{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WBVSVZX4Z4LB4BVFJMCM2AMQC5","short_pith_number":"pith:WBVSVZX4","schema_version":"1.0","canonical_sha256":"b06b2ae6fccf161e06a54b04cd01901761fe5a82a0f79cd6a61cba8adec8db5b","source":{"kind":"arxiv","id":"2608.02089","version":1},"attestation_state":"computed","paper":{"title":"How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andres Algaba, Bert Verbruggen, Francesca Carlon, Lynn Delcon, Marthe Ballon, Vincent Ginis","submitted_at":"2026-08-03T11:48:39Z","abstract_excerpt":"Large language models often show users a final response and a short reasoning summary while the full reasoning trace stays hidden. We introduce an observability ladder that holds each completed run fixed and varies only what a reader inspects to judge whether the answer is correct: the response, a self-summary the model writes from the trace, the trace itself, and internal signals, each with and without the prompt. Across three benchmarks and five open-weight Qwen3 and gpt-oss models, we train matched linear correctness predictors on each access level. Without the prompt, summaries carry most "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.02089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T11:48:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bbbf2e417d59198364fefbcc621781aa559583346802a3c7e1076c148f7383e2","abstract_canon_sha256":"c21bb18b56cb934afad8540acebf5c9c2066de2030f81a387943de9c34877f13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:10:49.583893Z","signature_b64":"pe8M/3z9BiT4M1bKDI/cuwXU1aCRHeK+RU9x8biimWNeDcy8MvGGh5SFZHYS7D37XOVRw5+SI86BmXbMNWaVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b06b2ae6fccf161e06a54b04cd01901761fe5a82a0f79cd6a61cba8adec8db5b","last_reissued_at":"2026-08-04T02:10:49.582365Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:10:49.582365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andres Algaba, Bert Verbruggen, Francesca Carlon, Lynn Delcon, Marthe Ballon, Vincent Ginis","submitted_at":"2026-08-03T11:48:39Z","abstract_excerpt":"Large language models often show users a final response and a short reasoning summary while the full reasoning trace stays hidden. We introduce an observability ladder that holds each completed run fixed and varies only what a reader inspects to judge whether the answer is correct: the response, a self-summary the model writes from the trace, the trace itself, and internal signals, each with and without the prompt. Across three benchmarks and five open-weight Qwen3 and gpt-oss models, we train matched linear correctness predictors on each access level. Without the prompt, summaries carry most "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02089","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/2608.02089/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.02089","created_at":"2026-08-04T02:10:49.583861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02089v1","created_at":"2026-08-04T02:10:49.583861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02089","created_at":"2026-08-04T02:10:49.583861+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBVSVZX4Z4LB","created_at":"2026-08-04T02:10:49.583861+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBVSVZX4Z4LB4BVF","created_at":"2026-08-04T02:10:49.583861+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBVSVZX4","created_at":"2026-08-04T02:10:49.583861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WBVSVZX4Z4LB4BVFJMCM2AMQC5","json":"https://pith.science/pith/WBVSVZX4Z4LB4BVFJMCM2AMQC5.json","graph_json":"https://pith.science/api/pith-number/WBVSVZX4Z4LB4BVFJMCM2AMQC5/graph.json","events_json":"https://pith.science/api/pith-number/WBVSVZX4Z4LB4BVFJMCM2AMQC5/events.json","paper":"https://pith.science/paper/WBVSVZX4"},"agent_actions":{"view_html":"https://pith.science/pith/WBVSVZX4Z4LB4BVFJMCM2AMQC5","download_json":"https://pith.science/pith/WBVSVZX4Z4LB4BVFJMCM2AMQC5.json","view_paper":"https://pith.science/paper/WBVSVZX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02089&json=true","fetch_graph":"https://pith.science/api/pith-number/WBVSVZX4Z4LB4BVFJMCM2AMQC5/graph.json","fetch_events":"https://pith.science/api/pith-number/WBVSVZX4Z4LB4BVFJMCM2AMQC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBVSVZX4Z4LB4BVFJMCM2AMQC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBVSVZX4Z4LB4BVFJMCM2AMQC5/action/storage_attestation","attest_author":"https://pith.science/pith/WBVSVZX4Z4LB4BVFJMCM2AMQC5/action/author_attestation","sign_citation":"https://pith.science/pith/WBVSVZX4Z4LB4BVFJMCM2AMQC5/action/citation_signature","submit_replication":"https://pith.science/pith/WBVSVZX4Z4LB4BVFJMCM2AMQC5/action/replication_record"}},"created_at":"2026-08-04T02:10:49.583861+00:00","updated_at":"2026-08-04T02:10:49.583861+00:00"}