{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FGEHE3DUSXLSYHLYHYWD5S4DMK","short_pith_number":"pith:FGEHE3DU","canonical_record":{"source":{"id":"2508.04162","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-06T07:39:17Z","cross_cats_sorted":[],"title_canon_sha256":"b726951fd65c32be81fa25d8170dcc2c7eb1b5b933ca43723b38beecf417e202","abstract_canon_sha256":"5c9e6cc5555e94d656898f8205ae53c65d420c9aa882260095171285867989da"},"schema_version":"1.0"},"canonical_sha256":"2988726c7495d72c1d783e2c3ecb8362b293a4dc0c06b0bbad716c28c36e4c0b","source":{"kind":"arxiv","id":"2508.04162","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04162","created_at":"2026-07-05T11:49:59Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04162v2","created_at":"2026-07-05T11:49:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04162","created_at":"2026-07-05T11:49:59Z"},{"alias_kind":"pith_short_12","alias_value":"FGEHE3DUSXLS","created_at":"2026-07-05T11:49:59Z"},{"alias_kind":"pith_short_16","alias_value":"FGEHE3DUSXLSYHLY","created_at":"2026-07-05T11:49:59Z"},{"alias_kind":"pith_short_8","alias_value":"FGEHE3DU","created_at":"2026-07-05T11:49:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FGEHE3DUSXLSYHLYHYWD5S4DMK","target":"record","payload":{"canonical_record":{"source":{"id":"2508.04162","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-06T07:39:17Z","cross_cats_sorted":[],"title_canon_sha256":"b726951fd65c32be81fa25d8170dcc2c7eb1b5b933ca43723b38beecf417e202","abstract_canon_sha256":"5c9e6cc5555e94d656898f8205ae53c65d420c9aa882260095171285867989da"},"schema_version":"1.0"},"canonical_sha256":"2988726c7495d72c1d783e2c3ecb8362b293a4dc0c06b0bbad716c28c36e4c0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:00.000289Z","signature_b64":"jdRYou1ZgAj+GSt+IeLubOyOcZCaSSTA52w4OWRtFkQJL3BKrVWgNUtVzmuhwbFHaHbGoHawVvxFG4fALcauAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2988726c7495d72c1d783e2c3ecb8362b293a4dc0c06b0bbad716c28c36e4c0b","last_reissued_at":"2026-07-05T11:49:59.999823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:59.999823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.04162","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":"2026-07-05T11:49:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/iCwLWxeyU1gNyR9Eu1d/+EOl7v5U34fdFxC74yFpT+MiAlI202kMCcwxnhNYTvdNCugzTUsFyT13LEl+y6yCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:15:34.241546Z"},"content_sha256":"4191cf095b4c55f9ddd8d6068ad39800dfd7bb1b7f7998e7f7ceb9f18358436b","schema_version":"1.0","event_id":"sha256:4191cf095b4c55f9ddd8d6068ad39800dfd7bb1b7f7998e7f7ceb9f18358436b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FGEHE3DUSXLSYHLYHYWD5S4DMK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SSEmb: A Joint Structural and Semantic Embedding Framework for Mathematical Formula Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ruyin Li, Xiaoyu Chen","submitted_at":"2025-08-06T07:39:17Z","abstract_excerpt":"Formula retrieval is an important topic in Mathematical Information Retrieval. We propose SSEmb, a novel embedding framework capable of capturing both structural and semantic features of mathematical formulas. Structurally, we employ Graph Contrastive Learning to encode formulas represented as Operator Graphs. To enhance structural diversity while preserving mathematical validity of these formula graphs, we introduce a novel graph data augmentation approach through a substitution strategy. Semantically, we utilize Sentence-BERT to encode the surrounding text of formulas. Finally, for each quer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04162","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/2508.04162/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":"2026-07-05T11:49:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cqwxvjiey/C06dsVluqZvsG8bu9jpUvLYjPRWvQSu2OCW9zvMC5Qns/qP9caLYnG4GbDEsBC5CYFwqfuWuGMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:15:34.242920Z"},"content_sha256":"158c1b9bcbfd4b8a0dcc2f471045fcc9e6b094aeb008df6a3eecacdd35fb3282","schema_version":"1.0","event_id":"sha256:158c1b9bcbfd4b8a0dcc2f471045fcc9e6b094aeb008df6a3eecacdd35fb3282"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGEHE3DUSXLSYHLYHYWD5S4DMK/bundle.json","state_url":"https://pith.science/pith/FGEHE3DUSXLSYHLYHYWD5S4DMK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGEHE3DUSXLSYHLYHYWD5S4DMK/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":"2026-08-05T15:15:34Z","links":{"resolver":"https://pith.science/pith/FGEHE3DUSXLSYHLYHYWD5S4DMK","bundle":"https://pith.science/pith/FGEHE3DUSXLSYHLYHYWD5S4DMK/bundle.json","state":"https://pith.science/pith/FGEHE3DUSXLSYHLYHYWD5S4DMK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGEHE3DUSXLSYHLYHYWD5S4DMK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FGEHE3DUSXLSYHLYHYWD5S4DMK","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":"5c9e6cc5555e94d656898f8205ae53c65d420c9aa882260095171285867989da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-06T07:39:17Z","title_canon_sha256":"b726951fd65c32be81fa25d8170dcc2c7eb1b5b933ca43723b38beecf417e202"},"schema_version":"1.0","source":{"id":"2508.04162","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04162","created_at":"2026-07-05T11:49:59Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04162v2","created_at":"2026-07-05T11:49:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04162","created_at":"2026-07-05T11:49:59Z"},{"alias_kind":"pith_short_12","alias_value":"FGEHE3DUSXLS","created_at":"2026-07-05T11:49:59Z"},{"alias_kind":"pith_short_16","alias_value":"FGEHE3DUSXLSYHLY","created_at":"2026-07-05T11:49:59Z"},{"alias_kind":"pith_short_8","alias_value":"FGEHE3DU","created_at":"2026-07-05T11:49:59Z"}],"graph_snapshots":[{"event_id":"sha256:158c1b9bcbfd4b8a0dcc2f471045fcc9e6b094aeb008df6a3eecacdd35fb3282","target":"graph","created_at":"2026-07-05T11:49:59Z","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/2508.04162/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Formula retrieval is an important topic in Mathematical Information Retrieval. We propose SSEmb, a novel embedding framework capable of capturing both structural and semantic features of mathematical formulas. Structurally, we employ Graph Contrastive Learning to encode formulas represented as Operator Graphs. To enhance structural diversity while preserving mathematical validity of these formula graphs, we introduce a novel graph data augmentation approach through a substitution strategy. Semantically, we utilize Sentence-BERT to encode the surrounding text of formulas. Finally, for each quer","authors_text":"Ruyin Li, Xiaoyu Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-06T07:39:17Z","title":"SSEmb: A Joint Structural and Semantic Embedding Framework for Mathematical Formula Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04162","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":"sha256:4191cf095b4c55f9ddd8d6068ad39800dfd7bb1b7f7998e7f7ceb9f18358436b","target":"record","created_at":"2026-07-05T11:49:59Z","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":"5c9e6cc5555e94d656898f8205ae53c65d420c9aa882260095171285867989da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-06T07:39:17Z","title_canon_sha256":"b726951fd65c32be81fa25d8170dcc2c7eb1b5b933ca43723b38beecf417e202"},"schema_version":"1.0","source":{"id":"2508.04162","kind":"arxiv","version":2}},"canonical_sha256":"2988726c7495d72c1d783e2c3ecb8362b293a4dc0c06b0bbad716c28c36e4c0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2988726c7495d72c1d783e2c3ecb8362b293a4dc0c06b0bbad716c28c36e4c0b","first_computed_at":"2026-07-05T11:49:59.999823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:59.999823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jdRYou1ZgAj+GSt+IeLubOyOcZCaSSTA52w4OWRtFkQJL3BKrVWgNUtVzmuhwbFHaHbGoHawVvxFG4fALcauAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:00.000289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.04162","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4191cf095b4c55f9ddd8d6068ad39800dfd7bb1b7f7998e7f7ceb9f18358436b","sha256:158c1b9bcbfd4b8a0dcc2f471045fcc9e6b094aeb008df6a3eecacdd35fb3282"],"state_sha256":"45d3a730fd2385cc2e7c5f6670c6df5a2e84691cfb6880a05f5d2a5d9d275c24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRDAi3PcECxfRgGU/FT1COk1Jzg+urjl5VyWpbWrfnuObFIqof8I/eTpvgpRyULDWmQyZhjaCq3K24idin7yAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:15:34.249947Z","bundle_sha256":"d4157e067a796843fba7680b7b48757b6e7bd58c49b760b9d4085091b1b9044a"}}