{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JSFRPO35HWYPEMSMYSIQ2RAWVP","short_pith_number":"pith:JSFRPO35","canonical_record":{"source":{"id":"2012.07565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-09T22:45:40Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"e6de7504c865b290eebff19d2d0d4d933a2f28163615c2cc70d425a310e3a1b3","abstract_canon_sha256":"28d24cf3f1f1ad27a9a739c3f63a7fe455c80dd8d7050ea9cc8a68d21fb57a11"},"schema_version":"1.0"},"canonical_sha256":"4c8b17bb7d3db0f2324cc4910d4416abd414de8739067f27a23a6b605a6ec6b5","source":{"kind":"arxiv","id":"2012.07565","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.07565","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"arxiv_version","alias_value":"2012.07565v1","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07565","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"pith_short_12","alias_value":"JSFRPO35HWYP","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"pith_short_16","alias_value":"JSFRPO35HWYPEMSM","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"pith_short_8","alias_value":"JSFRPO35","created_at":"2026-07-05T01:59:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JSFRPO35HWYPEMSMYSIQ2RAWVP","target":"record","payload":{"canonical_record":{"source":{"id":"2012.07565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-09T22:45:40Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"e6de7504c865b290eebff19d2d0d4d933a2f28163615c2cc70d425a310e3a1b3","abstract_canon_sha256":"28d24cf3f1f1ad27a9a739c3f63a7fe455c80dd8d7050ea9cc8a68d21fb57a11"},"schema_version":"1.0"},"canonical_sha256":"4c8b17bb7d3db0f2324cc4910d4416abd414de8739067f27a23a6b605a6ec6b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:22.010232Z","signature_b64":"Xe5ARmWw6aC0zxiC89z5ojmDZ1KMP/SGR/b6QUy8CGjUB4csmgiTJe20f3hBbAbzNM2PFrlJ4sIikP8BURcUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c8b17bb7d3db0f2324cc4910d4416abd414de8739067f27a23a6b605a6ec6b5","last_reissued_at":"2026-07-05T01:59:22.009843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:22.009843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.07565","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":"2026-07-05T01:59:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N5GPHKpOVFLFxZgtMh2O6wLigM60/OS3JcwRNdWSvF0m+xgf4ZQsIq/Uu0FZTaSHCz4GnGxPC6NrBcOL9TDUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:02:12.558463Z"},"content_sha256":"836fc40873821565a95117d3166179ac13f0ef2f08b41404ba5136291cfebe73","schema_version":"1.0","event_id":"sha256:836fc40873821565a95117d3166179ac13f0ef2f08b41404ba5136291cfebe73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JSFRPO35HWYPEMSMYSIQ2RAWVP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automating Document Classification with Distant Supervision to Increase the Efficiency of Systematic Reviews","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amy Zhang, C. Lee Giles, Le Bao, Rabah Al-Zaidy, Stefan Baral, Xiaoxiao Li","submitted_at":"2020-12-09T22:45:40Z","abstract_excerpt":"Objective: Systematic reviews of scholarly documents often provide complete and exhaustive summaries of literature relevant to a research question. However, well-done systematic reviews are expensive, time-demanding, and labor-intensive. Here, we propose an automatic document classification approach to significantly reduce the effort in reviewing documents. Methods: We first describe a manual document classification procedure that is used to curate a pertinent training dataset and then propose three classifiers: a keyword-guided method, a cluster analysis-based refined method, and a random for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07565","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/2012.07565/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":"2026-07-05T01:59:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gBRE438SLgXQtcYDH6kf7lbMuNEa/iFiWLPyRYycd4Jx9iWvCow/fuL52QBw+PRIgenp7tDY17JVLX+sZL5DDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:02:12.559435Z"},"content_sha256":"d15c46d41622559b1d248b6ce4037d77a4213c48d49105d9bd06119c59e01385","schema_version":"1.0","event_id":"sha256:d15c46d41622559b1d248b6ce4037d77a4213c48d49105d9bd06119c59e01385"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP/bundle.json","state_url":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP/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":"2026-08-06T18:02:12Z","links":{"resolver":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP","bundle":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP/bundle.json","state":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JSFRPO35HWYPEMSMYSIQ2RAWVP","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":"28d24cf3f1f1ad27a9a739c3f63a7fe455c80dd8d7050ea9cc8a68d21fb57a11","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-09T22:45:40Z","title_canon_sha256":"e6de7504c865b290eebff19d2d0d4d933a2f28163615c2cc70d425a310e3a1b3"},"schema_version":"1.0","source":{"id":"2012.07565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.07565","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"arxiv_version","alias_value":"2012.07565v1","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07565","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"pith_short_12","alias_value":"JSFRPO35HWYP","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"pith_short_16","alias_value":"JSFRPO35HWYPEMSM","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"pith_short_8","alias_value":"JSFRPO35","created_at":"2026-07-05T01:59:22Z"}],"graph_snapshots":[{"event_id":"sha256:d15c46d41622559b1d248b6ce4037d77a4213c48d49105d9bd06119c59e01385","target":"graph","created_at":"2026-07-05T01:59:22Z","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/2012.07565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Objective: Systematic reviews of scholarly documents often provide complete and exhaustive summaries of literature relevant to a research question. However, well-done systematic reviews are expensive, time-demanding, and labor-intensive. Here, we propose an automatic document classification approach to significantly reduce the effort in reviewing documents. Methods: We first describe a manual document classification procedure that is used to curate a pertinent training dataset and then propose three classifiers: a keyword-guided method, a cluster analysis-based refined method, and a random for","authors_text":"Amy Zhang, C. Lee Giles, Le Bao, Rabah Al-Zaidy, Stefan Baral, Xiaoxiao Li","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-09T22:45:40Z","title":"Automating Document Classification with Distant Supervision to Increase the Efficiency of Systematic Reviews"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07565","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":"sha256:836fc40873821565a95117d3166179ac13f0ef2f08b41404ba5136291cfebe73","target":"record","created_at":"2026-07-05T01:59:22Z","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":"28d24cf3f1f1ad27a9a739c3f63a7fe455c80dd8d7050ea9cc8a68d21fb57a11","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-09T22:45:40Z","title_canon_sha256":"e6de7504c865b290eebff19d2d0d4d933a2f28163615c2cc70d425a310e3a1b3"},"schema_version":"1.0","source":{"id":"2012.07565","kind":"arxiv","version":1}},"canonical_sha256":"4c8b17bb7d3db0f2324cc4910d4416abd414de8739067f27a23a6b605a6ec6b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c8b17bb7d3db0f2324cc4910d4416abd414de8739067f27a23a6b605a6ec6b5","first_computed_at":"2026-07-05T01:59:22.009843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:22.009843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xe5ARmWw6aC0zxiC89z5ojmDZ1KMP/SGR/b6QUy8CGjUB4csmgiTJe20f3hBbAbzNM2PFrlJ4sIikP8BURcUCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:22.010232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.07565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:836fc40873821565a95117d3166179ac13f0ef2f08b41404ba5136291cfebe73","sha256:d15c46d41622559b1d248b6ce4037d77a4213c48d49105d9bd06119c59e01385"],"state_sha256":"e1750e62e67704dfe67bb61e5b0fffbcfbb441ceac1d900d190ec0edc931c74c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZTLA+1Eyyb3Fp/1fU2TFJ+BCn2AaBmTrmMrCEu8UuYgaWLquRFBWcML6jmIqx9e9JpZL4ozd2PEIO5xz3lW3BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:02:12.569780Z","bundle_sha256":"c504e33c2724283074146b98e08e4f068bf3a401dcda6bdf3e12cd72eec7e593"}}