{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:42RLSRF535L3WF2ZKZGVLROH4T","short_pith_number":"pith:42RLSRF5","canonical_record":{"source":{"id":"2304.08352","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T15:14:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0317f643e76cafaef3507dd0f35ac8eb816027617a2c3342754c0cbf2970c8c1","abstract_canon_sha256":"e8c7c3ccf426b2f8fd264bf11210df6fed1cd574864bc818073fd47b0e8cbb9d"},"schema_version":"1.0"},"canonical_sha256":"e6a2b944bddf57bb1759564d55c5c7e4ebd8af883c6fb4fb49d4f00a6d4a9839","source":{"kind":"arxiv","id":"2304.08352","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08352","created_at":"2026-07-05T06:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08352v1","created_at":"2026-07-05T06:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08352","created_at":"2026-07-05T06:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"42RLSRF535L3","created_at":"2026-07-05T06:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"42RLSRF535L3WF2Z","created_at":"2026-07-05T06:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"42RLSRF5","created_at":"2026-07-05T06:01:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:42RLSRF535L3WF2ZKZGVLROH4T","target":"record","payload":{"canonical_record":{"source":{"id":"2304.08352","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T15:14:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0317f643e76cafaef3507dd0f35ac8eb816027617a2c3342754c0cbf2970c8c1","abstract_canon_sha256":"e8c7c3ccf426b2f8fd264bf11210df6fed1cd574864bc818073fd47b0e8cbb9d"},"schema_version":"1.0"},"canonical_sha256":"e6a2b944bddf57bb1759564d55c5c7e4ebd8af883c6fb4fb49d4f00a6d4a9839","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:42.234974Z","signature_b64":"xaf5NQb6ctAJT6t/cwydptNJlI5glSD1BoFfKvS0M3kytkITGtBltKfpp0pkH4SLvHi9ZnYm86FpjbtV1/23Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6a2b944bddf57bb1759564d55c5c7e4ebd8af883c6fb4fb49d4f00a6d4a9839","last_reissued_at":"2026-07-05T06:01:42.234581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:42.234581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.08352","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":"2026-07-05T06:01:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VqoqoO48lszv0hnw2HNpZzwINcUn8DbxwSbHM7/dgxAnYWLpc9UgHS9LkP9vglfrg6hd2fZPBq+mxJBa3SvxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T20:54:36.286235Z"},"content_sha256":"03d3d5433d437853fe847b20aae6bc67ee7e324caaa28c66bfa106175bf2e29d","schema_version":"1.0","event_id":"sha256:03d3d5433d437853fe847b20aae6bc67ee7e324caaa28c66bfa106175bf2e29d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:42RLSRF535L3WF2ZKZGVLROH4T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Makes a Good Dataset for Symbol Description Reading?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bradley Eck, Joern Ploennigs, Karol Lynch","submitted_at":"2023-04-17T15:14:27Z","abstract_excerpt":"The usage of mathematical formulas as concise representations of a document's key ideas is common practice. Correctly interpreting these formulas, by identifying mathematical symbols and extracting their descriptions, is an important task in document understanding. This paper makes the following contributions to the mathematical identifier description reading (MIDR) task:\n  (i) introduces the Math Formula Question Answering Dataset (MFQuAD) with $7508$ annotated identifier occurrences;\n  (ii) describes novel variations of the noun phrase ranking approach for the MIDR task;\n  (iii) reports expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08352","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/2304.08352/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":"2026-07-05T06:01:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WlDpmaWD84PPR3mWKipeR3MPdBEbZumVskng2B/7f/2OBGH14h7E2N2HmXxx5legVZ/eMgzFeRuYf0leDHo+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T20:54:36.286829Z"},"content_sha256":"4df9ba7f6455a391eb22cf16561a7769a4983ab7fffe8d0c0405aebb426093f7","schema_version":"1.0","event_id":"sha256:4df9ba7f6455a391eb22cf16561a7769a4983ab7fffe8d0c0405aebb426093f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T/bundle.json","state_url":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/42RLSRF535L3WF2ZKZGVLROH4T/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":"2026-07-10T20:54:36Z","links":{"resolver":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T","bundle":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T/bundle.json","state":"https://pith.science/pith/42RLSRF535L3WF2ZKZGVLROH4T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/42RLSRF535L3WF2ZKZGVLROH4T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:42RLSRF535L3WF2ZKZGVLROH4T","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":"e8c7c3ccf426b2f8fd264bf11210df6fed1cd574864bc818073fd47b0e8cbb9d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T15:14:27Z","title_canon_sha256":"0317f643e76cafaef3507dd0f35ac8eb816027617a2c3342754c0cbf2970c8c1"},"schema_version":"1.0","source":{"id":"2304.08352","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08352","created_at":"2026-07-05T06:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08352v1","created_at":"2026-07-05T06:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08352","created_at":"2026-07-05T06:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"42RLSRF535L3","created_at":"2026-07-05T06:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"42RLSRF535L3WF2Z","created_at":"2026-07-05T06:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"42RLSRF5","created_at":"2026-07-05T06:01:42Z"}],"graph_snapshots":[{"event_id":"sha256:4df9ba7f6455a391eb22cf16561a7769a4983ab7fffe8d0c0405aebb426093f7","target":"graph","created_at":"2026-07-05T06:01:42Z","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/2304.08352/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The usage of mathematical formulas as concise representations of a document's key ideas is common practice. Correctly interpreting these formulas, by identifying mathematical symbols and extracting their descriptions, is an important task in document understanding. This paper makes the following contributions to the mathematical identifier description reading (MIDR) task:\n  (i) introduces the Math Formula Question Answering Dataset (MFQuAD) with $7508$ annotated identifier occurrences;\n  (ii) describes novel variations of the noun phrase ranking approach for the MIDR task;\n  (iii) reports expe","authors_text":"Bradley Eck, Joern Ploennigs, Karol Lynch","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T15:14:27Z","title":"What Makes a Good Dataset for Symbol Description Reading?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08352","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":"sha256:03d3d5433d437853fe847b20aae6bc67ee7e324caaa28c66bfa106175bf2e29d","target":"record","created_at":"2026-07-05T06:01:42Z","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":"e8c7c3ccf426b2f8fd264bf11210df6fed1cd574864bc818073fd47b0e8cbb9d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T15:14:27Z","title_canon_sha256":"0317f643e76cafaef3507dd0f35ac8eb816027617a2c3342754c0cbf2970c8c1"},"schema_version":"1.0","source":{"id":"2304.08352","kind":"arxiv","version":1}},"canonical_sha256":"e6a2b944bddf57bb1759564d55c5c7e4ebd8af883c6fb4fb49d4f00a6d4a9839","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6a2b944bddf57bb1759564d55c5c7e4ebd8af883c6fb4fb49d4f00a6d4a9839","first_computed_at":"2026-07-05T06:01:42.234581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:01:42.234581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xaf5NQb6ctAJT6t/cwydptNJlI5glSD1BoFfKvS0M3kytkITGtBltKfpp0pkH4SLvHi9ZnYm86FpjbtV1/23Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:01:42.234974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.08352","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03d3d5433d437853fe847b20aae6bc67ee7e324caaa28c66bfa106175bf2e29d","sha256:4df9ba7f6455a391eb22cf16561a7769a4983ab7fffe8d0c0405aebb426093f7"],"state_sha256":"959dad2432fafeb7fef48905a012577f53ef91922cbae82199757f64b001cbbb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iVXH8ah7Sr24Lbp3Fpi/b3wd3B1ma0ZAbXnqT7Z0HRqdx6j7bjA8UHPRXn4mw0Kp6c1lsbdYr53DF/Q6Y7ZhDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T20:54:36.289540Z","bundle_sha256":"3513652aed40c41533f345542bf05026793820bbebbcdeb758722b885b239818"}}