{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FVRYKACTRLSXFBJVVNH6G6XUGM","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":"2259381b4e5fab93695407451dff726f088ff04282d5f8dc0f562710e3e8c9e0","cross_cats_sorted":["cs.CL","cs.DL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-09-19T17:18:36Z","title_canon_sha256":"1a167222a413c0293cd014d24177c8bd2835c627ddff1d75aadd482825822865"},"schema_version":"1.0","source":{"id":"2309.10772","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10772","created_at":"2026-07-05T06:52:16Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10772v1","created_at":"2026-07-05T06:52:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10772","created_at":"2026-07-05T06:52:16Z"},{"alias_kind":"pith_short_12","alias_value":"FVRYKACTRLSX","created_at":"2026-07-05T06:52:16Z"},{"alias_kind":"pith_short_16","alias_value":"FVRYKACTRLSXFBJV","created_at":"2026-07-05T06:52:16Z"},{"alias_kind":"pith_short_8","alias_value":"FVRYKACT","created_at":"2026-07-05T06:52:16Z"}],"graph_snapshots":[{"event_id":"sha256:789bca54ecc0df5dd9b5cf00f7cde784de09f923e79ac34f217243e83821c360","target":"graph","created_at":"2026-07-05T06:52:16Z","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/2309.10772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Highly specific datasets of scientific literature are important for both research and education. However, it is difficult to build such datasets at scale. A common approach is to build these datasets reductively by applying topic modeling on an established corpus and selecting specific topics. A more robust but time-consuming approach is to build the dataset constructively in which a subject matter expert (SME) handpicks documents. This method does not scale and is prone to error as the dataset grows. Here we showcase a new tool, based on machine learning, for constructively generating targete","authors_text":"Boian S. Alexandrov, Kim O. Rasmussen, Maksim E. Eren, Manish Bhattarai, Nicholas Solovyev, Ryan Barron","cross_cats":["cs.CL","cs.DL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-09-19T17:18:36Z","title":"Interactive Distillation of Large Single-Topic Corpora of Scientific Papers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10772","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":"sha256:0d39921fa6a229389bc27da6d249a14df3765d300f084eb79d57336c09c232f1","target":"record","created_at":"2026-07-05T06:52:16Z","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":"2259381b4e5fab93695407451dff726f088ff04282d5f8dc0f562710e3e8c9e0","cross_cats_sorted":["cs.CL","cs.DL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-09-19T17:18:36Z","title_canon_sha256":"1a167222a413c0293cd014d24177c8bd2835c627ddff1d75aadd482825822865"},"schema_version":"1.0","source":{"id":"2309.10772","kind":"arxiv","version":1}},"canonical_sha256":"2d638500538ae5728535ab4fe37af4332f66138f0510032605dd4cc89b4f9b13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d638500538ae5728535ab4fe37af4332f66138f0510032605dd4cc89b4f9b13","first_computed_at":"2026-07-05T06:52:16.945289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:16.945289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/4yfWCzyKzPHbVa5Ony6WYiNwwwdohgkncq9QkfXeYjKg3fo/g1iTxyyz1NlOAPCMeCzH5tFYuiDQYFKqtQZBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:16.945922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10772","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d39921fa6a229389bc27da6d249a14df3765d300f084eb79d57336c09c232f1","sha256:789bca54ecc0df5dd9b5cf00f7cde784de09f923e79ac34f217243e83821c360"],"state_sha256":"160ac0eabda93bfb8def0b38f00e9bd7de2bca62723e6280315b2eb761f51c4d"}