{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:O652YWPR3YK3YCTAEYP574K4DX","short_pith_number":"pith:O652YWPR","canonical_record":{"source":{"id":"2606.28050","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-26T12:52:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ecace79139242ec0faba8961dfba97010fbf54627520296347f9538f6fd6529","abstract_canon_sha256":"670eb9d0d778f9f2c11d3ba13f8165ea5d16c6c97f24a3c381f9e247c648b6b7"},"schema_version":"1.0"},"canonical_sha256":"77bbac59f1de15bc0a60261fdff15c1dc604e5e5f410eac47a0369cf3ff491d6","source":{"kind":"arxiv","id":"2606.28050","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28050","created_at":"2026-06-29T01:14:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28050v1","created_at":"2026-06-29T01:14:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28050","created_at":"2026-06-29T01:14:56Z"},{"alias_kind":"pith_short_12","alias_value":"O652YWPR3YK3","created_at":"2026-06-29T01:14:56Z"},{"alias_kind":"pith_short_16","alias_value":"O652YWPR3YK3YCTA","created_at":"2026-06-29T01:14:56Z"},{"alias_kind":"pith_short_8","alias_value":"O652YWPR","created_at":"2026-06-29T01:14:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:O652YWPR3YK3YCTAEYP574K4DX","target":"record","payload":{"canonical_record":{"source":{"id":"2606.28050","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-26T12:52:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ecace79139242ec0faba8961dfba97010fbf54627520296347f9538f6fd6529","abstract_canon_sha256":"670eb9d0d778f9f2c11d3ba13f8165ea5d16c6c97f24a3c381f9e247c648b6b7"},"schema_version":"1.0"},"canonical_sha256":"77bbac59f1de15bc0a60261fdff15c1dc604e5e5f410eac47a0369cf3ff491d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:56.343402Z","signature_b64":"ZcYRdFmYm0bhql8cW2aNZbSrhKUh/n0rsIZJSMj6uWnx1ADV0zORSlwKuJy/Mdy0sQbQZdHesKhHQvTwm67uAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77bbac59f1de15bc0a60261fdff15c1dc604e5e5f410eac47a0369cf3ff491d6","last_reissued_at":"2026-06-29T01:14:56.343003Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:56.343003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.28050","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":"2026-06-29T01:14:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kORZ1YARvWDaeL7n4pdQAU4B36QT8XRyA9ii7JT4UfcmOMfbyUxv67LHIf0qymhpNBgw6/ZKzN77QxPgzCsMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T07:19:08.789495Z"},"content_sha256":"e9b6396a5a73832ed57e27f2efea62027d2d57605f8efe24ce33385e5b3f5143","schema_version":"1.0","event_id":"sha256:e9b6396a5a73832ed57e27f2efea62027d2d57605f8efe24ce33385e5b3f5143"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:O652YWPR3YK3YCTAEYP574K4DX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Sambaran Bandyopadhyay","submitted_at":"2026-06-26T12:52:03Z","abstract_excerpt":"LLM-as-a-Judge and self-evaluation pipelines implicitly assume that evaluation is easier than generation. We test this in a controlled in-context QA setting where a context passage is the sole information source and each model judges the answer it generated, removing the parametric-knowledge confound of open-domain comparisons. Across four benchmarks (SQuAD 2.0, DROP, HotpotQA, MuSiQue) and two models, evaluation is not uniformly easier: generation accuracy exceeds self-evaluation on three of four, with multi-hop MuSiQue the exception. Attention analysis reveals why: evaluation attends to cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28050","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/2606.28050/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":"2026-06-29T01:14:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mgpJa5PE1ZcNsdnbaBIeVhRSWxiWbdBk6oguMgCRkedHpc5puuTYiBRnkwUj6o5w/TpPtx2PcAQE1AuCzjo0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T07:19:08.789869Z"},"content_sha256":"82c339165635ff78cc3ab3b9e58d39c98b713fdc5f9c1399cf80f797ee9fdafe","schema_version":"1.0","event_id":"sha256:82c339165635ff78cc3ab3b9e58d39c98b713fdc5f9c1399cf80f797ee9fdafe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O652YWPR3YK3YCTAEYP574K4DX/bundle.json","state_url":"https://pith.science/pith/O652YWPR3YK3YCTAEYP574K4DX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O652YWPR3YK3YCTAEYP574K4DX/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":"2026-07-04T07:19:08Z","links":{"resolver":"https://pith.science/pith/O652YWPR3YK3YCTAEYP574K4DX","bundle":"https://pith.science/pith/O652YWPR3YK3YCTAEYP574K4DX/bundle.json","state":"https://pith.science/pith/O652YWPR3YK3YCTAEYP574K4DX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O652YWPR3YK3YCTAEYP574K4DX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O652YWPR3YK3YCTAEYP574K4DX","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":"670eb9d0d778f9f2c11d3ba13f8165ea5d16c6c97f24a3c381f9e247c648b6b7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-26T12:52:03Z","title_canon_sha256":"2ecace79139242ec0faba8961dfba97010fbf54627520296347f9538f6fd6529"},"schema_version":"1.0","source":{"id":"2606.28050","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28050","created_at":"2026-06-29T01:14:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28050v1","created_at":"2026-06-29T01:14:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28050","created_at":"2026-06-29T01:14:56Z"},{"alias_kind":"pith_short_12","alias_value":"O652YWPR3YK3","created_at":"2026-06-29T01:14:56Z"},{"alias_kind":"pith_short_16","alias_value":"O652YWPR3YK3YCTA","created_at":"2026-06-29T01:14:56Z"},{"alias_kind":"pith_short_8","alias_value":"O652YWPR","created_at":"2026-06-29T01:14:56Z"}],"graph_snapshots":[{"event_id":"sha256:82c339165635ff78cc3ab3b9e58d39c98b713fdc5f9c1399cf80f797ee9fdafe","target":"graph","created_at":"2026-06-29T01:14:56Z","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/2606.28050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-as-a-Judge and self-evaluation pipelines implicitly assume that evaluation is easier than generation. We test this in a controlled in-context QA setting where a context passage is the sole information source and each model judges the answer it generated, removing the parametric-knowledge confound of open-domain comparisons. Across four benchmarks (SQuAD 2.0, DROP, HotpotQA, MuSiQue) and two models, evaluation is not uniformly easier: generation accuracy exceeds self-evaluation on three of four, with multi-hop MuSiQue the exception. Attention analysis reveals why: evaluation attends to cont","authors_text":"Sambaran Bandyopadhyay","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-26T12:52:03Z","title":"Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28050","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:e9b6396a5a73832ed57e27f2efea62027d2d57605f8efe24ce33385e5b3f5143","target":"record","created_at":"2026-06-29T01:14:56Z","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":"670eb9d0d778f9f2c11d3ba13f8165ea5d16c6c97f24a3c381f9e247c648b6b7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-26T12:52:03Z","title_canon_sha256":"2ecace79139242ec0faba8961dfba97010fbf54627520296347f9538f6fd6529"},"schema_version":"1.0","source":{"id":"2606.28050","kind":"arxiv","version":1}},"canonical_sha256":"77bbac59f1de15bc0a60261fdff15c1dc604e5e5f410eac47a0369cf3ff491d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77bbac59f1de15bc0a60261fdff15c1dc604e5e5f410eac47a0369cf3ff491d6","first_computed_at":"2026-06-29T01:14:56.343003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:14:56.343003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZcYRdFmYm0bhql8cW2aNZbSrhKUh/n0rsIZJSMj6uWnx1ADV0zORSlwKuJy/Mdy0sQbQZdHesKhHQvTwm67uAQ==","signature_status":"signed_v1","signed_at":"2026-06-29T01:14:56.343402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28050","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9b6396a5a73832ed57e27f2efea62027d2d57605f8efe24ce33385e5b3f5143","sha256:82c339165635ff78cc3ab3b9e58d39c98b713fdc5f9c1399cf80f797ee9fdafe"],"state_sha256":"71069f86640d4249194c3300d073f650764a4b1f193985662147e864227cf43e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X6IigFwmZmd1g1zl6fTeZ+CpZe/ZK8h6e4EbwZlZgUdWKJyXVKeEyGu8UrSGcjK2LArt/11t6bIFxfn5sALsDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T07:19:08.791840Z","bundle_sha256":"6a91bc2f62a1f24dcdeb0b8cd7a39793eb8c97e884a7afa630a6bb4892bcb3fe"}}