{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7E5A6R7EFGGLXXU5D6PPZ657MR","short_pith_number":"pith:7E5A6R7E","canonical_record":{"source":{"id":"2608.02444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T16:22:51Z","cross_cats_sorted":[],"title_canon_sha256":"445852220788ffbe4f79c13e7180762961df2afd7e0744f4ad58a17803b743c2","abstract_canon_sha256":"e256002983e84b336791fd9fd395415325658384adbb2120a435ff03b576b8f2"},"schema_version":"1.0"},"canonical_sha256":"f93a0f47e4298cbbde9d1f9efcfbbf644142f5ed9a3c5372bfd7cc8845cd551b","source":{"kind":"arxiv","id":"2608.02444","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02444","created_at":"2026-08-04T02:43:31Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02444v1","created_at":"2026-08-04T02:43:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02444","created_at":"2026-08-04T02:43:31Z"},{"alias_kind":"pith_short_12","alias_value":"7E5A6R7EFGGL","created_at":"2026-08-04T02:43:31Z"},{"alias_kind":"pith_short_16","alias_value":"7E5A6R7EFGGLXXU5","created_at":"2026-08-04T02:43:31Z"},{"alias_kind":"pith_short_8","alias_value":"7E5A6R7E","created_at":"2026-08-04T02:43:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7E5A6R7EFGGLXXU5D6PPZ657MR","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T16:22:51Z","cross_cats_sorted":[],"title_canon_sha256":"445852220788ffbe4f79c13e7180762961df2afd7e0744f4ad58a17803b743c2","abstract_canon_sha256":"e256002983e84b336791fd9fd395415325658384adbb2120a435ff03b576b8f2"},"schema_version":"1.0"},"canonical_sha256":"f93a0f47e4298cbbde9d1f9efcfbbf644142f5ed9a3c5372bfd7cc8845cd551b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:43:31.225505Z","signature_b64":"kazDKQDLEtcEWU51ZPIZiawupcYzy6IUqB8HnySt9bKzZMTvD3e0NraUaTLxd9DU5f2d3ynslg3d5a30H9QACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f93a0f47e4298cbbde9d1f9efcfbbf644142f5ed9a3c5372bfd7cc8845cd551b","last_reissued_at":"2026-08-04T02:43:31.223074Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:43:31.223074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02444","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":"2026-08-04T02:43:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i3GaxJZs5rxjiOwmLkDDDkW/ufkSP081FaGJWJWQIB56CCAnf4o+LvT1COEqvFFT0v07egER1pCQZ/f4DCOUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:39:07.100915Z"},"content_sha256":"e666b3a4e1c996b35f0cdffbf736cc713ac4613f7f2c475eb1f252469ea1564b","schema_version":"1.0","event_id":"sha256:e666b3a4e1c996b35f0cdffbf736cc713ac4613f7f2c475eb1f252469ea1564b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7E5A6R7EFGGLXXU5D6PPZ657MR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ParEvalLayer: When Partial LLM-Agent Evaluations Support a Decision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bonan Shen, Wei-Jung Huang","submitted_at":"2026-08-03T16:22:51Z","abstract_excerpt":"LLM-agent evaluations often produce task outcomes long before the full benchmark run is complete. A partial score is tempting to report, but it does not show whether the observed tasks support the same conclusion as the completed evaluation. Early tasks can omit important parts of a benchmark, running cheaper tasks first can distort the observed sample, and a rule that decides only easy pairs can appear accurate while leaving many comparisons unresolved. We introduce ParEvalLayer, a decision layer that reads paired outcomes for two agent systems and a comparison policy chosen in advance. For e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02444","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/2608.02444/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":"2026-08-04T02:43:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nstatGq6hbbyj+zw2Gi2mv8QjhhRYXdxiiAgEINOTRL9Y4dhl4XK0h33G1Qg4NSQy+rNuuHZlPhPS1auyeh5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:39:07.104021Z"},"content_sha256":"b875f7dd7ea76131ea3b97278c5f4ad5f87c3d92e1b54e8a8ac70719ac5baa67","schema_version":"1.0","event_id":"sha256:b875f7dd7ea76131ea3b97278c5f4ad5f87c3d92e1b54e8a8ac70719ac5baa67"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7E5A6R7EFGGLXXU5D6PPZ657MR/bundle.json","state_url":"https://pith.science/pith/7E5A6R7EFGGLXXU5D6PPZ657MR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7E5A6R7EFGGLXXU5D6PPZ657MR/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":"2026-08-05T16:39:07Z","links":{"resolver":"https://pith.science/pith/7E5A6R7EFGGLXXU5D6PPZ657MR","bundle":"https://pith.science/pith/7E5A6R7EFGGLXXU5D6PPZ657MR/bundle.json","state":"https://pith.science/pith/7E5A6R7EFGGLXXU5D6PPZ657MR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7E5A6R7EFGGLXXU5D6PPZ657MR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7E5A6R7EFGGLXXU5D6PPZ657MR","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":"e256002983e84b336791fd9fd395415325658384adbb2120a435ff03b576b8f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T16:22:51Z","title_canon_sha256":"445852220788ffbe4f79c13e7180762961df2afd7e0744f4ad58a17803b743c2"},"schema_version":"1.0","source":{"id":"2608.02444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02444","created_at":"2026-08-04T02:43:31Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02444v1","created_at":"2026-08-04T02:43:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02444","created_at":"2026-08-04T02:43:31Z"},{"alias_kind":"pith_short_12","alias_value":"7E5A6R7EFGGL","created_at":"2026-08-04T02:43:31Z"},{"alias_kind":"pith_short_16","alias_value":"7E5A6R7EFGGLXXU5","created_at":"2026-08-04T02:43:31Z"},{"alias_kind":"pith_short_8","alias_value":"7E5A6R7E","created_at":"2026-08-04T02:43:31Z"}],"graph_snapshots":[{"event_id":"sha256:b875f7dd7ea76131ea3b97278c5f4ad5f87c3d92e1b54e8a8ac70719ac5baa67","target":"graph","created_at":"2026-08-04T02:43:31Z","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/2608.02444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-agent evaluations often produce task outcomes long before the full benchmark run is complete. A partial score is tempting to report, but it does not show whether the observed tasks support the same conclusion as the completed evaluation. Early tasks can omit important parts of a benchmark, running cheaper tasks first can distort the observed sample, and a rule that decides only easy pairs can appear accurate while leaving many comparisons unresolved. We introduce ParEvalLayer, a decision layer that reads paired outcomes for two agent systems and a comparison policy chosen in advance. For e","authors_text":"Bonan Shen, Wei-Jung Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T16:22:51Z","title":"ParEvalLayer: When Partial LLM-Agent Evaluations Support a Decision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02444","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:e666b3a4e1c996b35f0cdffbf736cc713ac4613f7f2c475eb1f252469ea1564b","target":"record","created_at":"2026-08-04T02:43:31Z","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":"e256002983e84b336791fd9fd395415325658384adbb2120a435ff03b576b8f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T16:22:51Z","title_canon_sha256":"445852220788ffbe4f79c13e7180762961df2afd7e0744f4ad58a17803b743c2"},"schema_version":"1.0","source":{"id":"2608.02444","kind":"arxiv","version":1}},"canonical_sha256":"f93a0f47e4298cbbde9d1f9efcfbbf644142f5ed9a3c5372bfd7cc8845cd551b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f93a0f47e4298cbbde9d1f9efcfbbf644142f5ed9a3c5372bfd7cc8845cd551b","first_computed_at":"2026-08-04T02:43:31.223074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:43:31.223074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kazDKQDLEtcEWU51ZPIZiawupcYzy6IUqB8HnySt9bKzZMTvD3e0NraUaTLxd9DU5f2d3ynslg3d5a30H9QACw==","signature_status":"signed_v1","signed_at":"2026-08-04T02:43:31.225505Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e666b3a4e1c996b35f0cdffbf736cc713ac4613f7f2c475eb1f252469ea1564b","sha256:b875f7dd7ea76131ea3b97278c5f4ad5f87c3d92e1b54e8a8ac70719ac5baa67"],"state_sha256":"0bd1a70dc2866b3d3d1405f9b7932ebfc437a8eaee7a4662f118c0e6b04a2b6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rTEskLaS9y0+dTKjtkXsFFR130njuqm33eQ/3F3vAg0KRdIcmulJpvnuoqbBbjvo6ml1EZR8lzV+c13iGBdXCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:39:07.112349Z","bundle_sha256":"e1ed37860c979f5249614cb68b92ef1091b6aeb75acbb8ebd1d1f3ede73a0886"}}