{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:G3XDCUQVX5Q52FDJCRLE7TSHGV","short_pith_number":"pith:G3XDCUQV","canonical_record":{"source":{"id":"2607.12227","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T00:18:42Z","cross_cats_sorted":[],"title_canon_sha256":"1747e19c78f562c8ba789f436128379a527dea5a7ffb08becb6ab66789c93e5c","abstract_canon_sha256":"9c1d32d4242f34a63261590c3e0ccf531b1a446e8c457d48e837d1b21d923c8c"},"schema_version":"1.0"},"canonical_sha256":"36ee315215bf61dd146914564fce4735715cea4016fe23cd464eb399b794cf67","source":{"kind":"arxiv","id":"2607.12227","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.12227","created_at":"2026-07-15T00:21:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.12227v1","created_at":"2026-07-15T00:21:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12227","created_at":"2026-07-15T00:21:39Z"},{"alias_kind":"pith_short_12","alias_value":"G3XDCUQVX5Q5","created_at":"2026-07-15T00:21:39Z"},{"alias_kind":"pith_short_16","alias_value":"G3XDCUQVX5Q52FDJ","created_at":"2026-07-15T00:21:39Z"},{"alias_kind":"pith_short_8","alias_value":"G3XDCUQV","created_at":"2026-07-15T00:21:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:G3XDCUQVX5Q52FDJCRLE7TSHGV","target":"record","payload":{"canonical_record":{"source":{"id":"2607.12227","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T00:18:42Z","cross_cats_sorted":[],"title_canon_sha256":"1747e19c78f562c8ba789f436128379a527dea5a7ffb08becb6ab66789c93e5c","abstract_canon_sha256":"9c1d32d4242f34a63261590c3e0ccf531b1a446e8c457d48e837d1b21d923c8c"},"schema_version":"1.0"},"canonical_sha256":"36ee315215bf61dd146914564fce4735715cea4016fe23cd464eb399b794cf67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T00:21:39.586848Z","signature_b64":"gCbuS7ERNLtW5+NR5G8kYbMPVeHojJ1JUyblw6Azgsh8c1EzpP+CzQvPyfizQvW6o1taB4oURzVqgNkWIRs4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36ee315215bf61dd146914564fce4735715cea4016fe23cd464eb399b794cf67","last_reissued_at":"2026-07-15T00:21:39.586069Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T00:21:39.586069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.12227","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":"2026-07-15T00:21:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kF8M1U7Wcs5NQOp2xAIZds5ya2M3qWwaSidN98fo23ngxMbjFSLHmZB2goYsIxbm2ZgZAPByOwwLwg7c0D0eCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:35:41.619798Z"},"content_sha256":"7536e5d928a5fed9040e949a10a3fefcf77a449442f0046d73c5e0207d7db808","schema_version":"1.0","event_id":"sha256:7536e5d928a5fed9040e949a10a3fefcf77a449442f0046d73c5e0207d7db808"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:G3XDCUQVX5Q52FDJCRLE7TSHGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking the Evaluation of Harness Evolution for Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hannaneh Hajishirzi, Huaisheng Zhu, Pradeep Dasigi, Shakti Senthil, Teng Xiao, Yige Yuan, Yike Wang, Yulia Tsvetkov, Zhengyu Chen, Zhengyu Hu","submitted_at":"2026-07-14T00:18:42Z","abstract_excerpt":"We revisit the evaluation of automatic harness evolution for LLM agents. Existing harness evolution methods use unit test cases to search for harness configurations and then report final performance on the same public benchmark. This protocol raises two fundamental concerns. First, harness evolution is itself an iterative search procedure that repeatedly evaluates and revises candidate harnesses using task feedback. As in agentic test-time scaling, it should therefore be compared with simple task-level search baselines under matched feedback and inference budgets to determine whether its gains"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12227","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/2607.12227/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":"2026-07-15T00:21:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n4OROEEU9Qb3PLpG6BNGT6SPIWgbnzfNCtsIdxiBIgu8mHjgmy8I0dvIN1IhV1hc9HB4x27S8t/RFOOi0CxWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:35:41.620679Z"},"content_sha256":"fc87761a60c8d716f8f35541e45727170da1051194e825e4ae54df09a0a7f425","schema_version":"1.0","event_id":"sha256:fc87761a60c8d716f8f35541e45727170da1051194e825e4ae54df09a0a7f425"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G3XDCUQVX5Q52FDJCRLE7TSHGV/bundle.json","state_url":"https://pith.science/pith/G3XDCUQVX5Q52FDJCRLE7TSHGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G3XDCUQVX5Q52FDJCRLE7TSHGV/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":"2026-08-06T09:35:41Z","links":{"resolver":"https://pith.science/pith/G3XDCUQVX5Q52FDJCRLE7TSHGV","bundle":"https://pith.science/pith/G3XDCUQVX5Q52FDJCRLE7TSHGV/bundle.json","state":"https://pith.science/pith/G3XDCUQVX5Q52FDJCRLE7TSHGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G3XDCUQVX5Q52FDJCRLE7TSHGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G3XDCUQVX5Q52FDJCRLE7TSHGV","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":"9c1d32d4242f34a63261590c3e0ccf531b1a446e8c457d48e837d1b21d923c8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T00:18:42Z","title_canon_sha256":"1747e19c78f562c8ba789f436128379a527dea5a7ffb08becb6ab66789c93e5c"},"schema_version":"1.0","source":{"id":"2607.12227","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.12227","created_at":"2026-07-15T00:21:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.12227v1","created_at":"2026-07-15T00:21:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12227","created_at":"2026-07-15T00:21:39Z"},{"alias_kind":"pith_short_12","alias_value":"G3XDCUQVX5Q5","created_at":"2026-07-15T00:21:39Z"},{"alias_kind":"pith_short_16","alias_value":"G3XDCUQVX5Q52FDJ","created_at":"2026-07-15T00:21:39Z"},{"alias_kind":"pith_short_8","alias_value":"G3XDCUQV","created_at":"2026-07-15T00:21:39Z"}],"graph_snapshots":[{"event_id":"sha256:fc87761a60c8d716f8f35541e45727170da1051194e825e4ae54df09a0a7f425","target":"graph","created_at":"2026-07-15T00:21:39Z","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/2607.12227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We revisit the evaluation of automatic harness evolution for LLM agents. Existing harness evolution methods use unit test cases to search for harness configurations and then report final performance on the same public benchmark. This protocol raises two fundamental concerns. First, harness evolution is itself an iterative search procedure that repeatedly evaluates and revises candidate harnesses using task feedback. As in agentic test-time scaling, it should therefore be compared with simple task-level search baselines under matched feedback and inference budgets to determine whether its gains","authors_text":"Hannaneh Hajishirzi, Huaisheng Zhu, Pradeep Dasigi, Shakti Senthil, Teng Xiao, Yige Yuan, Yike Wang, Yulia Tsvetkov, Zhengyu Chen, Zhengyu Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T00:18:42Z","title":"Rethinking the Evaluation of Harness Evolution for Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12227","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":"sha256:7536e5d928a5fed9040e949a10a3fefcf77a449442f0046d73c5e0207d7db808","target":"record","created_at":"2026-07-15T00:21:39Z","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":"9c1d32d4242f34a63261590c3e0ccf531b1a446e8c457d48e837d1b21d923c8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T00:18:42Z","title_canon_sha256":"1747e19c78f562c8ba789f436128379a527dea5a7ffb08becb6ab66789c93e5c"},"schema_version":"1.0","source":{"id":"2607.12227","kind":"arxiv","version":1}},"canonical_sha256":"36ee315215bf61dd146914564fce4735715cea4016fe23cd464eb399b794cf67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36ee315215bf61dd146914564fce4735715cea4016fe23cd464eb399b794cf67","first_computed_at":"2026-07-15T00:21:39.586069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-15T00:21:39.586069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gCbuS7ERNLtW5+NR5G8kYbMPVeHojJ1JUyblw6Azgsh8c1EzpP+CzQvPyfizQvW6o1taB4oURzVqgNkWIRs4CA==","signature_status":"signed_v1","signed_at":"2026-07-15T00:21:39.586848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.12227","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7536e5d928a5fed9040e949a10a3fefcf77a449442f0046d73c5e0207d7db808","sha256:fc87761a60c8d716f8f35541e45727170da1051194e825e4ae54df09a0a7f425"],"state_sha256":"f8e847e6ee9e27160c13330fe11044fdd5924a4a18ce505541135d00f13ae7a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"min4yPSHyNXQomzkkuYJCZhwMbrdzbXz4zPgEdHAgyTtWtpz+CShhI2SJsUpB7m9kdQmdNOlnjo63+dguECjDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:35:41.676287Z","bundle_sha256":"04bd0b2c4158cd4382c3e9e88dcc97e565094141fd9dc38aac11249f988d2105"}}