{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7QQN3ZMVYRWTCYA5CNS5QIKBRZ","short_pith_number":"pith:7QQN3ZMV","canonical_record":{"source":{"id":"2508.15804","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T03:33:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3dc63227b97ac9b7ae775be1596b0049bf63506e9e23ccbf8f2f7359a7d2d4fc","abstract_canon_sha256":"ca05ca74978979c4cded92909922a1c41a8b1fd0f4307adef0d5c9bce0262417"},"schema_version":"1.0"},"canonical_sha256":"fc20dde595c46d31601d1365d821418e444b5904798c4f89bb4d5c7a13230e8b","source":{"kind":"arxiv","id":"2508.15804","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15804","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15804v1","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15804","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_12","alias_value":"7QQN3ZMVYRWT","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_16","alias_value":"7QQN3ZMVYRWTCYA5","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_8","alias_value":"7QQN3ZMV","created_at":"2026-07-05T11:57:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7QQN3ZMVYRWTCYA5CNS5QIKBRZ","target":"record","payload":{"canonical_record":{"source":{"id":"2508.15804","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T03:33:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3dc63227b97ac9b7ae775be1596b0049bf63506e9e23ccbf8f2f7359a7d2d4fc","abstract_canon_sha256":"ca05ca74978979c4cded92909922a1c41a8b1fd0f4307adef0d5c9bce0262417"},"schema_version":"1.0"},"canonical_sha256":"fc20dde595c46d31601d1365d821418e444b5904798c4f89bb4d5c7a13230e8b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:21.338122Z","signature_b64":"o0xOg71udB5gMyGNqtRNLsIV1rIbwLXaVYFD6PYnFz7NjE9KBh2uzOtSQIUnZaKnyDL3jzCtk0c4NPA64ItvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc20dde595c46d31601d1365d821418e444b5904798c4f89bb4d5c7a13230e8b","last_reissued_at":"2026-07-05T11:57:21.337778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:21.337778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.15804","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":"2026-07-05T11:57:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GVaMvANGJkyIbJHAhRK5HKU6CEuHv6ntRlD/3xHUUGw3VyNE2awRyvjHRTS3S7y7PaClTW7EJfKAKNXiiv30Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:59:48.830662Z"},"content_sha256":"0a7582588f0efb58e81fd773caa9024e592861de077dec3f5d75b44efb4e3e29","schema_version":"1.0","event_id":"sha256:0a7582588f0efb58e81fd773caa9024e592861de077dec3f5d75b44efb4e3e29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7QQN3ZMVYRWTCYA5CNS5QIKBRZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cong Ma, Kai Jia, Minghao Li, Ying Zeng, Zhihao Cheng","submitted_at":"2025-08-14T03:33:43Z","abstract_excerpt":"The advent of Deep Research agents has substantially reduced the time required for conducting extensive research tasks. However, these tasks inherently demand rigorous standards of factual accuracy and comprehensiveness, necessitating thorough evaluation before widespread adoption. In this paper, we propose ReportBench, a systematic benchmark designed to evaluate the content quality of research reports generated by large language models (LLMs). Our evaluation focuses on two critical dimensions: (1) the quality and relevance of cited literature, and (2) the faithfulness and veracity of the stat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15804","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/2508.15804/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":"2026-07-05T11:57:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nlMogvMlrPZfNqCqTwCDkiDu7OflA1BGvR5bARywXDC80VB8vhuq3GVmUJdXwUZPRT3Iau/7PUNzf32ZV02RAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:59:48.831183Z"},"content_sha256":"ef1a282a7c2ac927e07504f16d9ec0193732cd4a12a5a427736d4a567f632f5c","schema_version":"1.0","event_id":"sha256:ef1a282a7c2ac927e07504f16d9ec0193732cd4a12a5a427736d4a567f632f5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7QQN3ZMVYRWTCYA5CNS5QIKBRZ/bundle.json","state_url":"https://pith.science/pith/7QQN3ZMVYRWTCYA5CNS5QIKBRZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7QQN3ZMVYRWTCYA5CNS5QIKBRZ/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":"2026-08-10T04:59:48Z","links":{"resolver":"https://pith.science/pith/7QQN3ZMVYRWTCYA5CNS5QIKBRZ","bundle":"https://pith.science/pith/7QQN3ZMVYRWTCYA5CNS5QIKBRZ/bundle.json","state":"https://pith.science/pith/7QQN3ZMVYRWTCYA5CNS5QIKBRZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7QQN3ZMVYRWTCYA5CNS5QIKBRZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7QQN3ZMVYRWTCYA5CNS5QIKBRZ","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":"ca05ca74978979c4cded92909922a1c41a8b1fd0f4307adef0d5c9bce0262417","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T03:33:43Z","title_canon_sha256":"3dc63227b97ac9b7ae775be1596b0049bf63506e9e23ccbf8f2f7359a7d2d4fc"},"schema_version":"1.0","source":{"id":"2508.15804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15804","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15804v1","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15804","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_12","alias_value":"7QQN3ZMVYRWT","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_16","alias_value":"7QQN3ZMVYRWTCYA5","created_at":"2026-07-05T11:57:21Z"},{"alias_kind":"pith_short_8","alias_value":"7QQN3ZMV","created_at":"2026-07-05T11:57:21Z"}],"graph_snapshots":[{"event_id":"sha256:ef1a282a7c2ac927e07504f16d9ec0193732cd4a12a5a427736d4a567f632f5c","target":"graph","created_at":"2026-07-05T11:57:21Z","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/2508.15804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of Deep Research agents has substantially reduced the time required for conducting extensive research tasks. However, these tasks inherently demand rigorous standards of factual accuracy and comprehensiveness, necessitating thorough evaluation before widespread adoption. In this paper, we propose ReportBench, a systematic benchmark designed to evaluate the content quality of research reports generated by large language models (LLMs). Our evaluation focuses on two critical dimensions: (1) the quality and relevance of cited literature, and (2) the faithfulness and veracity of the stat","authors_text":"Cong Ma, Kai Jia, Minghao Li, Ying Zeng, Zhihao Cheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T03:33:43Z","title":"ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15804","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":"sha256:0a7582588f0efb58e81fd773caa9024e592861de077dec3f5d75b44efb4e3e29","target":"record","created_at":"2026-07-05T11:57:21Z","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":"ca05ca74978979c4cded92909922a1c41a8b1fd0f4307adef0d5c9bce0262417","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T03:33:43Z","title_canon_sha256":"3dc63227b97ac9b7ae775be1596b0049bf63506e9e23ccbf8f2f7359a7d2d4fc"},"schema_version":"1.0","source":{"id":"2508.15804","kind":"arxiv","version":1}},"canonical_sha256":"fc20dde595c46d31601d1365d821418e444b5904798c4f89bb4d5c7a13230e8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc20dde595c46d31601d1365d821418e444b5904798c4f89bb4d5c7a13230e8b","first_computed_at":"2026-07-05T11:57:21.337778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:21.337778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o0xOg71udB5gMyGNqtRNLsIV1rIbwLXaVYFD6PYnFz7NjE9KBh2uzOtSQIUnZaKnyDL3jzCtk0c4NPA64ItvBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:21.338122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.15804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a7582588f0efb58e81fd773caa9024e592861de077dec3f5d75b44efb4e3e29","sha256:ef1a282a7c2ac927e07504f16d9ec0193732cd4a12a5a427736d4a567f632f5c"],"state_sha256":"ae3363fa93eaf834fa31d0a7bcc5c36c7fb34e9faa513aeff654a95aa60c6d06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h+06mh4FxRXkamP+LStmQYsg9TnVC60dnMWbf3Fx8/e4sKFjq9p6hfB1W+JkB1cJx48wrmsYo1lsZRSz+LUhBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T04:59:48.837931Z","bundle_sha256":"5bbea8b8a0667cbb018c80c1a1d652a20916871ece67ba0c9394d6df80c8047f"}}