{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YAI6Y7L2A2DGX2ZMYCNO4FQL2W","short_pith_number":"pith:YAI6Y7L2","canonical_record":{"source":{"id":"2502.13962","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T18:58:31Z","cross_cats_sorted":[],"title_canon_sha256":"68d357b211aa20c909410488ef3dc0f8f587de6be060dec5f86f14deaf5a4f82","abstract_canon_sha256":"e7063fd3645780392ca315bd8f54e4d5cd095e83cd6f5f20c41a0b7e50831375"},"schema_version":"1.0"},"canonical_sha256":"c011ec7d7a06866beb2cc09aee160bd5a2e46a06f27c63c1e7cf5f183f5a1d4e","source":{"kind":"arxiv","id":"2502.13962","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13962","created_at":"2026-07-05T11:39:09Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13962v2","created_at":"2026-07-05T11:39:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13962","created_at":"2026-07-05T11:39:09Z"},{"alias_kind":"pith_short_12","alias_value":"YAI6Y7L2A2DG","created_at":"2026-07-05T11:39:09Z"},{"alias_kind":"pith_short_16","alias_value":"YAI6Y7L2A2DGX2ZM","created_at":"2026-07-05T11:39:09Z"},{"alias_kind":"pith_short_8","alias_value":"YAI6Y7L2","created_at":"2026-07-05T11:39:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YAI6Y7L2A2DGX2ZMYCNO4FQL2W","target":"record","payload":{"canonical_record":{"source":{"id":"2502.13962","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T18:58:31Z","cross_cats_sorted":[],"title_canon_sha256":"68d357b211aa20c909410488ef3dc0f8f587de6be060dec5f86f14deaf5a4f82","abstract_canon_sha256":"e7063fd3645780392ca315bd8f54e4d5cd095e83cd6f5f20c41a0b7e50831375"},"schema_version":"1.0"},"canonical_sha256":"c011ec7d7a06866beb2cc09aee160bd5a2e46a06f27c63c1e7cf5f183f5a1d4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:09.621906Z","signature_b64":"auspAJDTh+mVRYQ/hBl66vdyvi4BGz+MHHeYJv2s2+Kzu+iOpv7ShVlDwhe7KEeogWCunakQgquKwtCUuW+mBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c011ec7d7a06866beb2cc09aee160bd5a2e46a06f27c63c1e7cf5f183f5a1d4e","last_reissued_at":"2026-07-05T11:39:09.621456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:09.621456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.13962","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:39:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U2Fml/4ZGsBnWBpoW/Z44VK5g7DIWDzsvgQCz7KLHBuQquakquljW1r0qC4esiY/jwq6HNneprv1fy1aam+jBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:10:27.274978Z"},"content_sha256":"db6708b0a6ed3508941a45d8c499e6f2ce55a0127261caf1031303072710256a","schema_version":"1.0","event_id":"sha256:db6708b0a6ed3508941a45d8c499e6f2ce55a0127261caf1031303072710256a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YAI6Y7L2A2DGX2ZMYCNO4FQL2W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Jeffrey Cheng, William Jurayj","submitted_at":"2025-02-19T18:58:31Z","abstract_excerpt":"Scaling the test-time compute of large language models has demonstrated impressive performance on reasoning benchmarks. However, existing evaluations of test-time scaling make the strong assumption that a reasoning system should always give an answer to any question provided. This overlooks concerns about whether a model is confident in its answer, and whether it is appropriate to always provide a response. To address these concerns, we extract confidence scores during reasoning for thresholding model responses. We find that increasing compute budget at inference time not only helps models ans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13962","kind":"arxiv","version":2},"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/2502.13962/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":"2026-07-05T11:39:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h3K11GCfCSb9SNhRVmXKkAuUVOg/UYSh3GvhcR0bTJgmSuoqC3lZm3b98s1ER14lj+UNdAezTz84qwYsvFP/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:10:27.275489Z"},"content_sha256":"6ccb07205171491aa33e59fe9c7e3ea2ff95377235d3d45386343ad8bacab229","schema_version":"1.0","event_id":"sha256:6ccb07205171491aa33e59fe9c7e3ea2ff95377235d3d45386343ad8bacab229"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YAI6Y7L2A2DGX2ZMYCNO4FQL2W/bundle.json","state_url":"https://pith.science/pith/YAI6Y7L2A2DGX2ZMYCNO4FQL2W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YAI6Y7L2A2DGX2ZMYCNO4FQL2W/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":"2026-08-08T09:10:27Z","links":{"resolver":"https://pith.science/pith/YAI6Y7L2A2DGX2ZMYCNO4FQL2W","bundle":"https://pith.science/pith/YAI6Y7L2A2DGX2ZMYCNO4FQL2W/bundle.json","state":"https://pith.science/pith/YAI6Y7L2A2DGX2ZMYCNO4FQL2W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YAI6Y7L2A2DGX2ZMYCNO4FQL2W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YAI6Y7L2A2DGX2ZMYCNO4FQL2W","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":"e7063fd3645780392ca315bd8f54e4d5cd095e83cd6f5f20c41a0b7e50831375","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T18:58:31Z","title_canon_sha256":"68d357b211aa20c909410488ef3dc0f8f587de6be060dec5f86f14deaf5a4f82"},"schema_version":"1.0","source":{"id":"2502.13962","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13962","created_at":"2026-07-05T11:39:09Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13962v2","created_at":"2026-07-05T11:39:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13962","created_at":"2026-07-05T11:39:09Z"},{"alias_kind":"pith_short_12","alias_value":"YAI6Y7L2A2DG","created_at":"2026-07-05T11:39:09Z"},{"alias_kind":"pith_short_16","alias_value":"YAI6Y7L2A2DGX2ZM","created_at":"2026-07-05T11:39:09Z"},{"alias_kind":"pith_short_8","alias_value":"YAI6Y7L2","created_at":"2026-07-05T11:39:09Z"}],"graph_snapshots":[{"event_id":"sha256:6ccb07205171491aa33e59fe9c7e3ea2ff95377235d3d45386343ad8bacab229","target":"graph","created_at":"2026-07-05T11:39:09Z","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/2502.13962/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling the test-time compute of large language models has demonstrated impressive performance on reasoning benchmarks. However, existing evaluations of test-time scaling make the strong assumption that a reasoning system should always give an answer to any question provided. This overlooks concerns about whether a model is confident in its answer, and whether it is appropriate to always provide a response. To address these concerns, we extract confidence scores during reasoning for thresholding model responses. We find that increasing compute budget at inference time not only helps models ans","authors_text":"Benjamin Van Durme, Jeffrey Cheng, William Jurayj","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T18:58:31Z","title":"Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13962","kind":"arxiv","version":2},"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:db6708b0a6ed3508941a45d8c499e6f2ce55a0127261caf1031303072710256a","target":"record","created_at":"2026-07-05T11:39:09Z","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":"e7063fd3645780392ca315bd8f54e4d5cd095e83cd6f5f20c41a0b7e50831375","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T18:58:31Z","title_canon_sha256":"68d357b211aa20c909410488ef3dc0f8f587de6be060dec5f86f14deaf5a4f82"},"schema_version":"1.0","source":{"id":"2502.13962","kind":"arxiv","version":2}},"canonical_sha256":"c011ec7d7a06866beb2cc09aee160bd5a2e46a06f27c63c1e7cf5f183f5a1d4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c011ec7d7a06866beb2cc09aee160bd5a2e46a06f27c63c1e7cf5f183f5a1d4e","first_computed_at":"2026-07-05T11:39:09.621456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:09.621456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"auspAJDTh+mVRYQ/hBl66vdyvi4BGz+MHHeYJv2s2+Kzu+iOpv7ShVlDwhe7KEeogWCunakQgquKwtCUuW+mBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:09.621906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13962","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db6708b0a6ed3508941a45d8c499e6f2ce55a0127261caf1031303072710256a","sha256:6ccb07205171491aa33e59fe9c7e3ea2ff95377235d3d45386343ad8bacab229"],"state_sha256":"fd9c3939f14594da17cf9c3fa9db848cac903777a7431122b454f2b4ee6b7ee7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UZWjmhLxe+5viYpY7cvHyPHtnBo//DCSNV2bkLdbCOJr95sdlYWscYHS0Aj212Q3f8qETErDThA3NLqGqz8uCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:10:27.280977Z","bundle_sha256":"085e634f0e626c6234d09f2142f37c105bcc94ea8d9258d75ebc5a88349e87e4"}}