{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MEDZI7HQ75OYPGFDRAES42JFT4","short_pith_number":"pith:MEDZI7HQ","canonical_record":{"source":{"id":"2204.12070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T04:36:14Z","cross_cats_sorted":[],"title_canon_sha256":"2a61c047930a87d083996577c069ffbe8f56879ba6da865d2ddec047825e40b2","abstract_canon_sha256":"34acb8d155c2ab338b804c52437d095b8a19ff0adef9e3609dac40496cf7ab8e"},"schema_version":"1.0"},"canonical_sha256":"6107947cf0ff5d8798a388092e69259f083d6a84e5b3f219479c91d29d22bea7","source":{"kind":"arxiv","id":"2204.12070","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12070","created_at":"2026-07-05T04:17:44Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12070v1","created_at":"2026-07-05T04:17:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12070","created_at":"2026-07-05T04:17:44Z"},{"alias_kind":"pith_short_12","alias_value":"MEDZI7HQ75OY","created_at":"2026-07-05T04:17:44Z"},{"alias_kind":"pith_short_16","alias_value":"MEDZI7HQ75OYPGFD","created_at":"2026-07-05T04:17:44Z"},{"alias_kind":"pith_short_8","alias_value":"MEDZI7HQ","created_at":"2026-07-05T04:17:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MEDZI7HQ75OYPGFDRAES42JFT4","target":"record","payload":{"canonical_record":{"source":{"id":"2204.12070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T04:36:14Z","cross_cats_sorted":[],"title_canon_sha256":"2a61c047930a87d083996577c069ffbe8f56879ba6da865d2ddec047825e40b2","abstract_canon_sha256":"34acb8d155c2ab338b804c52437d095b8a19ff0adef9e3609dac40496cf7ab8e"},"schema_version":"1.0"},"canonical_sha256":"6107947cf0ff5d8798a388092e69259f083d6a84e5b3f219479c91d29d22bea7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:44.135250Z","signature_b64":"HMO06JAzccuk4LrLZK+wutXduHlnLNhLboimAd18dQKJZ/oiUSH0ZzlOlvWrISz0d6g7pPVz1lqP3cb2dslhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6107947cf0ff5d8798a388092e69259f083d6a84e5b3f219479c91d29d22bea7","last_reissued_at":"2026-07-05T04:17:44.134708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:44.134708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.12070","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":"2026-07-05T04:17:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F8hXjcsMYnmvd5a8Xjhe0wlVeC49/+Mb17iKbIGWIAhdEyjkPX7yhbqF4U3jFVrrj24b2YWJ90iPAHE8QusFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:31:44.677911Z"},"content_sha256":"ef818faafa1edc9b88ec9c72b67a8f09d8828a8476fea5adb0e7aaa11eb06583","schema_version":"1.0","event_id":"sha256:ef818faafa1edc9b88ec9c72b67a8f09d8828a8476fea5adb0e7aaa11eb06583"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MEDZI7HQ75OYPGFDRAES42JFT4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Symlink: A New Dataset for Scientific Symbol-Description Linking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen, Viet Dac Lai","submitted_at":"2022-04-26T04:36:14Z","abstract_excerpt":"Mathematical symbols and descriptions appear in various forms across document section boundaries without explicit markup. In this paper, we present a new large-scale dataset that emphasizes extracting symbols and descriptions in scientific documents. Symlink annotates scientific papers of 5 different domains (i.e., computer science, biology, physics, mathematics, and economics). Our experiments on Symlink demonstrate the challenges of the symbol-description linking task for existing models and call for further research effort in this area. We will publicly release Symlink to facilitate future "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12070","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/2204.12070/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":"2026-07-05T04:17:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UmUqc8IZcsDR5DsL5dlRwJ9w+s7HG8b0TonNDZ4xjkDLR6olrLSe8NItF2Vf33pWpAu7IPtwQSqcXgmVu1tnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:31:44.678803Z"},"content_sha256":"753d543ddd3fb0358c04e840da10e3857b3935dcd08024bbecb8aff0faaf25b4","schema_version":"1.0","event_id":"sha256:753d543ddd3fb0358c04e840da10e3857b3935dcd08024bbecb8aff0faaf25b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4/bundle.json","state_url":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MEDZI7HQ75OYPGFDRAES42JFT4/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":"2026-08-05T23:31:44Z","links":{"resolver":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4","bundle":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4/bundle.json","state":"https://pith.science/pith/MEDZI7HQ75OYPGFDRAES42JFT4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MEDZI7HQ75OYPGFDRAES42JFT4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MEDZI7HQ75OYPGFDRAES42JFT4","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":"34acb8d155c2ab338b804c52437d095b8a19ff0adef9e3609dac40496cf7ab8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T04:36:14Z","title_canon_sha256":"2a61c047930a87d083996577c069ffbe8f56879ba6da865d2ddec047825e40b2"},"schema_version":"1.0","source":{"id":"2204.12070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12070","created_at":"2026-07-05T04:17:44Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12070v1","created_at":"2026-07-05T04:17:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12070","created_at":"2026-07-05T04:17:44Z"},{"alias_kind":"pith_short_12","alias_value":"MEDZI7HQ75OY","created_at":"2026-07-05T04:17:44Z"},{"alias_kind":"pith_short_16","alias_value":"MEDZI7HQ75OYPGFD","created_at":"2026-07-05T04:17:44Z"},{"alias_kind":"pith_short_8","alias_value":"MEDZI7HQ","created_at":"2026-07-05T04:17:44Z"}],"graph_snapshots":[{"event_id":"sha256:753d543ddd3fb0358c04e840da10e3857b3935dcd08024bbecb8aff0faaf25b4","target":"graph","created_at":"2026-07-05T04:17:44Z","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/2204.12070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mathematical symbols and descriptions appear in various forms across document section boundaries without explicit markup. In this paper, we present a new large-scale dataset that emphasizes extracting symbols and descriptions in scientific documents. Symlink annotates scientific papers of 5 different domains (i.e., computer science, biology, physics, mathematics, and economics). Our experiments on Symlink demonstrate the challenges of the symbol-description linking task for existing models and call for further research effort in this area. We will publicly release Symlink to facilitate future ","authors_text":"Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen, Viet Dac Lai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T04:36:14Z","title":"Symlink: A New Dataset for Scientific Symbol-Description Linking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12070","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:ef818faafa1edc9b88ec9c72b67a8f09d8828a8476fea5adb0e7aaa11eb06583","target":"record","created_at":"2026-07-05T04:17:44Z","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":"34acb8d155c2ab338b804c52437d095b8a19ff0adef9e3609dac40496cf7ab8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T04:36:14Z","title_canon_sha256":"2a61c047930a87d083996577c069ffbe8f56879ba6da865d2ddec047825e40b2"},"schema_version":"1.0","source":{"id":"2204.12070","kind":"arxiv","version":1}},"canonical_sha256":"6107947cf0ff5d8798a388092e69259f083d6a84e5b3f219479c91d29d22bea7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6107947cf0ff5d8798a388092e69259f083d6a84e5b3f219479c91d29d22bea7","first_computed_at":"2026-07-05T04:17:44.134708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:44.134708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HMO06JAzccuk4LrLZK+wutXduHlnLNhLboimAd18dQKJZ/oiUSH0ZzlOlvWrISz0d6g7pPVz1lqP3cb2dslhBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:44.135250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.12070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef818faafa1edc9b88ec9c72b67a8f09d8828a8476fea5adb0e7aaa11eb06583","sha256:753d543ddd3fb0358c04e840da10e3857b3935dcd08024bbecb8aff0faaf25b4"],"state_sha256":"b737214e3a73d9ce318f174e66296aee7fd8c4a143eaab2dd46f2f842e5c3445"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GTuoToK5Uhr1dMf7mpd+kpQVmeCRr+qqx1VEWEJzkzKwO3byC9Ba/0HL5b38es99JJl0y0hxk7NLZEFLbp26DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:31:44.683672Z","bundle_sha256":"4cc8b8d2ca7a2ef5714da978f665a77ffc9ef3fe32043d53956fd454b0a0b24e"}}