{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HGDFE7O6BHBV6NLLGHF4ITTUCR","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":"5016201c8a196c5b95f863573cd44afe74c73b686a69f00095ad282c2fcc98e9","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-05-28T13:31:08Z","title_canon_sha256":"27cdbd981b49dfa919f8a3f54ba6d20397af16c0ae2ce10a360870fe61864824"},"schema_version":"1.0","source":{"id":"2505.22349","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22349","created_at":"2026-07-05T11:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22349v1","created_at":"2026-07-05T11:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22349","created_at":"2026-07-05T11:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"HGDFE7O6BHBV","created_at":"2026-07-05T11:11:13Z"},{"alias_kind":"pith_short_16","alias_value":"HGDFE7O6BHBV6NLL","created_at":"2026-07-05T11:11:13Z"},{"alias_kind":"pith_short_8","alias_value":"HGDFE7O6","created_at":"2026-07-05T11:11:13Z"}],"graph_snapshots":[{"event_id":"sha256:0a73d9dc76f6a20a03160328caae8df1cc1b06e2d576294eb04725fd0ef0c6b3","target":"graph","created_at":"2026-07-05T11:11:13Z","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/2505.22349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scientific research heavily depends on suitable datasets for method validation, but existing academic platforms with dataset management like PapersWithCode suffer from inefficiencies in their manual workflow. To overcome this bottleneck, we present a system, called ChatPD, that utilizes Large Language Models (LLMs) to automate dataset information extraction from academic papers and construct a structured paper-dataset network. Our system consists of three key modules: \\textit{paper collection}, \\textit{dataset information extraction}, and \\textit{dataset entity resolution} to construct paper-d","authors_text":"Anjie Xu, Leye Wang, Ruiqing Ding","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-05-28T13:31:08Z","title":"ChatPD: An LLM-driven Paper-Dataset Networking System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22349","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:c23dd4aeafad4f1dbbf9ab689d5ae552aa03b8cec273e68b0adff15a81dda5d7","target":"record","created_at":"2026-07-05T11:11:13Z","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":"5016201c8a196c5b95f863573cd44afe74c73b686a69f00095ad282c2fcc98e9","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-05-28T13:31:08Z","title_canon_sha256":"27cdbd981b49dfa919f8a3f54ba6d20397af16c0ae2ce10a360870fe61864824"},"schema_version":"1.0","source":{"id":"2505.22349","kind":"arxiv","version":1}},"canonical_sha256":"3986527dde09c35f356b31cbc44e741462aa8d25046ad8033e531134ccad5cb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3986527dde09c35f356b31cbc44e741462aa8d25046ad8033e531134ccad5cb7","first_computed_at":"2026-07-05T11:11:13.699243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:13.699243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LboYVjvegBieIt1gt+TgBXWIr7X0lMbanogbhDQat1fxVJiSdk/FsbBXziiBuIVEMJ9PeloK0+mTqmxjToZ+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:13.699713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22349","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c23dd4aeafad4f1dbbf9ab689d5ae552aa03b8cec273e68b0adff15a81dda5d7","sha256:0a73d9dc76f6a20a03160328caae8df1cc1b06e2d576294eb04725fd0ef0c6b3"],"state_sha256":"e7906e4c5b980131e570fa9686926ad81ee741aad18b12b68e182cbfb4572f4d"}