{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CGHVNVONO37BMEJ33CUD27N4WT","short_pith_number":"pith:CGHVNVON","canonical_record":{"source":{"id":"2005.00129","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T22:34:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f53e151267ff77e8bac63faeee9884b1dd893ab0c4b601d4c79317c7612ebe13","abstract_canon_sha256":"b2358de0c3e46f49b23deff859d8b218e5853ae0c3cd0511cad71d2e8dfff9be"},"schema_version":"1.0"},"canonical_sha256":"118f56d5cd76fe16113bd8a83d7dbcb4e692bc405e79b8f9c40a906a106253f1","source":{"kind":"arxiv","id":"2005.00129","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00129","created_at":"2026-07-05T02:00:21Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00129v2","created_at":"2026-07-05T02:00:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00129","created_at":"2026-07-05T02:00:21Z"},{"alias_kind":"pith_short_12","alias_value":"CGHVNVONO37B","created_at":"2026-07-05T02:00:21Z"},{"alias_kind":"pith_short_16","alias_value":"CGHVNVONO37BMEJ3","created_at":"2026-07-05T02:00:21Z"},{"alias_kind":"pith_short_8","alias_value":"CGHVNVON","created_at":"2026-07-05T02:00:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CGHVNVONO37BMEJ33CUD27N4WT","target":"record","payload":{"canonical_record":{"source":{"id":"2005.00129","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T22:34:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f53e151267ff77e8bac63faeee9884b1dd893ab0c4b601d4c79317c7612ebe13","abstract_canon_sha256":"b2358de0c3e46f49b23deff859d8b218e5853ae0c3cd0511cad71d2e8dfff9be"},"schema_version":"1.0"},"canonical_sha256":"118f56d5cd76fe16113bd8a83d7dbcb4e692bc405e79b8f9c40a906a106253f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:21.935623Z","signature_b64":"VJre8fyv5T56Zo6sZO+r6yAiSS/8iE16N9arfRX9QjLU+3HlJXXKa0l8j+k1fT4cw2LcYAMc62kfbjond7+iDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"118f56d5cd76fe16113bd8a83d7dbcb4e692bc405e79b8f9c40a906a106253f1","last_reissued_at":"2026-07-05T02:00:21.935203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:21.935203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.00129","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:00:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+C2ki76gZ42IQXbW48Si0PqzNf3+LFuYTpon7as8tXOLWq50SRJB2DW+OARCf6Zf99n/Tv5h9XPTi2Yq/DTLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:23:37.643313Z"},"content_sha256":"f6511f8e57acdaf70be2bd5a72908e4ba88694de2cc5d906843d38ab953b06fe","schema_version":"1.0","event_id":"sha256:f6511f8e57acdaf70be2bd5a72908e4ba88694de2cc5d906843d38ab953b06fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CGHVNVONO37BMEJ33CUD27N4WT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structure-Tags Improve Text Classification for Scholarly Document Quality Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Edwin A. Valentijn, Eleri Aedmaa, Gideon Maillette de Buy Wenniger, Herbert Teun Kruitbosch, Lambert Schomaker, Thomas van Dongen","submitted_at":"2020-04-30T22:34:34Z","abstract_excerpt":"Training recurrent neural networks on long texts, in particular scholarly documents, causes problems for learning. While hierarchical attention networks (HANs) are effective in solving these problems, they still lose important information about the structure of the text. To tackle these problems, we propose the use of HANs combined with structure-tags which mark the role of sentences in the document. Adding tags to sentences, marking them as corresponding to title, abstract or main body text, yields improvements over the state-of-the-art for scholarly document quality prediction. The proposed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00129","kind":"arxiv","version":2},"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/2005.00129/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":"2026-07-05T02:00:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oXO3my/nhhvtY0E7JAQVvQG/LfW/fzgSz4zhgLfh88PX/9fhdnRFOcnIAExregPXlUVv9gdO4PDM2OK5kDluDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:23:37.643714Z"},"content_sha256":"f3c329b057deeef9622acb10f2998158507b4957453005bfda9779327c9deba7","schema_version":"1.0","event_id":"sha256:f3c329b057deeef9622acb10f2998158507b4957453005bfda9779327c9deba7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CGHVNVONO37BMEJ33CUD27N4WT/bundle.json","state_url":"https://pith.science/pith/CGHVNVONO37BMEJ33CUD27N4WT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CGHVNVONO37BMEJ33CUD27N4WT/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":"2026-07-07T07:23:37Z","links":{"resolver":"https://pith.science/pith/CGHVNVONO37BMEJ33CUD27N4WT","bundle":"https://pith.science/pith/CGHVNVONO37BMEJ33CUD27N4WT/bundle.json","state":"https://pith.science/pith/CGHVNVONO37BMEJ33CUD27N4WT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CGHVNVONO37BMEJ33CUD27N4WT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CGHVNVONO37BMEJ33CUD27N4WT","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":"b2358de0c3e46f49b23deff859d8b218e5853ae0c3cd0511cad71d2e8dfff9be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T22:34:34Z","title_canon_sha256":"f53e151267ff77e8bac63faeee9884b1dd893ab0c4b601d4c79317c7612ebe13"},"schema_version":"1.0","source":{"id":"2005.00129","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00129","created_at":"2026-07-05T02:00:21Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00129v2","created_at":"2026-07-05T02:00:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00129","created_at":"2026-07-05T02:00:21Z"},{"alias_kind":"pith_short_12","alias_value":"CGHVNVONO37B","created_at":"2026-07-05T02:00:21Z"},{"alias_kind":"pith_short_16","alias_value":"CGHVNVONO37BMEJ3","created_at":"2026-07-05T02:00:21Z"},{"alias_kind":"pith_short_8","alias_value":"CGHVNVON","created_at":"2026-07-05T02:00:21Z"}],"graph_snapshots":[{"event_id":"sha256:f3c329b057deeef9622acb10f2998158507b4957453005bfda9779327c9deba7","target":"graph","created_at":"2026-07-05T02:00:21Z","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/2005.00129/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training recurrent neural networks on long texts, in particular scholarly documents, causes problems for learning. While hierarchical attention networks (HANs) are effective in solving these problems, they still lose important information about the structure of the text. To tackle these problems, we propose the use of HANs combined with structure-tags which mark the role of sentences in the document. Adding tags to sentences, marking them as corresponding to title, abstract or main body text, yields improvements over the state-of-the-art for scholarly document quality prediction. The proposed ","authors_text":"Edwin A. Valentijn, Eleri Aedmaa, Gideon Maillette de Buy Wenniger, Herbert Teun Kruitbosch, Lambert Schomaker, Thomas van Dongen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T22:34:34Z","title":"Structure-Tags Improve Text Classification for Scholarly Document Quality Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00129","kind":"arxiv","version":2},"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:f6511f8e57acdaf70be2bd5a72908e4ba88694de2cc5d906843d38ab953b06fe","target":"record","created_at":"2026-07-05T02:00:21Z","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":"b2358de0c3e46f49b23deff859d8b218e5853ae0c3cd0511cad71d2e8dfff9be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T22:34:34Z","title_canon_sha256":"f53e151267ff77e8bac63faeee9884b1dd893ab0c4b601d4c79317c7612ebe13"},"schema_version":"1.0","source":{"id":"2005.00129","kind":"arxiv","version":2}},"canonical_sha256":"118f56d5cd76fe16113bd8a83d7dbcb4e692bc405e79b8f9c40a906a106253f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"118f56d5cd76fe16113bd8a83d7dbcb4e692bc405e79b8f9c40a906a106253f1","first_computed_at":"2026-07-05T02:00:21.935203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:00:21.935203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VJre8fyv5T56Zo6sZO+r6yAiSS/8iE16N9arfRX9QjLU+3HlJXXKa0l8j+k1fT4cw2LcYAMc62kfbjond7+iDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:00:21.935623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00129","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6511f8e57acdaf70be2bd5a72908e4ba88694de2cc5d906843d38ab953b06fe","sha256:f3c329b057deeef9622acb10f2998158507b4957453005bfda9779327c9deba7"],"state_sha256":"21f0ce5dee65ada9159e15b1219055ab2251e9701b03686d93cb9134c657d494"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z4zgO6Idyt5vvQ1N+9OvkDEB5Eb41NFTO8KHaryqU3WDJV7XmVDkbpmhWvtIz/+6gZ/OutTtcoP8xcoG9hfUCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:23:37.646748Z","bundle_sha256":"d346263d7da084db6ef59d245fd307c96bceb652a6dcfe212f5c0dcea1095dc1"}}