{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TCDTGMPE6GJ5R75EXKNEOTJ7YQ","short_pith_number":"pith:TCDTGMPE","canonical_record":{"source":{"id":"2503.24235","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T15:46:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"692639941b393c728761c2d31ad40e00d178a4f9153c2774a9e611f177b70b5b","abstract_canon_sha256":"635a548a0417be176954fbc5647b9a395cc5ae8d07a8bf252dcdeee8519cd706"},"schema_version":"1.0"},"canonical_sha256":"98873331e4f193d8ffa4ba9a474d3fc41747ba058c5d6ccd1755c9c2e7e1e548","source":{"kind":"arxiv","id":"2503.24235","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.24235","created_at":"2026-07-05T10:58:25Z"},{"alias_kind":"arxiv_version","alias_value":"2503.24235v3","created_at":"2026-07-05T10:58:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.24235","created_at":"2026-07-05T10:58:25Z"},{"alias_kind":"pith_short_12","alias_value":"TCDTGMPE6GJ5","created_at":"2026-07-05T10:58:25Z"},{"alias_kind":"pith_short_16","alias_value":"TCDTGMPE6GJ5R75E","created_at":"2026-07-05T10:58:25Z"},{"alias_kind":"pith_short_8","alias_value":"TCDTGMPE","created_at":"2026-07-05T10:58:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TCDTGMPE6GJ5R75EXKNEOTJ7YQ","target":"record","payload":{"canonical_record":{"source":{"id":"2503.24235","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T15:46:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"692639941b393c728761c2d31ad40e00d178a4f9153c2774a9e611f177b70b5b","abstract_canon_sha256":"635a548a0417be176954fbc5647b9a395cc5ae8d07a8bf252dcdeee8519cd706"},"schema_version":"1.0"},"canonical_sha256":"98873331e4f193d8ffa4ba9a474d3fc41747ba058c5d6ccd1755c9c2e7e1e548","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:25.102528Z","signature_b64":"jUPzli3GHyNiTFseya+Y6t6dXrS6HwzUaUhOOJv3ZOXq/YBYEypQr3z7rx/XuLAsthrfaAxp/Zok64HENaAjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98873331e4f193d8ffa4ba9a474d3fc41747ba058c5d6ccd1755c9c2e7e1e548","last_reissued_at":"2026-07-05T10:58:25.101963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:25.101963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.24235","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":"2026-07-05T10:58:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M5EMssIpIZOhm+ERz0ft2AHuTE4Fm8rDyEiFIwR9dwyrtvL7/MYOhY6DxZWEUSU4c/AQAb2C9BHuvCJkwv6yDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:48:01.819217Z"},"content_sha256":"986fe74a24dc5e4499d8d3bae054c02a48de850495697974c5f78dfa16f07f64","schema_version":"1.0","event_id":"sha256:986fe74a24dc5e4499d8d3bae054c02a48de850495697974c5f78dfa16f07f64"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TCDTGMPE6GJ5R75EXKNEOTJ7YQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Test-time scaling in large language models is organized by a four-part framework of what, how, where, and how well to scale computation at inference.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Ma, Fuyuan Lyu, Haolun Wu, Irwin King, Lei Wang, Niklas Muennighoff, Qiyuan Zhang, Weixu Zhang, Wenyue Hua, Xue Liu, Yufei Wang, Zexu Sun, Zhihan Guo","submitted_at":"2025-03-31T15:46:15Z","abstract_excerpt":"As enthusiasm for scaling computation (data and parameters) in the pretraining era gradually diminished, test-time scaling (TTS), also referred to as ``test-time computing'' has emerged as a prominent research focus. Recent studies demonstrate that TTS can further elicit the problem-solving capabilities of large language models (LLMs), enabling significant breakthroughs not only in specialized reasoning tasks, such as mathematics and coding, but also in general tasks like open-ended Q&A. However, despite the explosion of recent efforts in this area, there remains an urgent need for a comprehen"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose a unified, multidimensional framework structured along four core dimensions of TTS research: what to scale, how to scale, where to scale, and how well to scale.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the existing literature on test-time scaling is sufficiently mature and distinct to benefit from a comprehensive taxonomy that captures all major techniques without significant omissions or overlaps.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A survey proposes a unified four-dimensional framework for test-time scaling in LLMs, reviews methods and applications, and outlines future directions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Test-time scaling in large language models is organized by a four-part framework of what, how, where, and how well to scale computation at inference.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0f54fecd0bb84b86e8d2b3e97eab8f2e35d3e3075fa3bab495c7cb4562b06efa"},"source":{"id":"2503.24235","kind":"arxiv","version":3},"verdict":{"id":"c49f1686-dd89-4d6b-b439-981632942193","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T18:02:26.416406Z","strongest_claim":"We propose a unified, multidimensional framework structured along four core dimensions of TTS research: what to scale, how to scale, where to scale, and how well to scale.","one_line_summary":"A survey proposes a unified four-dimensional framework for test-time scaling in LLMs, reviews methods and applications, and outlines future directions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the existing literature on test-time scaling is sufficiently mature and distinct to benefit from a comprehensive taxonomy that captures all major techniques without significant omissions or overlaps.","pith_extraction_headline":"Test-time scaling in large language models is organized by a four-part framework of what, how, where, and how well to scale computation at inference."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.24235/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":2,"snapshot_sha256":"d16c2dc5f0fd073eace1afbbc5219d423bda379fa835c59466340176401196b0"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"c49f1686-dd89-4d6b-b439-981632942193"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:58:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h9KMEvofzQcmrRWiZo13CJwlR4k+7t/s/97lcyP0XNOfzQPl8dWiWZd5h8ayUJ0gwTONdsZUdKPUlKZWIx67AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:48:01.820051Z"},"content_sha256":"5caf52ddd346f798ad5b9e38dbb809f6add4f7bde1d16ee7c3b990e079ab66e4","schema_version":"1.0","event_id":"sha256:5caf52ddd346f798ad5b9e38dbb809f6add4f7bde1d16ee7c3b990e079ab66e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TCDTGMPE6GJ5R75EXKNEOTJ7YQ/bundle.json","state_url":"https://pith.science/pith/TCDTGMPE6GJ5R75EXKNEOTJ7YQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TCDTGMPE6GJ5R75EXKNEOTJ7YQ/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":"2026-08-06T11:48:01Z","links":{"resolver":"https://pith.science/pith/TCDTGMPE6GJ5R75EXKNEOTJ7YQ","bundle":"https://pith.science/pith/TCDTGMPE6GJ5R75EXKNEOTJ7YQ/bundle.json","state":"https://pith.science/pith/TCDTGMPE6GJ5R75EXKNEOTJ7YQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TCDTGMPE6GJ5R75EXKNEOTJ7YQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TCDTGMPE6GJ5R75EXKNEOTJ7YQ","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":"635a548a0417be176954fbc5647b9a395cc5ae8d07a8bf252dcdeee8519cd706","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T15:46:15Z","title_canon_sha256":"692639941b393c728761c2d31ad40e00d178a4f9153c2774a9e611f177b70b5b"},"schema_version":"1.0","source":{"id":"2503.24235","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.24235","created_at":"2026-07-05T10:58:25Z"},{"alias_kind":"arxiv_version","alias_value":"2503.24235v3","created_at":"2026-07-05T10:58:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.24235","created_at":"2026-07-05T10:58:25Z"},{"alias_kind":"pith_short_12","alias_value":"TCDTGMPE6GJ5","created_at":"2026-07-05T10:58:25Z"},{"alias_kind":"pith_short_16","alias_value":"TCDTGMPE6GJ5R75E","created_at":"2026-07-05T10:58:25Z"},{"alias_kind":"pith_short_8","alias_value":"TCDTGMPE","created_at":"2026-07-05T10:58:25Z"}],"graph_snapshots":[{"event_id":"sha256:5caf52ddd346f798ad5b9e38dbb809f6add4f7bde1d16ee7c3b990e079ab66e4","target":"graph","created_at":"2026-07-05T10:58:25Z","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":"We propose a unified, multidimensional framework structured along four core dimensions of TTS research: what to scale, how to scale, where to scale, and how well to scale."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the existing literature on test-time scaling is sufficiently mature and distinct to benefit from a comprehensive taxonomy that captures all major techniques without significant omissions or overlaps."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A survey proposes a unified four-dimensional framework for test-time scaling in LLMs, reviews methods and applications, and outlines future directions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Test-time scaling in large language models is organized by a four-part framework of what, how, where, and how well to scale computation at inference."}],"snapshot_sha256":"0f54fecd0bb84b86e8d2b3e97eab8f2e35d3e3075fa3bab495c7cb4562b06efa"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d16c2dc5f0fd073eace1afbbc5219d423bda379fa835c59466340176401196b0"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.24235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As enthusiasm for scaling computation (data and parameters) in the pretraining era gradually diminished, test-time scaling (TTS), also referred to as ``test-time computing'' has emerged as a prominent research focus. Recent studies demonstrate that TTS can further elicit the problem-solving capabilities of large language models (LLMs), enabling significant breakthroughs not only in specialized reasoning tasks, such as mathematics and coding, but also in general tasks like open-ended Q&A. However, despite the explosion of recent efforts in this area, there remains an urgent need for a comprehen","authors_text":"Chen Ma, Fuyuan Lyu, Haolun Wu, Irwin King, Lei Wang, Niklas Muennighoff, Qiyuan Zhang, Weixu Zhang, Wenyue Hua, Xue Liu, Yufei Wang, Zexu Sun, Zhihan Guo","cross_cats":["cs.AI"],"headline":"Test-time scaling in large language models is organized by a four-part framework of what, how, where, and how well to scale computation at inference.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T15:46:15Z","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.24235","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-13T18:02:26.416406Z","id":"c49f1686-dd89-4d6b-b439-981632942193","model_set":{"reader":"grok-4.3"},"one_line_summary":"A survey proposes a unified four-dimensional framework for test-time scaling in LLMs, reviews methods and applications, and outlines future directions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Test-time scaling in large language models is organized by a four-part framework of what, how, where, and how well to scale computation at inference.","strongest_claim":"We propose a unified, multidimensional framework structured along four core dimensions of TTS research: what to scale, how to scale, where to scale, and how well to scale.","weakest_assumption":"That the existing literature on test-time scaling is sufficiently mature and distinct to benefit from a comprehensive taxonomy that captures all major techniques without significant omissions or overlaps."}},"verdict_id":"c49f1686-dd89-4d6b-b439-981632942193"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:986fe74a24dc5e4499d8d3bae054c02a48de850495697974c5f78dfa16f07f64","target":"record","created_at":"2026-07-05T10:58:25Z","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":"635a548a0417be176954fbc5647b9a395cc5ae8d07a8bf252dcdeee8519cd706","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T15:46:15Z","title_canon_sha256":"692639941b393c728761c2d31ad40e00d178a4f9153c2774a9e611f177b70b5b"},"schema_version":"1.0","source":{"id":"2503.24235","kind":"arxiv","version":3}},"canonical_sha256":"98873331e4f193d8ffa4ba9a474d3fc41747ba058c5d6ccd1755c9c2e7e1e548","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98873331e4f193d8ffa4ba9a474d3fc41747ba058c5d6ccd1755c9c2e7e1e548","first_computed_at":"2026-07-05T10:58:25.101963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:25.101963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jUPzli3GHyNiTFseya+Y6t6dXrS6HwzUaUhOOJv3ZOXq/YBYEypQr3z7rx/XuLAsthrfaAxp/Zok64HENaAjCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:25.102528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.24235","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:986fe74a24dc5e4499d8d3bae054c02a48de850495697974c5f78dfa16f07f64","sha256:5caf52ddd346f798ad5b9e38dbb809f6add4f7bde1d16ee7c3b990e079ab66e4"],"state_sha256":"0758a1ec78bfe3e2edbc2e7a267507efe958530d68c68d056f821e614657561e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mu9m0nbOJdR2X7mwhkqSW0QUC86P2NkIJgijjBdFrQd8k8f7PvdSdnKIJaB+g9TbHeRE6mAGKUQ8djcafXp0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T11:48:01.828402Z","bundle_sha256":"49d1ab42ba01b0eb70e20aa7807ff9ace71f1fd8d24d4e99dbd7fa1bab7aa442"}}