{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4E44RJ5Z4HTGZRZO6DDYCVEOHF","short_pith_number":"pith:4E44RJ5Z","canonical_record":{"source":{"id":"2605.15100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T17:19:37Z","cross_cats_sorted":[],"title_canon_sha256":"5c73f0fba184df04ef8d25a76d97e7d66297d24eea947de7cbb6af73152e373a","abstract_canon_sha256":"9701e68219796e9e081a93fdb4732af9364d967aecaa2c84ee0666ce8f388020"},"schema_version":"1.0"},"canonical_sha256":"e139c8a7b9e1e66cc72ef0c781548e397202b6f48ee39256843533821ff40a9a","source":{"kind":"arxiv","id":"2605.15100","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15100","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15100v1","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"4E44RJ5Z4HTG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"4E44RJ5Z4HTGZRZO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"4E44RJ5Z","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4E44RJ5Z4HTGZRZO6DDYCVEOHF","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T17:19:37Z","cross_cats_sorted":[],"title_canon_sha256":"5c73f0fba184df04ef8d25a76d97e7d66297d24eea947de7cbb6af73152e373a","abstract_canon_sha256":"9701e68219796e9e081a93fdb4732af9364d967aecaa2c84ee0666ce8f388020"},"schema_version":"1.0"},"canonical_sha256":"e139c8a7b9e1e66cc72ef0c781548e397202b6f48ee39256843533821ff40a9a","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.2","canonical_sha256":"e139c8a7b9e1e66cc72ef0c781548e397202b6f48ee39256843533821ff40a9a","last_reissued_at":"2026-05-17T21:57:19.153888Z","signature_status":"unsigned_v0","first_computed_at":"2026-05-17T21:40:25.823376Z"},"source_kind":"arxiv","source_id":"2605.15100","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":"2026-05-17T21:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O2GMFXNa2NJ1vFPhbt89nt8aJYwUkHtgutyIukS8u73LUvGRsOY+4SaUrZI7HM1UTr1+h0zOuxkU5EzxmDbHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:44:09.408078Z"},"content_sha256":"1c86d128d78ed292303d2426f78141245061155b95872b6963509511efb75b0e","schema_version":"1.0","event_id":"sha256:1c86d128d78ed292303d2426f78141245061155b95872b6963509511efb75b0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4E44RJ5Z4HTGZRZO6DDYCVEOHF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"DDC reduces token consumption by over 10x in LLM reasoning while maintaining or exceeding baseline accuracy across five benchmarks via adaptive path quality filtering.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Li, Hang Yan, Rongman Xu, Tianzhe Zhao, Yanrui Wu, Yifei Li","submitted_at":"2026-05-14T17:19:37Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning. However, maximizing their potential through inference-time scaling faces challenges in trade-off between sampling budget and reasoning quality. Current strategies remain inefficient as they typically treat sampling width and depth as orthogonal objectives, where width consensus methods risk reinforcing hallucinations, while depth pruning mechanisms prematurely truncate complex yet valid reasoning chains. Therefore, we propose Dual-Dimensional Consistency (DDC), a unified framework that bridges path quality with a"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"Evaluations across five benchmarks demonstrate that this approach reduces token consumption by over 10 times while maintaining or exceeding the accuracy of strong baselines across various LLMs.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that Confidence-Weighted Bayesian protocol combined with Trend-Aware Stratified Pruning will reliably concentrate compute on high-quality paths and filter hallucinations without discarding valid complex reasoning chains.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DDC reduces token consumption by over 10x in LLM reasoning while maintaining or exceeding baseline accuracy across five benchmarks via adaptive path quality filtering.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"a95a984003f2f88e3a7ad257f22955bb3e7aa3d90c691900aa0c3ec3b6f63a86"},"source":{"id":"2605.15100","kind":"arxiv","version":1},"verdict":{"id":"ff5bf447-ee7d-4444-87ad-b399ddb9d9a6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:18:20.178979Z","strongest_claim":"Evaluations across five benchmarks demonstrate that this approach reduces token consumption by over 10 times while maintaining or exceeding the accuracy of strong baselines across various LLMs.","one_line_summary":"DDC reduces token consumption by over 10x in LLM reasoning while maintaining or exceeding baseline accuracy across five benchmarks via adaptive path quality filtering.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that Confidence-Weighted Bayesian protocol combined with Trend-Aware Stratified Pruning will reliably concentrate compute on high-quality paths and filter hallucinations without discarding valid complex reasoning chains.","pith_extraction_headline":""},"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":"ff5bf447-ee7d-4444-87ad-b399ddb9d9a6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T21:57:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/W8Fowqkc4/B9PWtbv4eAPU1ud0NZjOuTcp5f26Nfija2V1f825GyWcm+g0WFbkNKgbf5QgGjUlxe/ngk06SCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:44:09.408903Z"},"content_sha256":"4e493c363f44315150c09a82cfe205d1880b09e64078c19323e8d0fb69ff2470","schema_version":"1.0","event_id":"sha256:4e493c363f44315150c09a82cfe205d1880b09e64078c19323e8d0fb69ff2470"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4E44RJ5Z4HTGZRZO6DDYCVEOHF/bundle.json","state_url":"https://pith.science/pith/4E44RJ5Z4HTGZRZO6DDYCVEOHF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4E44RJ5Z4HTGZRZO6DDYCVEOHF/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":"2026-05-25T18:44:09Z","links":{"resolver":"https://pith.science/pith/4E44RJ5Z4HTGZRZO6DDYCVEOHF","bundle":"https://pith.science/pith/4E44RJ5Z4HTGZRZO6DDYCVEOHF/bundle.json","state":"https://pith.science/pith/4E44RJ5Z4HTGZRZO6DDYCVEOHF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4E44RJ5Z4HTGZRZO6DDYCVEOHF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4E44RJ5Z4HTGZRZO6DDYCVEOHF","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":"9701e68219796e9e081a93fdb4732af9364d967aecaa2c84ee0666ce8f388020","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T17:19:37Z","title_canon_sha256":"5c73f0fba184df04ef8d25a76d97e7d66297d24eea947de7cbb6af73152e373a"},"schema_version":"1.0","source":{"id":"2605.15100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15100","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15100v1","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"4E44RJ5Z4HTG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"4E44RJ5Z4HTGZRZO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"4E44RJ5Z","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:4e493c363f44315150c09a82cfe205d1880b09e64078c19323e8d0fb69ff2470","target":"graph","created_at":"2026-05-17T21:57:19Z","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":3,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Evaluations across five benchmarks demonstrate that this approach reduces token consumption by over 10 times while maintaining or exceeding the accuracy of strong baselines across various LLMs."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that Confidence-Weighted Bayesian protocol combined with Trend-Aware Stratified Pruning will reliably concentrate compute on high-quality paths and filter hallucinations without discarding valid complex reasoning chains."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DDC reduces token consumption by over 10x in LLM reasoning while maintaining or exceeding baseline accuracy across five benchmarks via adaptive path quality filtering."}],"snapshot_sha256":"a95a984003f2f88e3a7ad257f22955bb3e7aa3d90c691900aa0c3ec3b6f63a86"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning. However, maximizing their potential through inference-time scaling faces challenges in trade-off between sampling budget and reasoning quality. Current strategies remain inefficient as they typically treat sampling width and depth as orthogonal objectives, where width consensus methods risk reinforcing hallucinations, while depth pruning mechanisms prematurely truncate complex yet valid reasoning chains. Therefore, we propose Dual-Dimensional Consistency (DDC), a unified framework that bridges path quality with a","authors_text":"Bo Li, Hang Yan, Rongman Xu, Tianzhe Zhao, Yanrui Wu, Yifei Li","cross_cats":[],"headline":"DDC reduces token consumption by over 10x in LLM reasoning while maintaining or exceeding baseline accuracy across five benchmarks via adaptive path quality filtering.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T17:19:37Z","title":"Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15100","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T03:18:20.178979Z","id":"ff5bf447-ee7d-4444-87ad-b399ddb9d9a6","model_set":{"reader":"grok-4.3"},"one_line_summary":"DDC reduces token consumption by over 10x in LLM reasoning while maintaining or exceeding baseline accuracy across five benchmarks via adaptive path quality filtering.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"","strongest_claim":"Evaluations across five benchmarks demonstrate that this approach reduces token consumption by over 10 times while maintaining or exceeding the accuracy of strong baselines across various LLMs.","weakest_assumption":"The assumption that Confidence-Weighted Bayesian protocol combined with Trend-Aware Stratified Pruning will reliably concentrate compute on high-quality paths and filter hallucinations without discarding valid complex reasoning chains."}},"verdict_id":"ff5bf447-ee7d-4444-87ad-b399ddb9d9a6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1c86d128d78ed292303d2426f78141245061155b95872b6963509511efb75b0e","target":"record","created_at":"2026-05-17T21:18:33Z","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":"9701e68219796e9e081a93fdb4732af9364d967aecaa2c84ee0666ce8f388020","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T17:19:37Z","title_canon_sha256":"5c73f0fba184df04ef8d25a76d97e7d66297d24eea947de7cbb6af73152e373a"},"schema_version":"1.0","source":{"id":"2605.15100","kind":"arxiv","version":1}},"canonical_sha256":"e139c8a7b9e1e66cc72ef0c781548e397202b6f48ee39256843533821ff40a9a","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e139c8a7b9e1e66cc72ef0c781548e397202b6f48ee39256843533821ff40a9a","first_computed_at":"2026-05-17T21:40:25.823376Z","kind":"pith_receipt","last_reissued_at":"2026-05-17T21:57:19.153888Z","receipt_version":"0.2","signature_status":"unsigned_v0"},"source_id":"2605.15100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c86d128d78ed292303d2426f78141245061155b95872b6963509511efb75b0e","sha256:4e493c363f44315150c09a82cfe205d1880b09e64078c19323e8d0fb69ff2470"],"state_sha256":"fd16bcf95748e0493bd46a3045a337a6a32e9da2029716cd5adc2bfbfb002b87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aZM53m72HbDUEOH9Z+gkk8vjPiOWJrVymQ8Fri/pzC0So48l9C6P9qy1u1XM1XfFsQ+VlF+UC/dWI3jkZy50CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:44:09.413151Z","bundle_sha256":"90aa25cdd6f20e88463713fabd71628140c2cf845b8884c2504c080a4e3e2e97"}}