{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3UIXGXVTVYBPQIEK7NE2VLLZ7C","short_pith_number":"pith:3UIXGXVT","canonical_record":{"source":{"id":"2608.02372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T15:15:55Z","cross_cats_sorted":[],"title_canon_sha256":"98301a209b3d4520de0fcf5ba2aaf1387987a0ff9101915979b360cc5304d686","abstract_canon_sha256":"2b83c55c75618228aa7701038d8f78df4301cb8d9e9e44c77017e8f9ff01ad1a"},"schema_version":"1.0"},"canonical_sha256":"dd11735eb3ae02f8208afb49aaad79f8a74b300ec5c28031830c5a8f9a862187","source":{"kind":"arxiv","id":"2608.02372","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02372","created_at":"2026-08-04T02:12:05Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02372v1","created_at":"2026-08-04T02:12:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02372","created_at":"2026-08-04T02:12:05Z"},{"alias_kind":"pith_short_12","alias_value":"3UIXGXVTVYBP","created_at":"2026-08-04T02:12:05Z"},{"alias_kind":"pith_short_16","alias_value":"3UIXGXVTVYBPQIEK","created_at":"2026-08-04T02:12:05Z"},{"alias_kind":"pith_short_8","alias_value":"3UIXGXVT","created_at":"2026-08-04T02:12:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3UIXGXVTVYBPQIEK7NE2VLLZ7C","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T15:15:55Z","cross_cats_sorted":[],"title_canon_sha256":"98301a209b3d4520de0fcf5ba2aaf1387987a0ff9101915979b360cc5304d686","abstract_canon_sha256":"2b83c55c75618228aa7701038d8f78df4301cb8d9e9e44c77017e8f9ff01ad1a"},"schema_version":"1.0"},"canonical_sha256":"dd11735eb3ae02f8208afb49aaad79f8a74b300ec5c28031830c5a8f9a862187","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:12:05.409943Z","signature_b64":"Zlm6zdPnETafp3ekS5ea2mp0X/f7YHtMtqr97+s4hENQqcIib7pRotQrKM+EpIUmsR9RZeHPPlvoj2HhiHv9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd11735eb3ae02f8208afb49aaad79f8a74b300ec5c28031830c5a8f9a862187","last_reissued_at":"2026-08-04T02:12:05.408170Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:12:05.408170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02372","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":"2026-08-04T02:12:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GTZygQjhE4zrCf4rqe+DN3+qi7SpIO6Z+r8mU/rcX4VSIXm4A89zEavLVCf6kcJYcY+sZ72dUBp7Lvut/rOdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:19:52.071146Z"},"content_sha256":"5cb7ef2239a184087804f86083ff06f040d97770394b4552a0f0aecad12438c9","schema_version":"1.0","event_id":"sha256:5cb7ef2239a184087804f86083ff06f040d97770394b4552a0f0aecad12438c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3UIXGXVTVYBPQIEK7NE2VLLZ7C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PredAct-Bench: Benchmarking Tool-Augmented Dialogue under Controlled Tool Noise","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdulrahman AlRabah, Abdussalam Alawini, Dilek Hakkani-T\\\"ur, Xiaocheng Yang","submitted_at":"2026-08-03T15:15:55Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly deployed in task-oriented dialogue systems that support multi-step decision-making in high-stakes domains such as education, healthcare, and finance. However, existing benchmarks typically assume perfectly accurate tool outputs, overlooking the reality that deployed systems must operate with noisy tools and human decision-makers whose trust in the agent is itself uncertain. Such conditions are common in practice, for example, a clinician using a diagnostic prediction tool or an advisor relying on a model that forecasts student outcomes from histori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02372","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/2608.02372/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":"2026-08-04T02:12:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YmHw3SY+OITdRUOzts78g6MRdKBe/b97IW8K9UZILhV2ao3IlFlpdLDOCp2/2P3vrWLawhMeN/9mUdN/Ed7xAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:19:52.071677Z"},"content_sha256":"eac14f808442b9422cd2959e9a8ca7e74c1ae04eb9dcf0d35c05c50f245aa1b7","schema_version":"1.0","event_id":"sha256:eac14f808442b9422cd2959e9a8ca7e74c1ae04eb9dcf0d35c05c50f245aa1b7"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:3UIXGXVTVYBPQIEK7NE2VLLZ7C","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/D18-1547) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Osman Ramadan, and Milica Gaši´c. MultiWOZ - a large-scale multi-domain Wizard-of-Oz dataset for task-oriented dialogue modelling. In Ellen Riloff, David C","arxiv_id":"2608.02372","detector":"doi_compliance","evidence":{"ref_index":4,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v","reconstructed_doi":"10.18653/v1/D18-1547"},"severity":"advisory","ref_index":4,"audited_at":"2026-08-04T08:38:11.628291Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/D18-1547","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"439b9447058688795d337192dbcb65fef9443955e7a94be86a82cccda1dbee52","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":17824,"payload_sha256":"3974290d7282b90d8645d90d7fa608750fd0f9a71de872ae00631290c55b40b6","signature_b64":"rlqxk/M1Te8ggbAvsABdtPhYrvTAovAnlHx2ieIjCNwv4ss5q9quoRedpgW9rODF30jvSy6MwdLWKGD4BmofAA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T08:38:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BX0ssdl7aXfTvrKESZqvFPGFLKRm+mRw5Set7XG8TgChTkJ8wMzTOspB3KcveKeewVk5WhZX+ZUc3iJXwgCVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:19:52.075680Z"},"content_sha256":"6ddaa9c1cb1d549fd8a4ab370766da1f63bab08a96fb2b6914f783fd4584e52e","schema_version":"1.0","event_id":"sha256:6ddaa9c1cb1d549fd8a4ab370766da1f63bab08a96fb2b6914f783fd4584e52e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3UIXGXVTVYBPQIEK7NE2VLLZ7C/bundle.json","state_url":"https://pith.science/pith/3UIXGXVTVYBPQIEK7NE2VLLZ7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3UIXGXVTVYBPQIEK7NE2VLLZ7C/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":"2026-08-07T07:19:52Z","links":{"resolver":"https://pith.science/pith/3UIXGXVTVYBPQIEK7NE2VLLZ7C","bundle":"https://pith.science/pith/3UIXGXVTVYBPQIEK7NE2VLLZ7C/bundle.json","state":"https://pith.science/pith/3UIXGXVTVYBPQIEK7NE2VLLZ7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3UIXGXVTVYBPQIEK7NE2VLLZ7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3UIXGXVTVYBPQIEK7NE2VLLZ7C","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2b83c55c75618228aa7701038d8f78df4301cb8d9e9e44c77017e8f9ff01ad1a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T15:15:55Z","title_canon_sha256":"98301a209b3d4520de0fcf5ba2aaf1387987a0ff9101915979b360cc5304d686"},"schema_version":"1.0","source":{"id":"2608.02372","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02372","created_at":"2026-08-04T02:12:05Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02372v1","created_at":"2026-08-04T02:12:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02372","created_at":"2026-08-04T02:12:05Z"},{"alias_kind":"pith_short_12","alias_value":"3UIXGXVTVYBP","created_at":"2026-08-04T02:12:05Z"},{"alias_kind":"pith_short_16","alias_value":"3UIXGXVTVYBPQIEK","created_at":"2026-08-04T02:12:05Z"},{"alias_kind":"pith_short_8","alias_value":"3UIXGXVT","created_at":"2026-08-04T02:12:05Z"}],"graph_snapshots":[{"event_id":"sha256:eac14f808442b9422cd2959e9a8ca7e74c1ae04eb9dcf0d35c05c50f245aa1b7","target":"graph","created_at":"2026-08-04T02:12:05Z","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/2608.02372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are increasingly deployed in task-oriented dialogue systems that support multi-step decision-making in high-stakes domains such as education, healthcare, and finance. However, existing benchmarks typically assume perfectly accurate tool outputs, overlooking the reality that deployed systems must operate with noisy tools and human decision-makers whose trust in the agent is itself uncertain. Such conditions are common in practice, for example, a clinician using a diagnostic prediction tool or an advisor relying on a model that forecasts student outcomes from histori","authors_text":"Abdulrahman AlRabah, Abdussalam Alawini, Dilek Hakkani-T\\\"ur, Xiaocheng Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T15:15:55Z","title":"PredAct-Bench: Benchmarking Tool-Augmented Dialogue under Controlled Tool Noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02372","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":"sha256:5cb7ef2239a184087804f86083ff06f040d97770394b4552a0f0aecad12438c9","target":"record","created_at":"2026-08-04T02:12:05Z","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":"2b83c55c75618228aa7701038d8f78df4301cb8d9e9e44c77017e8f9ff01ad1a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T15:15:55Z","title_canon_sha256":"98301a209b3d4520de0fcf5ba2aaf1387987a0ff9101915979b360cc5304d686"},"schema_version":"1.0","source":{"id":"2608.02372","kind":"arxiv","version":1}},"canonical_sha256":"dd11735eb3ae02f8208afb49aaad79f8a74b300ec5c28031830c5a8f9a862187","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd11735eb3ae02f8208afb49aaad79f8a74b300ec5c28031830c5a8f9a862187","first_computed_at":"2026-08-04T02:12:05.408170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:12:05.408170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zlm6zdPnETafp3ekS5ea2mp0X/f7YHtMtqr97+s4hENQqcIib7pRotQrKM+EpIUmsR9RZeHPPlvoj2HhiHv9BA==","signature_status":"signed_v1","signed_at":"2026-08-04T02:12:05.409943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02372","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cb7ef2239a184087804f86083ff06f040d97770394b4552a0f0aecad12438c9","sha256:eac14f808442b9422cd2959e9a8ca7e74c1ae04eb9dcf0d35c05c50f245aa1b7","sha256:6ddaa9c1cb1d549fd8a4ab370766da1f63bab08a96fb2b6914f783fd4584e52e"],"state_sha256":"f21b9a5a8a456b7a77834db8c8c53dd552469cd3d68d8c21c4399290087eaa11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iK7tqXj9UryfZEPGRnhirpKg1Mb/s1LL+8o4YQjN7VuZZwxKHf6WZ3Ro7+shtClKkk9u24KzpZs/25PnyNdCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:19:52.078156Z","bundle_sha256":"fd071a7d01473f15a0a3f64134254fffa045827d911cffb3185406503f9818dd"}}