{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JZZRQ732X7NOLP72S2ZEWYMSMY","short_pith_number":"pith:JZZRQ732","schema_version":"1.0","canonical_sha256":"4e73187f7abfdae5bffa96b24b61926608ca30c2fe66ad7dec49ca60ab79d6fb","source":{"kind":"arxiv","id":"2406.03914","version":1},"attestation_state":"computed","paper":{"title":"Neuro-Symbolic Temporal Point Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boyang Li, Chao Yang, Shuang Li, Yang Yang, Yinghao Fu","submitted_at":"2024-06-06T09:52:56Z","abstract_excerpt":"Our goal is to $\\textit{efficiently}$ discover a compact set of temporal logic rules to explain irregular events of interest. We introduce a neural-symbolic rule induction framework within the temporal point process model. The negative log-likelihood is the loss that guides the learning, where the explanatory logic rules and their weights are learned end-to-end in a $\\textit{differentiable}$ way. Specifically, predicates and logic rules are represented as $\\textit{vector embeddings}$, where the predicate embeddings are fixed and the rule embeddings are trained via gradient descent to obtain th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.03914","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T09:52:56Z","cross_cats_sorted":[],"title_canon_sha256":"247fbe19a0918f9cd9ccf44660fb29e50a2ec6c8ea3537834c219d5151767b10","abstract_canon_sha256":"732d57cbd384ea67e2198d635f0975378f6cc660f8ef31e448b0f08679811abd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:17.868825Z","signature_b64":"i/IsBz2m55jswWRpyzHR8ZSkWugmOlV7SjecRAspL0LJx1fwExqSS4C0zucoCqV/rJLQCs++ZeMdfO2w+hJNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e73187f7abfdae5bffa96b24b61926608ca30c2fe66ad7dec49ca60ab79d6fb","last_reissued_at":"2026-07-05T08:28:17.868308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:17.868308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neuro-Symbolic Temporal Point Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boyang Li, Chao Yang, Shuang Li, Yang Yang, Yinghao Fu","submitted_at":"2024-06-06T09:52:56Z","abstract_excerpt":"Our goal is to $\\textit{efficiently}$ discover a compact set of temporal logic rules to explain irregular events of interest. We introduce a neural-symbolic rule induction framework within the temporal point process model. The negative log-likelihood is the loss that guides the learning, where the explanatory logic rules and their weights are learned end-to-end in a $\\textit{differentiable}$ way. Specifically, predicates and logic rules are represented as $\\textit{vector embeddings}$, where the predicate embeddings are fixed and the rule embeddings are trained via gradient descent to obtain th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03914","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/2406.03914/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.03914","created_at":"2026-07-05T08:28:17.868381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03914v1","created_at":"2026-07-05T08:28:17.868381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03914","created_at":"2026-07-05T08:28:17.868381+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZZRQ732X7NO","created_at":"2026-07-05T08:28:17.868381+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZZRQ732X7NOLP72","created_at":"2026-07-05T08:28:17.868381+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZZRQ732","created_at":"2026-07-05T08:28:17.868381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17482","citing_title":"LTLZinc: a Benchmarking Framework for Continual Learning and Neuro-Symbolic Temporal Reasoning","ref_index":81,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZZRQ732X7NOLP72S2ZEWYMSMY","json":"https://pith.science/pith/JZZRQ732X7NOLP72S2ZEWYMSMY.json","graph_json":"https://pith.science/api/pith-number/JZZRQ732X7NOLP72S2ZEWYMSMY/graph.json","events_json":"https://pith.science/api/pith-number/JZZRQ732X7NOLP72S2ZEWYMSMY/events.json","paper":"https://pith.science/paper/JZZRQ732"},"agent_actions":{"view_html":"https://pith.science/pith/JZZRQ732X7NOLP72S2ZEWYMSMY","download_json":"https://pith.science/pith/JZZRQ732X7NOLP72S2ZEWYMSMY.json","view_paper":"https://pith.science/paper/JZZRQ732","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03914&json=true","fetch_graph":"https://pith.science/api/pith-number/JZZRQ732X7NOLP72S2ZEWYMSMY/graph.json","fetch_events":"https://pith.science/api/pith-number/JZZRQ732X7NOLP72S2ZEWYMSMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZZRQ732X7NOLP72S2ZEWYMSMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZZRQ732X7NOLP72S2ZEWYMSMY/action/storage_attestation","attest_author":"https://pith.science/pith/JZZRQ732X7NOLP72S2ZEWYMSMY/action/author_attestation","sign_citation":"https://pith.science/pith/JZZRQ732X7NOLP72S2ZEWYMSMY/action/citation_signature","submit_replication":"https://pith.science/pith/JZZRQ732X7NOLP72S2ZEWYMSMY/action/replication_record"}},"created_at":"2026-07-05T08:28:17.868381+00:00","updated_at":"2026-07-05T08:28:17.868381+00:00"}