{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YGACVKZH5QH342ZJRBK66KCD4T","short_pith_number":"pith:YGACVKZH","canonical_record":{"source":{"id":"2506.14448","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T12:13:56Z","cross_cats_sorted":[],"title_canon_sha256":"b9d9f3c2185a706bc46ce75caa846d543f1147cc4ef489581b7241f2f4279cc6","abstract_canon_sha256":"7817db4b4a5718fdd67f0939ebe7b7c85e1fe1198f7d42535defe78c27d7cd4b"},"schema_version":"1.0"},"canonical_sha256":"c1802aab27ec0fbe6b298855ef2843e4fb8224164b1c444971df391ac29f796c","source":{"kind":"arxiv","id":"2506.14448","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14448","created_at":"2026-07-05T11:49:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14448v2","created_at":"2026-07-05T11:49:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14448","created_at":"2026-07-05T11:49:10Z"},{"alias_kind":"pith_short_12","alias_value":"YGACVKZH5QH3","created_at":"2026-07-05T11:49:10Z"},{"alias_kind":"pith_short_16","alias_value":"YGACVKZH5QH342ZJ","created_at":"2026-07-05T11:49:10Z"},{"alias_kind":"pith_short_8","alias_value":"YGACVKZH","created_at":"2026-07-05T11:49:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YGACVKZH5QH342ZJRBK66KCD4T","target":"record","payload":{"canonical_record":{"source":{"id":"2506.14448","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T12:13:56Z","cross_cats_sorted":[],"title_canon_sha256":"b9d9f3c2185a706bc46ce75caa846d543f1147cc4ef489581b7241f2f4279cc6","abstract_canon_sha256":"7817db4b4a5718fdd67f0939ebe7b7c85e1fe1198f7d42535defe78c27d7cd4b"},"schema_version":"1.0"},"canonical_sha256":"c1802aab27ec0fbe6b298855ef2843e4fb8224164b1c444971df391ac29f796c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:10.849143Z","signature_b64":"nq2wODYsveTk24lbDReyffGqTgy8CIeOGdgycrzVZBJpZQ6nysH5ZOBJPDgUtDcAgIz2YWWEMHcApfFFiHdXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1802aab27ec0fbe6b298855ef2843e4fb8224164b1c444971df391ac29f796c","last_reissued_at":"2026-07-05T11:49:10.848650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:10.848650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.14448","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":"2026-07-05T11:49:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gYjBy+s7FUiL+hZpVtCWlb8JoSpzFI85PU8KpcZHpBjVmYaqiJTi06h77rrL/tgV8WWE4ydPMvocBYWsq7dAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:57:14.018959Z"},"content_sha256":"8e18622e4296bbdbe76d4db82693e01671e1193c4148f2cfff01e8411463887a","schema_version":"1.0","event_id":"sha256:8e18622e4296bbdbe76d4db82693e01671e1193c4148f2cfff01e8411463887a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YGACVKZH5QH342ZJRBK66KCD4T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Far Can LLMs Improve from Experience? Measuring Test-Time Learning Ability in LLMs with Human Comparison","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiayin Wang, Min Zhang, Weizhi Ma, Zhiquang Guo","submitted_at":"2025-06-17T12:13:56Z","abstract_excerpt":"As evaluation designs of large language models may shape our trajectory toward artificial general intelligence, comprehensive and forward-looking assessment is essential. Existing benchmarks primarily assess static knowledge, while intelligence also entails the ability to rapidly learn from experience. To this end, we advocate for the evaluation of Test-time Learning, the capacity to improve performance in experience-based, reasoning-intensive tasks during test time. In this work, we propose semantic games as effective testbeds for evaluating test-time learning, due to their resistance to satu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14448","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/2506.14448/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":"2026-07-05T11:49:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dEh9b+ZWd7OBg6XIR6U8wWiKIKiocl444S/e9A//8Wz9zDUCLYSTJpZF3FkbC31GSltcp3XoN12gGSw+CiaCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:57:14.019518Z"},"content_sha256":"a96ea0eccc694af34d9ba6426eb734a71e717f9c1c01e7591416e5ee1c39f657","schema_version":"1.0","event_id":"sha256:a96ea0eccc694af34d9ba6426eb734a71e717f9c1c01e7591416e5ee1c39f657"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YGACVKZH5QH342ZJRBK66KCD4T/bundle.json","state_url":"https://pith.science/pith/YGACVKZH5QH342ZJRBK66KCD4T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YGACVKZH5QH342ZJRBK66KCD4T/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":"2026-08-10T10:57:14Z","links":{"resolver":"https://pith.science/pith/YGACVKZH5QH342ZJRBK66KCD4T","bundle":"https://pith.science/pith/YGACVKZH5QH342ZJRBK66KCD4T/bundle.json","state":"https://pith.science/pith/YGACVKZH5QH342ZJRBK66KCD4T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YGACVKZH5QH342ZJRBK66KCD4T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YGACVKZH5QH342ZJRBK66KCD4T","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":"7817db4b4a5718fdd67f0939ebe7b7c85e1fe1198f7d42535defe78c27d7cd4b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T12:13:56Z","title_canon_sha256":"b9d9f3c2185a706bc46ce75caa846d543f1147cc4ef489581b7241f2f4279cc6"},"schema_version":"1.0","source":{"id":"2506.14448","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14448","created_at":"2026-07-05T11:49:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14448v2","created_at":"2026-07-05T11:49:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14448","created_at":"2026-07-05T11:49:10Z"},{"alias_kind":"pith_short_12","alias_value":"YGACVKZH5QH3","created_at":"2026-07-05T11:49:10Z"},{"alias_kind":"pith_short_16","alias_value":"YGACVKZH5QH342ZJ","created_at":"2026-07-05T11:49:10Z"},{"alias_kind":"pith_short_8","alias_value":"YGACVKZH","created_at":"2026-07-05T11:49:10Z"}],"graph_snapshots":[{"event_id":"sha256:a96ea0eccc694af34d9ba6426eb734a71e717f9c1c01e7591416e5ee1c39f657","target":"graph","created_at":"2026-07-05T11:49:10Z","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/2506.14448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As evaluation designs of large language models may shape our trajectory toward artificial general intelligence, comprehensive and forward-looking assessment is essential. Existing benchmarks primarily assess static knowledge, while intelligence also entails the ability to rapidly learn from experience. To this end, we advocate for the evaluation of Test-time Learning, the capacity to improve performance in experience-based, reasoning-intensive tasks during test time. In this work, we propose semantic games as effective testbeds for evaluating test-time learning, due to their resistance to satu","authors_text":"Jiayin Wang, Min Zhang, Weizhi Ma, Zhiquang Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T12:13:56Z","title":"How Far Can LLMs Improve from Experience? Measuring Test-Time Learning Ability in LLMs with Human Comparison"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14448","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":"sha256:8e18622e4296bbdbe76d4db82693e01671e1193c4148f2cfff01e8411463887a","target":"record","created_at":"2026-07-05T11:49:10Z","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":"7817db4b4a5718fdd67f0939ebe7b7c85e1fe1198f7d42535defe78c27d7cd4b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T12:13:56Z","title_canon_sha256":"b9d9f3c2185a706bc46ce75caa846d543f1147cc4ef489581b7241f2f4279cc6"},"schema_version":"1.0","source":{"id":"2506.14448","kind":"arxiv","version":2}},"canonical_sha256":"c1802aab27ec0fbe6b298855ef2843e4fb8224164b1c444971df391ac29f796c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1802aab27ec0fbe6b298855ef2843e4fb8224164b1c444971df391ac29f796c","first_computed_at":"2026-07-05T11:49:10.848650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:10.848650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nq2wODYsveTk24lbDReyffGqTgy8CIeOGdgycrzVZBJpZQ6nysH5ZOBJPDgUtDcAgIz2YWWEMHcApfFFiHdXBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:10.849143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14448","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e18622e4296bbdbe76d4db82693e01671e1193c4148f2cfff01e8411463887a","sha256:a96ea0eccc694af34d9ba6426eb734a71e717f9c1c01e7591416e5ee1c39f657"],"state_sha256":"8d21b7118295fb2a53634c92663a6e7db9edc5bacf5df4b10d14a99485545050"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tes/KrSrkmrczWIMKSQ2XZm7UWjVqGvacu5cTeEqiaXL75aHEVc1UTATxkviY+voBG1cYQaxAu7PXIm47m0GAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:57:14.022830Z","bundle_sha256":"32a1f5d224f1d5b11a3c4208b88960b355084e649152ac77d7971e00429ab020"}}