{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HMXUOUHUPLWEP543W4VGTWY6OX","short_pith_number":"pith:HMXUOUHU","canonical_record":{"source":{"id":"2605.13282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T09:59:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5b4754684cfd0aa5dccfe9699372d0df6d6d27c9a246cd57e9c1b91fd3a8ddad","abstract_canon_sha256":"67bee74cca35e230c624dc64a60ac3ecc01d7b2d81d14a9f828837beef478ebe"},"schema_version":"1.0"},"canonical_sha256":"3b2f4750f47aec47f79bb72a69db1e75f16207df175fe0337f86a40562b22ae8","source":{"kind":"arxiv","id":"2605.13282","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13282","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13282v1","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13282","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"HMXUOUHUPLWE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"HMXUOUHUPLWEP543","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"HMXUOUHU","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HMXUOUHUPLWEP543W4VGTWY6OX","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T09:59:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5b4754684cfd0aa5dccfe9699372d0df6d6d27c9a246cd57e9c1b91fd3a8ddad","abstract_canon_sha256":"67bee74cca35e230c624dc64a60ac3ecc01d7b2d81d14a9f828837beef478ebe"},"schema_version":"1.0"},"canonical_sha256":"3b2f4750f47aec47f79bb72a69db1e75f16207df175fe0337f86a40562b22ae8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:49.186943Z","signature_b64":"aFmAR1ifO4ZVKKkh6i43L6xD+vuBzgL5VgV1Db/d8d+bdKr/8SgM2FIqVyQezs7io65yoABGpfE6ozDT/0f9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b2f4750f47aec47f79bb72a69db1e75f16207df175fe0337f86a40562b22ae8","last_reissued_at":"2026-05-18T02:44:49.186519Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:49.186519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13282","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JUBsSrHONeSblKPTyGerjQC79LqIBb2HtNtXVn+Atr9+252lWHsdnilTflPd1Nia2xwpSDb0PhMCFZ7LpJhKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:20:12.086737Z"},"content_sha256":"b08975c5df11c9df6c0e778a89d34aedc87d05b14bc0e7d99b1b47babe3c22b4","schema_version":"1.0","event_id":"sha256:b08975c5df11c9df6c0e778a89d34aedc87d05b14bc0e7d99b1b47babe3c22b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HMXUOUHUPLWEP543W4VGTWY6OX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Differentiable Learning of Lifted Action Schemas for Classical Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A differentiable neural network learns lifted action schemas from fully observed state traces by inferring unobserved action arguments from state changes.","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Hector Geffner, Jakob Elias Gebler, Jonas Reiter","submitted_at":"2026-05-13T09:59:49Z","abstract_excerpt":"Classical planners can effectively solve very large deterministic MDPs represented in STRIPS or PDDL where states are sets of atoms over objects and relations, and lifted action schemas add or delete these atoms. This compact representation yields strong search heuristics and provides an ideal setting for structural generalization, since lifted relations and action schemas give rise to infinitely many domain instances. A central challenge is to learn these relations and action schemas from data, and recent approaches have addressed this problem using different types of observations. In this wo"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our approach yields a robust differentiable component that can then be integrated into larger neuro-symbolic models. We evaluate the architecture on various planning domains, where the learned lifted action schemas must recover the ground-truth structure.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that states are fully observed as sets of atoms and that action arguments can be uniquely recovered from observed state changes without additional supervision or ambiguity.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A differentiable neural model recovers ground-truth lifted action schemas from state traces by jointly learning schemas and inferring unobserved action arguments.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A differentiable neural network learns lifted action schemas from fully observed state traces by inferring unobserved action arguments from state changes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"017f16872f112c7b4769e506a409a9f1c60b7119103205c9ffaff3ab813a717f"},"source":{"id":"2605.13282","kind":"arxiv","version":1},"verdict":{"id":"92213afd-a4ef-4695-af23-db0ff711621c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:37:18.570924Z","strongest_claim":"Our approach yields a robust differentiable component that can then be integrated into larger neuro-symbolic models. We evaluate the architecture on various planning domains, where the learned lifted action schemas must recover the ground-truth structure.","one_line_summary":"A differentiable neural model recovers ground-truth lifted action schemas from state traces by jointly learning schemas and inferring unobserved action arguments.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that states are fully observed as sets of atoms and that action arguments can be uniquely recovered from observed state changes without additional supervision or ambiguity.","pith_extraction_headline":"A differentiable neural network learns lifted action schemas from fully observed state traces by inferring unobserved action arguments from state changes."},"references":{"count":300,"sample":[{"doi":"10.1016/j.artint.2019.05.003","year":2019,"title":"doi:10.1016/j.artint.2019.05.003 , langid =","work_id":"1ca22c72-e5ab-4f88-acd5-9feaf9c846cb","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Asai, Masataro and Fukunaga, Alex , date =. Classical","work_id":"34e600d1-30b6-4078-9c1a-aa369c8e31bc","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.24963/kr.2024/76","year":2024,"title":"Michael , date =","work_id":"ad700027-3d8b-4514-9eb9-3bbef7015cd9","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"and Monet, Mikael and Pérez, Jorge and Reutter, Juan and Silva, Juan Pablo , date =","work_id":"83c78b13-4a58-423c-ae56-96abd5247e5d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/icpr56361.2022.9956203","year":2022,"title":"Going Beyond Accuracy: Interpretability Metrics for CNN Representations of Physiological Signals , shorttitle =","work_id":"30810c46-a407-4245-b6d7-61f9288984fb","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":300,"snapshot_sha256":"4304f3b2b418b91b5b4fa6050954432d65d90bc97b5845dcc5e44f72a398fadd","internal_anchors":2},"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":"92213afd-a4ef-4695-af23-db0ff711621c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/9CNfNjunNsUo0xaB4ItFx1oV2zSFpFmUAFpIGEP+VbDkAX+qktzvrQyX36waIoehX5JR2ZBSZPHSbxyGdAnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:20:12.087874Z"},"content_sha256":"4372c06dd6163b95aa063aa521e59b3a7f23b923626b66aa851844fb50f43d25","schema_version":"1.0","event_id":"sha256:4372c06dd6163b95aa063aa521e59b3a7f23b923626b66aa851844fb50f43d25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HMXUOUHUPLWEP543W4VGTWY6OX/bundle.json","state_url":"https://pith.science/pith/HMXUOUHUPLWEP543W4VGTWY6OX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HMXUOUHUPLWEP543W4VGTWY6OX/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":"2026-05-25T21:20:12Z","links":{"resolver":"https://pith.science/pith/HMXUOUHUPLWEP543W4VGTWY6OX","bundle":"https://pith.science/pith/HMXUOUHUPLWEP543W4VGTWY6OX/bundle.json","state":"https://pith.science/pith/HMXUOUHUPLWEP543W4VGTWY6OX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HMXUOUHUPLWEP543W4VGTWY6OX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HMXUOUHUPLWEP543W4VGTWY6OX","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":"67bee74cca35e230c624dc64a60ac3ecc01d7b2d81d14a9f828837beef478ebe","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T09:59:49Z","title_canon_sha256":"5b4754684cfd0aa5dccfe9699372d0df6d6d27c9a246cd57e9c1b91fd3a8ddad"},"schema_version":"1.0","source":{"id":"2605.13282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13282","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13282v1","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13282","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"HMXUOUHUPLWE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"HMXUOUHUPLWEP543","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"HMXUOUHU","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:4372c06dd6163b95aa063aa521e59b3a7f23b923626b66aa851844fb50f43d25","target":"graph","created_at":"2026-05-18T02:44:49Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our approach yields a robust differentiable component that can then be integrated into larger neuro-symbolic models. We evaluate the architecture on various planning domains, where the learned lifted action schemas must recover the ground-truth structure."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that states are fully observed as sets of atoms and that action arguments can be uniquely recovered from observed state changes without additional supervision or ambiguity."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A differentiable neural model recovers ground-truth lifted action schemas from state traces by jointly learning schemas and inferring unobserved action arguments."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A differentiable neural network learns lifted action schemas from fully observed state traces by inferring unobserved action arguments from state changes."}],"snapshot_sha256":"017f16872f112c7b4769e506a409a9f1c60b7119103205c9ffaff3ab813a717f"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Classical planners can effectively solve very large deterministic MDPs represented in STRIPS or PDDL where states are sets of atoms over objects and relations, and lifted action schemas add or delete these atoms. This compact representation yields strong search heuristics and provides an ideal setting for structural generalization, since lifted relations and action schemas give rise to infinitely many domain instances. A central challenge is to learn these relations and action schemas from data, and recent approaches have addressed this problem using different types of observations. In this wo","authors_text":"Hector Geffner, Jakob Elias Gebler, Jonas Reiter","cross_cats":["cs.LG"],"headline":"A differentiable neural network learns lifted action schemas from fully observed state traces by inferring unobserved action arguments from state changes.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T09:59:49Z","title":"Differentiable Learning of Lifted Action Schemas for Classical Planning"},"references":{"count":300,"internal_anchors":2,"resolved_work":300,"sample":[{"cited_arxiv_id":"","doi":"10.1016/j.artint.2019.05.003","is_internal_anchor":false,"ref_index":1,"title":"doi:10.1016/j.artint.2019.05.003 , langid =","work_id":"1ca22c72-e5ab-4f88-acd5-9feaf9c846cb","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Asai, Masataro and Fukunaga, Alex , date =. Classical","work_id":"34e600d1-30b6-4078-9c1a-aa369c8e31bc","year":null},{"cited_arxiv_id":"","doi":"10.24963/kr.2024/76","is_internal_anchor":false,"ref_index":3,"title":"Michael , date =","work_id":"ad700027-3d8b-4514-9eb9-3bbef7015cd9","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"and Monet, Mikael and Pérez, Jorge and Reutter, Juan and Silva, Juan Pablo , date =","work_id":"83c78b13-4a58-423c-ae56-96abd5247e5d","year":null},{"cited_arxiv_id":"","doi":"10.1109/icpr56361.2022.9956203","is_internal_anchor":false,"ref_index":5,"title":"Going Beyond Accuracy: Interpretability Metrics for CNN Representations of Physiological Signals , shorttitle =","work_id":"30810c46-a407-4245-b6d7-61f9288984fb","year":2022}],"snapshot_sha256":"4304f3b2b418b91b5b4fa6050954432d65d90bc97b5845dcc5e44f72a398fadd"},"source":{"id":"2605.13282","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:37:18.570924Z","id":"92213afd-a4ef-4695-af23-db0ff711621c","model_set":{"reader":"grok-4.3"},"one_line_summary":"A differentiable neural model recovers ground-truth lifted action schemas from state traces by jointly learning schemas and inferring unobserved action arguments.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A differentiable neural network learns lifted action schemas from fully observed state traces by inferring unobserved action arguments from state changes.","strongest_claim":"Our approach yields a robust differentiable component that can then be integrated into larger neuro-symbolic models. We evaluate the architecture on various planning domains, where the learned lifted action schemas must recover the ground-truth structure.","weakest_assumption":"The assumption that states are fully observed as sets of atoms and that action arguments can be uniquely recovered from observed state changes without additional supervision or ambiguity."}},"verdict_id":"92213afd-a4ef-4695-af23-db0ff711621c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b08975c5df11c9df6c0e778a89d34aedc87d05b14bc0e7d99b1b47babe3c22b4","target":"record","created_at":"2026-05-18T02:44:49Z","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":"67bee74cca35e230c624dc64a60ac3ecc01d7b2d81d14a9f828837beef478ebe","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T09:59:49Z","title_canon_sha256":"5b4754684cfd0aa5dccfe9699372d0df6d6d27c9a246cd57e9c1b91fd3a8ddad"},"schema_version":"1.0","source":{"id":"2605.13282","kind":"arxiv","version":1}},"canonical_sha256":"3b2f4750f47aec47f79bb72a69db1e75f16207df175fe0337f86a40562b22ae8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b2f4750f47aec47f79bb72a69db1e75f16207df175fe0337f86a40562b22ae8","first_computed_at":"2026-05-18T02:44:49.186519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:49.186519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aFmAR1ifO4ZVKKkh6i43L6xD+vuBzgL5VgV1Db/d8d+bdKr/8SgM2FIqVyQezs7io65yoABGpfE6ozDT/0f9Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:49.186943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b08975c5df11c9df6c0e778a89d34aedc87d05b14bc0e7d99b1b47babe3c22b4","sha256:4372c06dd6163b95aa063aa521e59b3a7f23b923626b66aa851844fb50f43d25"],"state_sha256":"c78f7269b8bb8cb388cd46c849f03e6946573195d2c5f8b773745f9c549b6342"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bZLdT7nTDLoYW1jFO8XPl61+rpFVQwuLqn6/VJo7exo+iHBLjnJSTtgkMYRHlzElWSIoYHfuOnSKcr5C9rglCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:20:12.091762Z","bundle_sha256":"0d65cbba2fd9c8f6312486dfcf0fcf363934088854ad29a3d10dd185a4d6c967"}}