{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:R42P24MUAUCXEHNM2NQRF2A7I4","short_pith_number":"pith:R42P24MU","canonical_record":{"source":{"id":"2501.14951","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T22:39:08Z","cross_cats_sorted":["cs.CL","cs.SC"],"title_canon_sha256":"f27d25b368ca3bd7234839d129f9dbddbc75cd300c6455f30dc3e6946e48a242","abstract_canon_sha256":"07da6c361ff7575cadddecb4e1ad30a7be86cb11a9f2813901c96e9ef9d88b35"},"schema_version":"1.0"},"canonical_sha256":"8f34fd71940505721dacd36112e81f47031af49c68e55f8e04917fb3cf2df808","source":{"kind":"arxiv","id":"2501.14951","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14951","created_at":"2026-07-05T10:27:24Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14951v2","created_at":"2026-07-05T10:27:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14951","created_at":"2026-07-05T10:27:24Z"},{"alias_kind":"pith_short_12","alias_value":"R42P24MUAUCX","created_at":"2026-07-05T10:27:24Z"},{"alias_kind":"pith_short_16","alias_value":"R42P24MUAUCXEHNM","created_at":"2026-07-05T10:27:24Z"},{"alias_kind":"pith_short_8","alias_value":"R42P24MU","created_at":"2026-07-05T10:27:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:R42P24MUAUCXEHNM2NQRF2A7I4","target":"record","payload":{"canonical_record":{"source":{"id":"2501.14951","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T22:39:08Z","cross_cats_sorted":["cs.CL","cs.SC"],"title_canon_sha256":"f27d25b368ca3bd7234839d129f9dbddbc75cd300c6455f30dc3e6946e48a242","abstract_canon_sha256":"07da6c361ff7575cadddecb4e1ad30a7be86cb11a9f2813901c96e9ef9d88b35"},"schema_version":"1.0"},"canonical_sha256":"8f34fd71940505721dacd36112e81f47031af49c68e55f8e04917fb3cf2df808","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:24.117944Z","signature_b64":"2GbigV0ggsvttkzsgnNY8yE3cOG/zEUOz0QZC0+vR4PfzyIzzrSz2BN0b+2bB653lNCEw3Io1f858YrNoF4xBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f34fd71940505721dacd36112e81f47031af49c68e55f8e04917fb3cf2df808","last_reissued_at":"2026-07-05T10:27:24.117436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:24.117436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.14951","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":"2026-07-05T10:27:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uAl5PMNx/rkx8LPwQvEKyp06RprSRg2HPcIopbF4ENOXkH40v2unlgEo+6u+pdLJiyIjRiNwb/fCG7lfZVIkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:11:47.283799Z"},"content_sha256":"656d3fd3d020ecca03b5bf62ee712d4ac1781e340a3518d9d2988106f5fe7b85","schema_version":"1.0","event_id":"sha256:656d3fd3d020ecca03b5bf62ee712d4ac1781e340a3518d9d2988106f5fe7b85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:R42P24MUAUCXEHNM2NQRF2A7I4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SC"],"primary_cat":"cs.LG","authors_text":"Hongbo Zheng, Neeraj Gangwar, Nickvash Kani, Suyuan Wang","submitted_at":"2025-01-24T22:39:08Z","abstract_excerpt":"Vector representations have been pivotal in advancing natural language processing (NLP), with prior research focusing on embedding techniques for mathematical expressions using mathematically equivalent formulations. While effective, these approaches are constrained by the size and diversity of training data. In this work, we address these limitations by introducing E-Gen, a novel e-graph-based dataset generation scheme that synthesizes large and diverse mathematical expression datasets, surpassing prior methods in size and operator variety. Leveraging this dataset, we train embedding models u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14951","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/2501.14951/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":"2026-07-05T10:27:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KUwhdW3akEfwneZuhw4bFGUHm1HJYUn8CAK/K3O3CrgBdCcb1WjLB28+dnJpTYknYzSpEQDjzZ0/nfT9ujpxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:11:47.284905Z"},"content_sha256":"2ad3f03e2ad6ec172392d322a126808998342802e8076e110f30c2baf372968a","schema_version":"1.0","event_id":"sha256:2ad3f03e2ad6ec172392d322a126808998342802e8076e110f30c2baf372968a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R42P24MUAUCXEHNM2NQRF2A7I4/bundle.json","state_url":"https://pith.science/pith/R42P24MUAUCXEHNM2NQRF2A7I4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R42P24MUAUCXEHNM2NQRF2A7I4/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":"2026-08-11T01:11:47Z","links":{"resolver":"https://pith.science/pith/R42P24MUAUCXEHNM2NQRF2A7I4","bundle":"https://pith.science/pith/R42P24MUAUCXEHNM2NQRF2A7I4/bundle.json","state":"https://pith.science/pith/R42P24MUAUCXEHNM2NQRF2A7I4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R42P24MUAUCXEHNM2NQRF2A7I4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R42P24MUAUCXEHNM2NQRF2A7I4","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":"07da6c361ff7575cadddecb4e1ad30a7be86cb11a9f2813901c96e9ef9d88b35","cross_cats_sorted":["cs.CL","cs.SC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T22:39:08Z","title_canon_sha256":"f27d25b368ca3bd7234839d129f9dbddbc75cd300c6455f30dc3e6946e48a242"},"schema_version":"1.0","source":{"id":"2501.14951","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14951","created_at":"2026-07-05T10:27:24Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14951v2","created_at":"2026-07-05T10:27:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14951","created_at":"2026-07-05T10:27:24Z"},{"alias_kind":"pith_short_12","alias_value":"R42P24MUAUCX","created_at":"2026-07-05T10:27:24Z"},{"alias_kind":"pith_short_16","alias_value":"R42P24MUAUCXEHNM","created_at":"2026-07-05T10:27:24Z"},{"alias_kind":"pith_short_8","alias_value":"R42P24MU","created_at":"2026-07-05T10:27:24Z"}],"graph_snapshots":[{"event_id":"sha256:2ad3f03e2ad6ec172392d322a126808998342802e8076e110f30c2baf372968a","target":"graph","created_at":"2026-07-05T10:27:24Z","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/2501.14951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vector representations have been pivotal in advancing natural language processing (NLP), with prior research focusing on embedding techniques for mathematical expressions using mathematically equivalent formulations. While effective, these approaches are constrained by the size and diversity of training data. In this work, we address these limitations by introducing E-Gen, a novel e-graph-based dataset generation scheme that synthesizes large and diverse mathematical expression datasets, surpassing prior methods in size and operator variety. Leveraging this dataset, we train embedding models u","authors_text":"Hongbo Zheng, Neeraj Gangwar, Nickvash Kani, Suyuan Wang","cross_cats":["cs.CL","cs.SC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T22:39:08Z","title":"E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14951","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":"sha256:656d3fd3d020ecca03b5bf62ee712d4ac1781e340a3518d9d2988106f5fe7b85","target":"record","created_at":"2026-07-05T10:27:24Z","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":"07da6c361ff7575cadddecb4e1ad30a7be86cb11a9f2813901c96e9ef9d88b35","cross_cats_sorted":["cs.CL","cs.SC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T22:39:08Z","title_canon_sha256":"f27d25b368ca3bd7234839d129f9dbddbc75cd300c6455f30dc3e6946e48a242"},"schema_version":"1.0","source":{"id":"2501.14951","kind":"arxiv","version":2}},"canonical_sha256":"8f34fd71940505721dacd36112e81f47031af49c68e55f8e04917fb3cf2df808","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f34fd71940505721dacd36112e81f47031af49c68e55f8e04917fb3cf2df808","first_computed_at":"2026-07-05T10:27:24.117436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:24.117436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2GbigV0ggsvttkzsgnNY8yE3cOG/zEUOz0QZC0+vR4PfzyIzzrSz2BN0b+2bB653lNCEw3Io1f858YrNoF4xBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:24.117944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14951","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:656d3fd3d020ecca03b5bf62ee712d4ac1781e340a3518d9d2988106f5fe7b85","sha256:2ad3f03e2ad6ec172392d322a126808998342802e8076e110f30c2baf372968a"],"state_sha256":"1827f77a61caccd8424e8d805108413725e7eedd62685be3551aff2d38d4e95d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vFIXHd+jZptViuw8kpfZwAFLz6mtH0WviajUuvHJuxCwA6PLHlqFdTOWu5ueM4I2QpifQQNmj4k5j8BfYxjjBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:11:47.292934Z","bundle_sha256":"f4dabf4123419b184724f46cbeeeb8bc0fb91d1bc9275830de538a0fe8c6de96"}}