{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SDNYOHMXHUUUTVIS6QRZADMW37","short_pith_number":"pith:SDNYOHMX","schema_version":"1.0","canonical_sha256":"90db871d973d2949d512f423900d96dfe46835e52f54d1c82b94be5f9e7ff547","source":{"kind":"arxiv","id":"2403.11734","version":2},"attestation_state":"computed","paper":{"title":"Learning More Expressive General Policies for Classical Planning Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Blai Bonet, Hector Geffner, Simon St\\r{a}hlberg","submitted_at":"2024-03-18T12:42:53Z","abstract_excerpt":"GNN-based approaches for learning general policies across planning domains are limited by the expressive power of $C_2$, namely; first-order logic with two variables and counting. This limitation can be overcame by transitioning to $k$-GNNs, for $k=3$, wherein object embeddings are substituted with triplet embeddings. Yet, while $3$-GNNs have the expressive power of $C_3$, unlike $1$- and $2$-GNNs that are confined to $C_2$, they require quartic time for message exchange and cubic space to store embeddings, rendering them infeasible in practice. In this work, we introduce a parameterized versi"},"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":"2403.11734","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-18T12:42:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ddce440b12306bcba71b480c14a23bf8a86352c5546b33779628d8306220aff8","abstract_canon_sha256":"2fc7a1fb49510a5a447133cf0b50950b37b4060efdeb21da58d964fcdc511d50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:07.937311Z","signature_b64":"M2wj0xAMW+PBhhUTuVUa5eNFGhOt2tMKu4dqCxm5Onlja6c2O/aMKbbURpkzQvjJHCpXrPwzvIzQPy7KHSsODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90db871d973d2949d512f423900d96dfe46835e52f54d1c82b94be5f9e7ff547","last_reissued_at":"2026-07-05T10:16:07.936825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:07.936825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning More Expressive General Policies for Classical Planning Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Blai Bonet, Hector Geffner, Simon St\\r{a}hlberg","submitted_at":"2024-03-18T12:42:53Z","abstract_excerpt":"GNN-based approaches for learning general policies across planning domains are limited by the expressive power of $C_2$, namely; first-order logic with two variables and counting. This limitation can be overcame by transitioning to $k$-GNNs, for $k=3$, wherein object embeddings are substituted with triplet embeddings. Yet, while $3$-GNNs have the expressive power of $C_3$, unlike $1$- and $2$-GNNs that are confined to $C_2$, they require quartic time for message exchange and cubic space to store embeddings, rendering them infeasible in practice. In this work, we introduce a parameterized versi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11734","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/2403.11734/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":"2403.11734","created_at":"2026-07-05T10:16:07.936884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11734v2","created_at":"2026-07-05T10:16:07.936884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11734","created_at":"2026-07-05T10:16:07.936884+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDNYOHMXHUUU","created_at":"2026-07-05T10:16:07.936884+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDNYOHMXHUUUTVIS","created_at":"2026-07-05T10:16:07.936884+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDNYOHMX","created_at":"2026-07-05T10:16:07.936884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02136","citing_title":"Graph Learning for Planning: The Story Thus Far and Open Challenges","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDNYOHMXHUUUTVIS6QRZADMW37","json":"https://pith.science/pith/SDNYOHMXHUUUTVIS6QRZADMW37.json","graph_json":"https://pith.science/api/pith-number/SDNYOHMXHUUUTVIS6QRZADMW37/graph.json","events_json":"https://pith.science/api/pith-number/SDNYOHMXHUUUTVIS6QRZADMW37/events.json","paper":"https://pith.science/paper/SDNYOHMX"},"agent_actions":{"view_html":"https://pith.science/pith/SDNYOHMXHUUUTVIS6QRZADMW37","download_json":"https://pith.science/pith/SDNYOHMXHUUUTVIS6QRZADMW37.json","view_paper":"https://pith.science/paper/SDNYOHMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11734&json=true","fetch_graph":"https://pith.science/api/pith-number/SDNYOHMXHUUUTVIS6QRZADMW37/graph.json","fetch_events":"https://pith.science/api/pith-number/SDNYOHMXHUUUTVIS6QRZADMW37/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDNYOHMXHUUUTVIS6QRZADMW37/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDNYOHMXHUUUTVIS6QRZADMW37/action/storage_attestation","attest_author":"https://pith.science/pith/SDNYOHMXHUUUTVIS6QRZADMW37/action/author_attestation","sign_citation":"https://pith.science/pith/SDNYOHMXHUUUTVIS6QRZADMW37/action/citation_signature","submit_replication":"https://pith.science/pith/SDNYOHMXHUUUTVIS6QRZADMW37/action/replication_record"}},"created_at":"2026-07-05T10:16:07.936884+00:00","updated_at":"2026-07-05T10:16:07.936884+00:00"}