{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EROO3PS3CE4AX7APPW5DLEM47N","short_pith_number":"pith:EROO3PS3","schema_version":"1.0","canonical_sha256":"245cedbe5b11380bfc0f7dba35919cfb73947379bcf7c40fac79759c03ce31c9","source":{"kind":"arxiv","id":"2605.18674","version":1},"attestation_state":"computed","paper":{"title":"Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hector Geffner, Martin Funkquist, Michael Aichm\\\"uller, Simon St{\\aa}hlberg","submitted_at":"2026-05-18T17:15:23Z","abstract_excerpt":"Generalized planning aims to learn policies that generalize across collections of instances within a classical planning domain. Recent Graph Neural Network (GNN) approaches have learned nearly perfect policies for several domains. This work improves on the recently published idea of Iterated Width (IW) policies. Therein, the policy broadens its successor scope through an IW-lookahead search that can \"jump\" over multiple transitions, simplifying the problem structure. Yet, each transition is evaluated individually, leading to unscalable compute costs and expressivity limitations. Furthermore, a"},"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":"2605.18674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T17:15:23Z","cross_cats_sorted":[],"title_canon_sha256":"8b80a9bfa0982e06b120557a7f44ec52ff516f68bc2f3f40c6a6c9c486fee2bd","abstract_canon_sha256":"427f4d45eb6522d2c716ed81339dc6142a0c9367a7527c69dc9b2bf1e75c356e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:14.150279Z","signature_b64":"9NNvricT26k2cWe0FakSBI5qYL1PREdPLBGJv2vpUYzAPla6StmqhGuM2/m1H8NEqRO/KZrANV+6z5NVT4/5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"245cedbe5b11380bfc0f7dba35919cfb73947379bcf7c40fac79759c03ce31c9","last_reissued_at":"2026-05-20T00:06:14.149416Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:14.149416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hector Geffner, Martin Funkquist, Michael Aichm\\\"uller, Simon St{\\aa}hlberg","submitted_at":"2026-05-18T17:15:23Z","abstract_excerpt":"Generalized planning aims to learn policies that generalize across collections of instances within a classical planning domain. Recent Graph Neural Network (GNN) approaches have learned nearly perfect policies for several domains. This work improves on the recently published idea of Iterated Width (IW) policies. Therein, the policy broadens its successor scope through an IW-lookahead search that can \"jump\" over multiple transitions, simplifying the problem structure. Yet, each transition is evaluated individually, leading to unscalable compute costs and expressivity limitations. Furthermore, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18674","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/2605.18674/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.129554Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"17660ba16393404c5df408b71d07398e25eafdda2962f035c604d4cfb7545f11"},"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":"2605.18674","created_at":"2026-05-20T00:06:14.149580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18674v1","created_at":"2026-05-20T00:06:14.149580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18674","created_at":"2026-05-20T00:06:14.149580+00:00"},{"alias_kind":"pith_short_12","alias_value":"EROO3PS3CE4A","created_at":"2026-05-20T00:06:14.149580+00:00"},{"alias_kind":"pith_short_16","alias_value":"EROO3PS3CE4AX7AP","created_at":"2026-05-20T00:06:14.149580+00:00"},{"alias_kind":"pith_short_8","alias_value":"EROO3PS3","created_at":"2026-05-20T00:06:14.149580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EROO3PS3CE4AX7APPW5DLEM47N","json":"https://pith.science/pith/EROO3PS3CE4AX7APPW5DLEM47N.json","graph_json":"https://pith.science/api/pith-number/EROO3PS3CE4AX7APPW5DLEM47N/graph.json","events_json":"https://pith.science/api/pith-number/EROO3PS3CE4AX7APPW5DLEM47N/events.json","paper":"https://pith.science/paper/EROO3PS3"},"agent_actions":{"view_html":"https://pith.science/pith/EROO3PS3CE4AX7APPW5DLEM47N","download_json":"https://pith.science/pith/EROO3PS3CE4AX7APPW5DLEM47N.json","view_paper":"https://pith.science/paper/EROO3PS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18674&json=true","fetch_graph":"https://pith.science/api/pith-number/EROO3PS3CE4AX7APPW5DLEM47N/graph.json","fetch_events":"https://pith.science/api/pith-number/EROO3PS3CE4AX7APPW5DLEM47N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EROO3PS3CE4AX7APPW5DLEM47N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EROO3PS3CE4AX7APPW5DLEM47N/action/storage_attestation","attest_author":"https://pith.science/pith/EROO3PS3CE4AX7APPW5DLEM47N/action/author_attestation","sign_citation":"https://pith.science/pith/EROO3PS3CE4AX7APPW5DLEM47N/action/citation_signature","submit_replication":"https://pith.science/pith/EROO3PS3CE4AX7APPW5DLEM47N/action/replication_record"}},"created_at":"2026-05-20T00:06:14.149580+00:00","updated_at":"2026-05-20T00:06:14.149580+00:00"}