{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XLZTRT52DFIFRZP6ICYFW72Y46","short_pith_number":"pith:XLZTRT52","canonical_record":{"source":{"id":"2604.11811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2026-04-10T03:22:26Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"5940f3f552839e945d0d9d51ae0c4950f5ad766c0b0911d674649645196452be","abstract_canon_sha256":"615e6f1e42d13bb7870ed92f3f47a8849dbf1aea0366307132a79d9d740043ce"},"schema_version":"1.0"},"canonical_sha256":"baf338cfba195058e5fe40b05b7f58e7a88476312353e31d2913a86b38c0e34f","source":{"kind":"arxiv","id":"2604.11811","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11811","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11811v2","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11811","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"pith_short_12","alias_value":"XLZTRT52DFIF","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"pith_short_16","alias_value":"XLZTRT52DFIFRZP6","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"pith_short_8","alias_value":"XLZTRT52","created_at":"2026-05-26T01:03:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XLZTRT52DFIFRZP6ICYFW72Y46","target":"record","payload":{"canonical_record":{"source":{"id":"2604.11811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2026-04-10T03:22:26Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"5940f3f552839e945d0d9d51ae0c4950f5ad766c0b0911d674649645196452be","abstract_canon_sha256":"615e6f1e42d13bb7870ed92f3f47a8849dbf1aea0366307132a79d9d740043ce"},"schema_version":"1.0"},"canonical_sha256":"baf338cfba195058e5fe40b05b7f58e7a88476312353e31d2913a86b38c0e34f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:29.940959Z","signature_b64":"W9sDJI9woTzYOkXwQ5unXa3PXvTrpomuDW7A8DCa5XBjTNPoNguQwhElQqy9h0h1yZLMQQIKNPwY9LxpiD6/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baf338cfba195058e5fe40b05b7f58e7a88476312353e31d2913a86b38c0e34f","last_reissued_at":"2026-05-26T01:03:29.940052Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:29.940052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.11811","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":"2026-05-26T01:03:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WtgkGYlReaSX6dqbuiNeBWuowJmOsLfEzR1ittQgTy8ON1b4cdev2rrh+34lbZ7yNPWhkgOfvdjpNesoxcR3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T16:35:29.399810Z"},"content_sha256":"53cbce0f0d46426cb6465c4064f6a270205b81d89aed498a9e6486ea88a2e9cb","schema_version":"1.0","event_id":"sha256:53cbce0f0d46426cb6465c4064f6a270205b81d89aed498a9e6486ea88a2e9cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XLZTRT52DFIFRZP6ICYFW72Y46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"M$^\\star$: Every Task Deserves Its Own Memory Harness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"LLM agents perform better with task-specific memory programs evolved as Python code than with any fixed shared design.","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.PL","authors_text":"Mirror Xu, Shiwei Zhang, Shujie Liu, Wanlu Shi, Wenbo Pan, Xiangyang Zhou, Xiaohua Jia","submitted_at":"2026-04-10T03:22:26Z","abstract_excerpt":"Large language model agents rely on specialized memory systems to accumulate and reuse knowledge during extended interactions. Recent architectures typically adopt a fixed memory design tailored to specific domains, such as semantic retrieval for conversations or skills reused for coding. However, a memory system optimized for one purpose frequently fails to transfer to others. To address this limitation, we introduce M$^\\star$, a method that automatically discovers task-optimized memory harnesses through executable program evolution. Specifically, M$^\\star$ models an agent memory system as a "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"M$^* improves performance over existing fixed-memory baselines robustly across all evaluated tasks. Furthermore, the evolved memory programs exhibit structurally distinct processing mechanisms for each domain.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That reflective population-based code evolution on the chosen benchmarks will reliably discover memory programs that are both superior and generalizable beyond the specific evaluation tasks and failure modes analyzed.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"M* evolves distinct Python memory programs per task via population-based reflective search, outperforming fixed-memory baselines on conversation, planning, and reasoning benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLM agents perform better with task-specific memory programs evolved as Python code than with any fixed shared design.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"feac4ba2381661eef6410860175d7320b30380b7196a390f4c7caeb7e37d229e"},"source":{"id":"2604.11811","kind":"arxiv","version":2},"verdict":{"id":"492efbc2-7f1c-4924-aa07-ace7911b35ea","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T17:34:40.321222Z","strongest_claim":"M$^* improves performance over existing fixed-memory baselines robustly across all evaluated tasks. Furthermore, the evolved memory programs exhibit structurally distinct processing mechanisms for each domain.","one_line_summary":"M* evolves distinct Python memory programs per task via population-based reflective search, outperforming fixed-memory baselines on conversation, planning, and reasoning benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That reflective population-based code evolution on the chosen benchmarks will reliably discover memory programs that are both superior and generalizable beyond the specific evaluation tasks and failure modes analyzed.","pith_extraction_headline":"LLM agents perform better with task-specific memory programs evolved as Python code than with any fixed shared design."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.11811/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":"492efbc2-7f1c-4924-aa07-ace7911b35ea"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ph2ZSq5CU+RF9bXIzgR2b6XkghToniaY+er6cDk3aLuBkGaU3vpZWRVqeOKi76XFACSNOaDfzL0IfAeHLirSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T16:35:29.400342Z"},"content_sha256":"3b4771e04757f431ce9ff5a4c3feaf4ceec7eec7c780711cab3feb27bc4a6d77","schema_version":"1.0","event_id":"sha256:3b4771e04757f431ce9ff5a4c3feaf4ceec7eec7c780711cab3feb27bc4a6d77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLZTRT52DFIFRZP6ICYFW72Y46/bundle.json","state_url":"https://pith.science/pith/XLZTRT52DFIFRZP6ICYFW72Y46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLZTRT52DFIFRZP6ICYFW72Y46/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":"2026-06-11T16:35:29Z","links":{"resolver":"https://pith.science/pith/XLZTRT52DFIFRZP6ICYFW72Y46","bundle":"https://pith.science/pith/XLZTRT52DFIFRZP6ICYFW72Y46/bundle.json","state":"https://pith.science/pith/XLZTRT52DFIFRZP6ICYFW72Y46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLZTRT52DFIFRZP6ICYFW72Y46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XLZTRT52DFIFRZP6ICYFW72Y46","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":"615e6f1e42d13bb7870ed92f3f47a8849dbf1aea0366307132a79d9d740043ce","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2026-04-10T03:22:26Z","title_canon_sha256":"5940f3f552839e945d0d9d51ae0c4950f5ad766c0b0911d674649645196452be"},"schema_version":"1.0","source":{"id":"2604.11811","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11811","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11811v2","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11811","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"pith_short_12","alias_value":"XLZTRT52DFIF","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"pith_short_16","alias_value":"XLZTRT52DFIFRZP6","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"pith_short_8","alias_value":"XLZTRT52","created_at":"2026-05-26T01:03:29Z"}],"graph_snapshots":[{"event_id":"sha256:3b4771e04757f431ce9ff5a4c3feaf4ceec7eec7c780711cab3feb27bc4a6d77","target":"graph","created_at":"2026-05-26T01:03:29Z","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":"M$^* improves performance over existing fixed-memory baselines robustly across all evaluated tasks. Furthermore, the evolved memory programs exhibit structurally distinct processing mechanisms for each domain."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That reflective population-based code evolution on the chosen benchmarks will reliably discover memory programs that are both superior and generalizable beyond the specific evaluation tasks and failure modes analyzed."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"M* evolves distinct Python memory programs per task via population-based reflective search, outperforming fixed-memory baselines on conversation, planning, and reasoning benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LLM agents perform better with task-specific memory programs evolved as Python code than with any fixed shared design."}],"snapshot_sha256":"feac4ba2381661eef6410860175d7320b30380b7196a390f4c7caeb7e37d229e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.11811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model agents rely on specialized memory systems to accumulate and reuse knowledge during extended interactions. Recent architectures typically adopt a fixed memory design tailored to specific domains, such as semantic retrieval for conversations or skills reused for coding. However, a memory system optimized for one purpose frequently fails to transfer to others. To address this limitation, we introduce M$^\\star$, a method that automatically discovers task-optimized memory harnesses through executable program evolution. Specifically, M$^\\star$ models an agent memory system as a ","authors_text":"Mirror Xu, Shiwei Zhang, Shujie Liu, Wanlu Shi, Wenbo Pan, Xiangyang Zhou, Xiaohua Jia","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"LLM agents perform better with task-specific memory programs evolved as Python code than with any fixed shared design.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2026-04-10T03:22:26Z","title":"M$^\\star$: Every Task Deserves Its Own Memory Harness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.11811","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T17:34:40.321222Z","id":"492efbc2-7f1c-4924-aa07-ace7911b35ea","model_set":{"reader":"grok-4.3"},"one_line_summary":"M* evolves distinct Python memory programs per task via population-based reflective search, outperforming fixed-memory baselines on conversation, planning, and reasoning benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"LLM agents perform better with task-specific memory programs evolved as Python code than with any fixed shared design.","strongest_claim":"M$^* improves performance over existing fixed-memory baselines robustly across all evaluated tasks. Furthermore, the evolved memory programs exhibit structurally distinct processing mechanisms for each domain.","weakest_assumption":"That reflective population-based code evolution on the chosen benchmarks will reliably discover memory programs that are both superior and generalizable beyond the specific evaluation tasks and failure modes analyzed."}},"verdict_id":"492efbc2-7f1c-4924-aa07-ace7911b35ea"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:53cbce0f0d46426cb6465c4064f6a270205b81d89aed498a9e6486ea88a2e9cb","target":"record","created_at":"2026-05-26T01:03:29Z","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":"615e6f1e42d13bb7870ed92f3f47a8849dbf1aea0366307132a79d9d740043ce","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2026-04-10T03:22:26Z","title_canon_sha256":"5940f3f552839e945d0d9d51ae0c4950f5ad766c0b0911d674649645196452be"},"schema_version":"1.0","source":{"id":"2604.11811","kind":"arxiv","version":2}},"canonical_sha256":"baf338cfba195058e5fe40b05b7f58e7a88476312353e31d2913a86b38c0e34f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"baf338cfba195058e5fe40b05b7f58e7a88476312353e31d2913a86b38c0e34f","first_computed_at":"2026-05-26T01:03:29.940052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:29.940052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W9sDJI9woTzYOkXwQ5unXa3PXvTrpomuDW7A8DCa5XBjTNPoNguQwhElQqy9h0h1yZLMQQIKNPwY9LxpiD6/Dw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:29.940959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.11811","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53cbce0f0d46426cb6465c4064f6a270205b81d89aed498a9e6486ea88a2e9cb","sha256:3b4771e04757f431ce9ff5a4c3feaf4ceec7eec7c780711cab3feb27bc4a6d77"],"state_sha256":"8ac2223f2a63e0603a0d4f68925c70056ad752b285158343dc970c39bb6c1913"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nmfY+1iTPeivoxY3SX1v0axgiSpD68OgwTWDMnTcTwMdZiwmEEBUzlGjcZAwf7dhT1e7AulspQGn4D7xvAwBCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T16:35:29.402842Z","bundle_sha256":"5c05b58ad363c5d68c13588e643d82876ff409369d0e745b29bc9d0e6a3e8b85"}}