{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:45IA3SBG4M4EKGE5KCIZ2JVNDB","short_pith_number":"pith:45IA3SBG","canonical_record":{"source":{"id":"2505.14398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T14:14:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d72ac408fc213effb898285f3afe486e13be5e441f364f180041741d728ccd49","abstract_canon_sha256":"3e0466db322910706f01b1a0448ea79e07753c6539cc6b3b61cfba5d8a7f618e"},"schema_version":"1.0"},"canonical_sha256":"e7500dc826e33845189d50919d26ad184e0fd9b4bce79d14fddd9b9840d7f549","source":{"kind":"arxiv","id":"2505.14398","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14398","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14398v1","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14398","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"45IA3SBG4M4E","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"45IA3SBG4M4EKGE5","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"45IA3SBG","created_at":"2026-07-05T11:06:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:45IA3SBG4M4EKGE5KCIZ2JVNDB","target":"record","payload":{"canonical_record":{"source":{"id":"2505.14398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T14:14:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d72ac408fc213effb898285f3afe486e13be5e441f364f180041741d728ccd49","abstract_canon_sha256":"3e0466db322910706f01b1a0448ea79e07753c6539cc6b3b61cfba5d8a7f618e"},"schema_version":"1.0"},"canonical_sha256":"e7500dc826e33845189d50919d26ad184e0fd9b4bce79d14fddd9b9840d7f549","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:00.844822Z","signature_b64":"KDPFxBDNtXeZ05X9o54T+G4CnHKB5K2oy+HtGOPraUN0qgxR7PF53kgBxnZULoRjZ3+WPneJvE5vZCGdwWPiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7500dc826e33845189d50919d26ad184e0fd9b4bce79d14fddd9b9840d7f549","last_reissued_at":"2026-07-05T11:06:00.844388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:00.844388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.14398","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":"2026-07-05T11:06:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0BCPKqrd5l/9pqkBSmSxqRhdhnBhBYBTS8NmkgnAVu6e7ofTJll+8s3Tmg0rbSaSJtzJK8Ve3Ap+PzbYfZKrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:49:03.894585Z"},"content_sha256":"cfcb37299e4d109ab28d6226598337ff4df58467efb16fc470991d271cc869b2","schema_version":"1.0","event_id":"sha256:cfcb37299e4d109ab28d6226598337ff4df58467efb16fc470991d271cc869b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:45IA3SBG4M4EKGE5KCIZ2JVNDB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dan Roth, Jacob Andreas, Michael Cafarella, Peter Baile Chen, Samuel Madden, Yi Zhang","submitted_at":"2025-05-20T14:14:38Z","abstract_excerpt":"While humans naturally learn and adapt from past experiences, large language models (LLMs) and their agentic counterparts struggle to retain reasoning from previous tasks and apply them in future contexts. To address this limitation, we propose a novel framework, log-augmented generation (LAG) that directly reuses prior computation and reasoning from past logs at test time to enhance model's ability to learn from previous tasks and perform better on new, unseen challenges, all while keeping the system efficient and scalable. Specifically, our system represents task logs using key-value (KV) ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14398","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/2505.14398/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":"2026-07-05T11:06:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fsv6Pb4AjHlqG+SA2NYxGlFhoB2yoISbvaER80m9kdaH6sykYgG0tfRcn/eDK30NHv6RXmQ03FcCkcdND4ZxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:49:03.895074Z"},"content_sha256":"a7296098198a3c4da8c3e9ba86ec28c3f68bb7907d4f459d4ee9853d9b3fd345","schema_version":"1.0","event_id":"sha256:a7296098198a3c4da8c3e9ba86ec28c3f68bb7907d4f459d4ee9853d9b3fd345"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/45IA3SBG4M4EKGE5KCIZ2JVNDB/bundle.json","state_url":"https://pith.science/pith/45IA3SBG4M4EKGE5KCIZ2JVNDB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/45IA3SBG4M4EKGE5KCIZ2JVNDB/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":"2026-08-09T09:49:03Z","links":{"resolver":"https://pith.science/pith/45IA3SBG4M4EKGE5KCIZ2JVNDB","bundle":"https://pith.science/pith/45IA3SBG4M4EKGE5KCIZ2JVNDB/bundle.json","state":"https://pith.science/pith/45IA3SBG4M4EKGE5KCIZ2JVNDB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/45IA3SBG4M4EKGE5KCIZ2JVNDB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:45IA3SBG4M4EKGE5KCIZ2JVNDB","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":"3e0466db322910706f01b1a0448ea79e07753c6539cc6b3b61cfba5d8a7f618e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T14:14:38Z","title_canon_sha256":"d72ac408fc213effb898285f3afe486e13be5e441f364f180041741d728ccd49"},"schema_version":"1.0","source":{"id":"2505.14398","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14398","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14398v1","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14398","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"45IA3SBG4M4E","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"45IA3SBG4M4EKGE5","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"45IA3SBG","created_at":"2026-07-05T11:06:00Z"}],"graph_snapshots":[{"event_id":"sha256:a7296098198a3c4da8c3e9ba86ec28c3f68bb7907d4f459d4ee9853d9b3fd345","target":"graph","created_at":"2026-07-05T11:06:00Z","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/2505.14398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While humans naturally learn and adapt from past experiences, large language models (LLMs) and their agentic counterparts struggle to retain reasoning from previous tasks and apply them in future contexts. To address this limitation, we propose a novel framework, log-augmented generation (LAG) that directly reuses prior computation and reasoning from past logs at test time to enhance model's ability to learn from previous tasks and perform better on new, unseen challenges, all while keeping the system efficient and scalable. Specifically, our system represents task logs using key-value (KV) ca","authors_text":"Dan Roth, Jacob Andreas, Michael Cafarella, Peter Baile Chen, Samuel Madden, Yi Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T14:14:38Z","title":"Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14398","kind":"arxiv","version":1},"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:cfcb37299e4d109ab28d6226598337ff4df58467efb16fc470991d271cc869b2","target":"record","created_at":"2026-07-05T11:06:00Z","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":"3e0466db322910706f01b1a0448ea79e07753c6539cc6b3b61cfba5d8a7f618e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T14:14:38Z","title_canon_sha256":"d72ac408fc213effb898285f3afe486e13be5e441f364f180041741d728ccd49"},"schema_version":"1.0","source":{"id":"2505.14398","kind":"arxiv","version":1}},"canonical_sha256":"e7500dc826e33845189d50919d26ad184e0fd9b4bce79d14fddd9b9840d7f549","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7500dc826e33845189d50919d26ad184e0fd9b4bce79d14fddd9b9840d7f549","first_computed_at":"2026-07-05T11:06:00.844388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:00.844388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KDPFxBDNtXeZ05X9o54T+G4CnHKB5K2oy+HtGOPraUN0qgxR7PF53kgBxnZULoRjZ3+WPneJvE5vZCGdwWPiDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:00.844822Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14398","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfcb37299e4d109ab28d6226598337ff4df58467efb16fc470991d271cc869b2","sha256:a7296098198a3c4da8c3e9ba86ec28c3f68bb7907d4f459d4ee9853d9b3fd345"],"state_sha256":"e7ed1327f57091b47d3a58ce21a340047f249091a2f10bdaf36ae9e922c8b455"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zhgHF4oVIFEfZyxCZ7TQrLCoUtZsyUBwYv9smO5SniJAV6IRunSeodiUmId5HKnALxI34bzvdl01jVYzhw4IAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:49:03.898451Z","bundle_sha256":"2e9944d60cacbe86498e749cd904c9529ae0a32aaedb7df5629221e3602443b3"}}