{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XMWG26CYBDVVAG2BI3ZCJIZUJ5","short_pith_number":"pith:XMWG26CY","canonical_record":{"source":{"id":"2507.11508","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-15T17:23:56Z","cross_cats_sorted":[],"title_canon_sha256":"80c6c295fd0fd76b4588e4a9dba5e08ca353a2cbb79e853fc7545c9d4c067ac5","abstract_canon_sha256":"feb5e6edb4bc84e8ca09d5a66bc78e23001c3fecad28b850ec617dde41187847"},"schema_version":"1.0"},"canonical_sha256":"bb2c6d785808eb501b4146f224a3344f4592c4c7ac2c1a9cf538eefe02edc386","source":{"kind":"arxiv","id":"2507.11508","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11508","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11508v1","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11508","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"pith_short_12","alias_value":"XMWG26CYBDVV","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"pith_short_16","alias_value":"XMWG26CYBDVVAG2B","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"pith_short_8","alias_value":"XMWG26CY","created_at":"2026-07-05T11:37:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XMWG26CYBDVVAG2BI3ZCJIZUJ5","target":"record","payload":{"canonical_record":{"source":{"id":"2507.11508","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-15T17:23:56Z","cross_cats_sorted":[],"title_canon_sha256":"80c6c295fd0fd76b4588e4a9dba5e08ca353a2cbb79e853fc7545c9d4c067ac5","abstract_canon_sha256":"feb5e6edb4bc84e8ca09d5a66bc78e23001c3fecad28b850ec617dde41187847"},"schema_version":"1.0"},"canonical_sha256":"bb2c6d785808eb501b4146f224a3344f4592c4c7ac2c1a9cf538eefe02edc386","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:40.205477Z","signature_b64":"fLRXgWvWbcUluqfB4i/Jjf/+76t5UQQz4Lv6sAWBEr+ZMA17n+dld51NiLcpRKboUVyuuf3aK8QPAhs+oz5oAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb2c6d785808eb501b4146f224a3344f4592c4c7ac2c1a9cf538eefe02edc386","last_reissued_at":"2026-07-05T11:37:40.205028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:40.205028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.11508","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":"2026-07-05T11:37:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1e/JI42HOqCxrqbdNWEBGdc2WMsh/6VxoNfazIwtthzgwR5yfK4Hu/lor51Bq54Mg83EYCYJxUa0aMjHBlzPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:18:27.905271Z"},"content_sha256":"d710f4976b7c8dd00c0915f602285b116f0de6419d647e173b844902ebc7d15a","schema_version":"1.0","event_id":"sha256:d710f4976b7c8dd00c0915f602285b116f0de6419d647e173b844902ebc7d15a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XMWG26CYBDVVAG2BI3ZCJIZUJ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Real-World Summarization: When Evaluation Reaches Its Limits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ond\\v{r}ej Du\\v{s}ek, Patr\\'icia Schmidtov\\'a, Saad Mahamood","submitted_at":"2025-07-15T17:23:56Z","abstract_excerpt":"We examine evaluation of faithfulness to input data in the context of hotel highlights: brief LLM-generated summaries that capture unique features of accommodations. Through human evaluation campaigns involving categorical error assessment and span-level annotation, we compare traditional metrics, trainable methods, and LLM-as-a-judge approaches. Our findings reveal that simpler metrics like word overlap correlate surprisingly well with human judgments (Spearman correlation rank of 0.63), often outperforming more complex methods when applied to out-of-domain data. We further demonstrate that w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11508","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/2507.11508/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":"2026-07-05T11:37:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dYoEk+nJoXMjanw4pi2XWCRe0eceBBdedeDqMJ76ZVLP/Nu2m1TI6SzdE/QIxN8PESl9aVnHmpsmI0qqbc6UCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:18:27.905735Z"},"content_sha256":"db5808eff770c0c071e40ba194136d59f30d1f4967947681d85fdc5ff9ac1625","schema_version":"1.0","event_id":"sha256:db5808eff770c0c071e40ba194136d59f30d1f4967947681d85fdc5ff9ac1625"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XMWG26CYBDVVAG2BI3ZCJIZUJ5/bundle.json","state_url":"https://pith.science/pith/XMWG26CYBDVVAG2BI3ZCJIZUJ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XMWG26CYBDVVAG2BI3ZCJIZUJ5/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":"2026-08-19T00:18:27Z","links":{"resolver":"https://pith.science/pith/XMWG26CYBDVVAG2BI3ZCJIZUJ5","bundle":"https://pith.science/pith/XMWG26CYBDVVAG2BI3ZCJIZUJ5/bundle.json","state":"https://pith.science/pith/XMWG26CYBDVVAG2BI3ZCJIZUJ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XMWG26CYBDVVAG2BI3ZCJIZUJ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XMWG26CYBDVVAG2BI3ZCJIZUJ5","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":"feb5e6edb4bc84e8ca09d5a66bc78e23001c3fecad28b850ec617dde41187847","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-15T17:23:56Z","title_canon_sha256":"80c6c295fd0fd76b4588e4a9dba5e08ca353a2cbb79e853fc7545c9d4c067ac5"},"schema_version":"1.0","source":{"id":"2507.11508","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11508","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11508v1","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11508","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"pith_short_12","alias_value":"XMWG26CYBDVV","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"pith_short_16","alias_value":"XMWG26CYBDVVAG2B","created_at":"2026-07-05T11:37:40Z"},{"alias_kind":"pith_short_8","alias_value":"XMWG26CY","created_at":"2026-07-05T11:37:40Z"}],"graph_snapshots":[{"event_id":"sha256:db5808eff770c0c071e40ba194136d59f30d1f4967947681d85fdc5ff9ac1625","target":"graph","created_at":"2026-07-05T11:37:40Z","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/2507.11508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We examine evaluation of faithfulness to input data in the context of hotel highlights: brief LLM-generated summaries that capture unique features of accommodations. Through human evaluation campaigns involving categorical error assessment and span-level annotation, we compare traditional metrics, trainable methods, and LLM-as-a-judge approaches. Our findings reveal that simpler metrics like word overlap correlate surprisingly well with human judgments (Spearman correlation rank of 0.63), often outperforming more complex methods when applied to out-of-domain data. We further demonstrate that w","authors_text":"Ond\\v{r}ej Du\\v{s}ek, Patr\\'icia Schmidtov\\'a, Saad Mahamood","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-15T17:23:56Z","title":"Real-World Summarization: When Evaluation Reaches Its Limits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11508","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:d710f4976b7c8dd00c0915f602285b116f0de6419d647e173b844902ebc7d15a","target":"record","created_at":"2026-07-05T11:37:40Z","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":"feb5e6edb4bc84e8ca09d5a66bc78e23001c3fecad28b850ec617dde41187847","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-15T17:23:56Z","title_canon_sha256":"80c6c295fd0fd76b4588e4a9dba5e08ca353a2cbb79e853fc7545c9d4c067ac5"},"schema_version":"1.0","source":{"id":"2507.11508","kind":"arxiv","version":1}},"canonical_sha256":"bb2c6d785808eb501b4146f224a3344f4592c4c7ac2c1a9cf538eefe02edc386","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb2c6d785808eb501b4146f224a3344f4592c4c7ac2c1a9cf538eefe02edc386","first_computed_at":"2026-07-05T11:37:40.205028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:40.205028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fLRXgWvWbcUluqfB4i/Jjf/+76t5UQQz4Lv6sAWBEr+ZMA17n+dld51NiLcpRKboUVyuuf3aK8QPAhs+oz5oAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:40.205477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.11508","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d710f4976b7c8dd00c0915f602285b116f0de6419d647e173b844902ebc7d15a","sha256:db5808eff770c0c071e40ba194136d59f30d1f4967947681d85fdc5ff9ac1625"],"state_sha256":"5fd16352f8ca6e0600b6d122241b3dcfdf3c1ed7aebf93adfea428404c1d11c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbjklHkC9nzFXCXpyEYOq71zZjIJhhCPHsKINIBkHSEe3108FU2yN/LZ3SQ79rZ6tmo6metrzqdRkudmyp+6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T00:18:27.909303Z","bundle_sha256":"7de5ec9296068fc4aac3519c2704fbdf4a63d1173702a69668ef60d4d6c717fc"}}