{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:NHOHDPSUOTLEHYJYR3EDKUSVBR","short_pith_number":"pith:NHOHDPSU","canonical_record":{"source":{"id":"1407.0167","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2014-07-01T09:56:42Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"ae42160438da32b4fc8c09db4bbef4b88b7f80daf872256aec3406a98563fe40","abstract_canon_sha256":"c894403385511b0ef986ba7d0354c6b7900d1e5b95b1aa633feb28736c77ffc4"},"schema_version":"1.0"},"canonical_sha256":"69dc71be5474d643e1388ec83552550c6c5df6b581de7dd1cd3798660211b81b","source":{"kind":"arxiv","id":"1407.0167","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.0167","created_at":"2026-05-17T23:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"1407.0167v1","created_at":"2026-05-17T23:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.0167","created_at":"2026-05-17T23:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"NHOHDPSUOTLE","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"NHOHDPSUOTLEHYJY","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"NHOHDPSU","created_at":"2026-05-18T12:28:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:NHOHDPSUOTLEHYJYR3EDKUSVBR","target":"record","payload":{"canonical_record":{"source":{"id":"1407.0167","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2014-07-01T09:56:42Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"ae42160438da32b4fc8c09db4bbef4b88b7f80daf872256aec3406a98563fe40","abstract_canon_sha256":"c894403385511b0ef986ba7d0354c6b7900d1e5b95b1aa633feb28736c77ffc4"},"schema_version":"1.0"},"canonical_sha256":"69dc71be5474d643e1388ec83552550c6c5df6b581de7dd1cd3798660211b81b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:57.043374Z","signature_b64":"cquwSTNtnvqQgTYYCEITYrfKKp4OvlNsvC6WShc9Ady8fccZTmviebbi9EfD7EXYsTWqwN/SWYlo5+CkD0hvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69dc71be5474d643e1388ec83552550c6c5df6b581de7dd1cd3798660211b81b","last_reissued_at":"2026-05-17T23:41:57.042693Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:57.042693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1407.0167","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":"2026-05-17T23:41:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xIJuN9gdmrXDgHnf57cDpwaEt0DvRJdALEV+cdzie/6KMEsNpHfhuKNEX0Jet66sX07+Dfo8qKph5MvJSSqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T05:14:30.375025Z"},"content_sha256":"6fde8ffd25b1e63369ab1614bf5a1e3a1abd5e2eeebb866c48b57fc232d0721e","schema_version":"1.0","event_id":"sha256:6fde8ffd25b1e63369ab1614bf5a1e3a1abd5e2eeebb866c48b57fc232d0721e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:NHOHDPSUOTLEHYJYR3EDKUSVBR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mathematical Language Processing Project","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.DL","authors_text":"Moritz Schubotz, Robert Pagael","submitted_at":"2014-07-01T09:56:42Z","abstract_excerpt":"In natural language, words and phrases themselves imply the semantics. In contrast, the meaning of identifiers in mathematical formulae is undefined. Thus scientists must study the context to decode the meaning. The Mathematical Language Processing (MLP) project aims to support that process. In this paper, we compare two approaches to discover identifier-definition tuples. At first we use a simple pattern matching approach. Second, we present the MLP approach that uses part-of-speech tag based distances as well as sentence positions to calculate identifier-definition probabilities. The evaluat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.0167","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":""},"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":"2026-05-17T23:41:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v3d/KXxwkofphR5E9jWhTTEqruIwqmtlBnKtIwcagBMGM5XYTbGped19LI3TGrDA/ys7WW0Icp0Vvc/jOWMlDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T05:14:30.375394Z"},"content_sha256":"d558a0c5f1de3a2b118f64382179d084dddde46bb09b24b701b3645600f788c2","schema_version":"1.0","event_id":"sha256:d558a0c5f1de3a2b118f64382179d084dddde46bb09b24b701b3645600f788c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NHOHDPSUOTLEHYJYR3EDKUSVBR/bundle.json","state_url":"https://pith.science/pith/NHOHDPSUOTLEHYJYR3EDKUSVBR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NHOHDPSUOTLEHYJYR3EDKUSVBR/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":"2026-06-04T05:14:30Z","links":{"resolver":"https://pith.science/pith/NHOHDPSUOTLEHYJYR3EDKUSVBR","bundle":"https://pith.science/pith/NHOHDPSUOTLEHYJYR3EDKUSVBR/bundle.json","state":"https://pith.science/pith/NHOHDPSUOTLEHYJYR3EDKUSVBR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NHOHDPSUOTLEHYJYR3EDKUSVBR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:NHOHDPSUOTLEHYJYR3EDKUSVBR","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":"c894403385511b0ef986ba7d0354c6b7900d1e5b95b1aa633feb28736c77ffc4","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2014-07-01T09:56:42Z","title_canon_sha256":"ae42160438da32b4fc8c09db4bbef4b88b7f80daf872256aec3406a98563fe40"},"schema_version":"1.0","source":{"id":"1407.0167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.0167","created_at":"2026-05-17T23:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"1407.0167v1","created_at":"2026-05-17T23:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.0167","created_at":"2026-05-17T23:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"NHOHDPSUOTLE","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"NHOHDPSUOTLEHYJY","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"NHOHDPSU","created_at":"2026-05-18T12:28:41Z"}],"graph_snapshots":[{"event_id":"sha256:d558a0c5f1de3a2b118f64382179d084dddde46bb09b24b701b3645600f788c2","target":"graph","created_at":"2026-05-17T23:41:57Z","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"},"paper":{"abstract_excerpt":"In natural language, words and phrases themselves imply the semantics. In contrast, the meaning of identifiers in mathematical formulae is undefined. Thus scientists must study the context to decode the meaning. The Mathematical Language Processing (MLP) project aims to support that process. In this paper, we compare two approaches to discover identifier-definition tuples. At first we use a simple pattern matching approach. Second, we present the MLP approach that uses part-of-speech tag based distances as well as sentence positions to calculate identifier-definition probabilities. The evaluat","authors_text":"Moritz Schubotz, Robert Pagael","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2014-07-01T09:56:42Z","title":"Mathematical Language Processing Project"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.0167","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":"sha256:6fde8ffd25b1e63369ab1614bf5a1e3a1abd5e2eeebb866c48b57fc232d0721e","target":"record","created_at":"2026-05-17T23:41:57Z","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":"c894403385511b0ef986ba7d0354c6b7900d1e5b95b1aa633feb28736c77ffc4","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2014-07-01T09:56:42Z","title_canon_sha256":"ae42160438da32b4fc8c09db4bbef4b88b7f80daf872256aec3406a98563fe40"},"schema_version":"1.0","source":{"id":"1407.0167","kind":"arxiv","version":1}},"canonical_sha256":"69dc71be5474d643e1388ec83552550c6c5df6b581de7dd1cd3798660211b81b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69dc71be5474d643e1388ec83552550c6c5df6b581de7dd1cd3798660211b81b","first_computed_at":"2026-05-17T23:41:57.042693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:57.042693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cquwSTNtnvqQgTYYCEITYrfKKp4OvlNsvC6WShc9Ady8fccZTmviebbi9EfD7EXYsTWqwN/SWYlo5+CkD0hvAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:57.043374Z","signed_message":"canonical_sha256_bytes"},"source_id":"1407.0167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fde8ffd25b1e63369ab1614bf5a1e3a1abd5e2eeebb866c48b57fc232d0721e","sha256:d558a0c5f1de3a2b118f64382179d084dddde46bb09b24b701b3645600f788c2"],"state_sha256":"c001c73014954e9f50e7c812336072ac29bd0fc83bd6403caf9e6068df22fc57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ihvaQ+GdzwQlFNOXd4lFYoNXpXfDEV1IgMsWwdJ1Kqthl5qFPp1BEEkwqSP07wJVnyvhyOwkw95axwtsaE4TAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T05:14:30.377438Z","bundle_sha256":"3d1618de888dd3b3efab5f106b990a8d55715089c852bcc1f92ba54668699353"}}