06-04T01:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"6PMSN6WR","created_at":"2026-06-04T01:08:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6PMSN6WREZROONKLEYFH3QJD5X","target":"record","payload":{"canonical_record":{"source":{"id":"2511.05722","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-07T21:29:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"205afd00d63fa64a9ae7565926d1afbf2e4f080561bb8214aa3756aed825a92f","abstract_canon_sha256":"4a75516bb1bc25cac2804383cb3723e9650b8de60d7707c5430fb2cc24f3ad71"},"schema_version":"1.0"},"canonical_sha256":"f3d926fad12662e7354b260a7dc123edc1d77b9cb39aec03958b6325bdc861ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:35.778367Z","signature_b64":"7tEVszWTwQir666VzAcGFjSdbLSzXYYUvAvrt1H9WF3HZCxJqPWIVaMiAefBZ+DBHr2IKDF3fvVaUr2fZHwPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3d926fad12662e7354b260a7dc123edc1d77b9cb39aec03958b6325bdc861ae","last_reissued_at":"2026-06-04T01:08:35.777479Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:35.777479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.05722","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q6hvit9ilUyGMZLs84Z2TK6CsG3TMyzwbaguK1I/eFGFigXWq+Jbkb9FozNXr0VuVmDHh0WtLE4nveXKYpcWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:40:38.421003Z"},"content_sha256":"a181121cbe64428c0de84ddb3b9997887d6a18648cfae42e3b34c7bb6677c9c4","schema_version":"1.0","event_id":"sha256:a181121cbe64428c0de84ddb3b9997887d6a18648cfae42e3b34c7bb6677c9c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6PMSN6WREZROONKLEYFH3QJD5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OckBench: Measuring the Efficiency of LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Kang, Ligeng Zhu, Song Han, Tushar Krishna, Zheng Du","submitted_at":"2025-11-07T21:29:41Z","abstract_excerpt":"Large language models (LLMs) such as GPT-5 and Gemini 3 have pushed the frontier of automated reasoning and code generation. Yet current benchmarks emphasize accuracy and output quality, neglecting a critical dimension: efficiency of token usage. The token efficiency is highly variable in practical. Models solving the same problem with similar accuracy can exhibit up to a \\textbf{5.0$\\times$} difference in token length, leading to massive gap of model reasoning ability. Such variance exposes significant redundancy, highlighting the critical need for a standardized benchmark to quantify the gap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.05722","kind":"arxiv","version":3},"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/2511.05722/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":"2026-06-04T01:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9XV4D0ZNrfR/VQyjAQN4jYrdLJ/Tkm0zVqYxb+XGUddkAZJgYkbzG76EHxZhxW7y8sDs6U7xKUgPNctNhrpOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:40:38.421385Z"},"content_sha256":"a8f7c5687658b30b8ab4eaa89be35a2fa3556183316509566627efd682f63722","schema_version":"1.0","event_id":"sha256:a8f7c5687658b30b8ab4eaa89be35a2fa3556183316509566627efd682f63722"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6PMSN6WREZROONKLEYFH3QJD5X/bundle.json","state_url":"https://pith.science/pith/6PMSN6WREZROONKLEYFH3QJD5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6PMSN6WREZROONKLEYFH3QJD5X/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":"2026-06-05T02:40:38Z","links":{"resolver":"https://pith.science/pith/6PMSN6WREZROONKLEYFH3QJD5X","bundle":"https://pith.science/pith/6PMSN6WREZROONKLEYFH3QJD5X/bundle.json","state":"https://pith.science/pith/6PMSN6WREZROONKLEYFH3QJD5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6PMSN6WREZROONKLEYFH3QJD5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6PMSN6WREZROONKLEYFH3QJD5X","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":"4a75516bb1bc25cac2804383cb3723e9650b8de60d7707c5430fb2cc24f3ad71","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-07T21:29:41Z","title_canon_sha256":"205afd00d63fa64a9ae7565926d1afbf2e4f080561bb8214aa3756aed825a92f"},"schema_version":"1.0","source":{"id":"2511.05722","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.05722","created_at":"2026-06-04T01:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2511.05722v3","created_at":"2026-06-04T01:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.05722","created_at":"2026-06-04T01:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"6PMSN6WREZRO","created_at":"2026-06-04T01:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"6PMSN6WREZROONKL","created_at":"2026-06-04T01:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"6PMSN6WR","created_at":"2026-06-04T01:08:35Z"}],"graph_snapshots":[{"event_id":"sha256:a8f7c5687658b30b8ab4eaa89be35a2fa3556183316509566627efd682f63722","target":"graph","created_at":"2026-06-04T01:08:35Z","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/2511.05722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) such as GPT-5 and Gemini 3 have pushed the frontier of automated reasoning and code generation. Yet current benchmarks emphasize accuracy and output quality, neglecting a critical dimension: efficiency of token usage. The token efficiency is highly variable in practical. Models solving the same problem with similar accuracy can exhibit up to a \\textbf{5.0$\\times$} difference in token length, leading to massive gap of model reasoning ability. Such variance exposes significant redundancy, highlighting the critical need for a standardized benchmark to quantify the gap","authors_text":"Hao Kang, Ligeng Zhu, Song Han, Tushar Krishna, Zheng Du","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-07T21:29:41Z","title":"OckBench: Measuring the Efficiency of LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.05722","kind":"arxiv","version":3},"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:a181121cbe64428c0de84ddb3b9997887d6a18648cfae42e3b34c7bb6677c9c4","target":"record","created_at":"2026-06-04T01:08:35Z","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":"4a75516bb1bc25cac2804383cb3723e9650b8de60d7707c5430fb2cc24f3ad71","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-07T21:29:41Z","title_canon_sha256":"205afd00d63fa64a9ae7565926d1afbf2e4f080561bb8214aa3756aed825a92f"},"schema_version":"1.0","source":{"id":"2511.05722","kind":"arxiv","version":3}},"canonical_sha256":"f3d926fad12662e7354b260a7dc123edc1d77b9cb39aec03958b6325bdc861ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3d926fad12662e7354b260a7dc123edc1d77b9cb39aec03958b6325bdc861ae","first_computed_at":"2026-06-04T01:08:35.777479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:35.777479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7tEVszWTwQir666VzAcGFjSdbLSzXYYUvAvrt1H9WF3HZCxJqPWIVaMiAefBZ+DBHr2IKDF3fvVaUr2fZHwPCQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:35.778367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.05722","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a181121cbe64428c0de84ddb3b9997887d6a18648cfae42e3b34c7bb6677c9c4","sha256:a8f7c5687658b30b8ab4eaa89be35a2fa3556183316509566627efd682f63722"],"state_sha256":"34d66e92b771074c7c10497f42adb4c0f2a5ef81298b3dd33dd48912ea1fa2ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jj2BLVcFk1PlxxO5QKUH1AmTnpinmY8bXN0wfC1CHKJsrWYIwlrQvTinLluE1toDISkdCzWj28zVpjZC9PSDCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T02:40:38.423507Z","bundle_sha256":"cb8c076d13c6c2fb5ce6f6d1533b98fcf46b1493e9e2ea54c8fefa4bcffbc2f6"}}