{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KK5YAO5GQ7TYDNCULMR4KTM2IU","short_pith_number":"pith:KK5YAO5G","canonical_record":{"source":{"id":"2605.08732","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-09T06:36:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dd19812f399afe97cf4ee42d5389ddd05896dc58cd2f7e0cfbd9337128612137","abstract_canon_sha256":"057bb88f7facbae970b49d2f09cfa2ff1f4a83b71c8e6b9bc34ef0ea6da34c82"},"schema_version":"1.0"},"canonical_sha256":"52bb803ba687e781b4545b23c54d9a450e28a7cf972bee8654287832638ae294","source":{"kind":"arxiv","id":"2605.08732","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08732","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08732v2","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08732","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"KK5YAO5GQ7TY","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"KK5YAO5GQ7TYDNCU","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"KK5YAO5G","created_at":"2026-06-08T01:04:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KK5YAO5GQ7TYDNCULMR4KTM2IU","target":"record","payload":{"canonical_record":{"source":{"id":"2605.08732","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-09T06:36:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dd19812f399afe97cf4ee42d5389ddd05896dc58cd2f7e0cfbd9337128612137","abstract_canon_sha256":"057bb88f7facbae970b49d2f09cfa2ff1f4a83b71c8e6b9bc34ef0ea6da34c82"},"schema_version":"1.0"},"canonical_sha256":"52bb803ba687e781b4545b23c54d9a450e28a7cf972bee8654287832638ae294","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:07.114910Z","signature_b64":"uyDBCTpgZ5srrN2yqTh86RunS9ON2dnBi55o+WsH3iYSSNsfpZ+ntHIhwzrgo3rbDsEA+703Y02nQUDM8UZgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52bb803ba687e781b4545b23c54d9a450e28a7cf972bee8654287832638ae294","last_reissued_at":"2026-06-08T01:04:07.114185Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:07.114185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.08732","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":"2026-06-08T01:04:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QqR40lREJhc0Yq7dGNpleUMJqs+a21WaO0l7o9TTwfedtJc5+XZ8Qafbb1Uyk4r4MMPVLHC3z+nLhjsENDZuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T00:25:49.777849Z"},"content_sha256":"dd3e38a89ddd89cd49478c67e7deea05f51a377f4bd2ba483185667e67321473","schema_version":"1.0","event_id":"sha256:dd3e38a89ddd89cd49478c67e7deea05f51a377f4bd2ba483185667e67321473"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KK5YAO5GQ7TYDNCULMR4KTM2IU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Geometry Beyond Search: Amortizing Planning in World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"In a pretrained world model whose latent space is regularized for smoothness and uniformity, a goal-conditioned inverse dynamics model can replace online search while matching its performance at far lower cost.","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Hoang Nguyen, Xiaohao Xu, Xiaonan Huang","submitted_at":"2026-05-09T06:36:23Z","abstract_excerpt":"Modern vision-based world models can represent observations as compact yet expressive latent manifolds, but fast goal-oriented planning in these spaces remains challenging. This raises a central question: when does a learned representation simplify control, rather than merely enabling prediction? We study this question in a pretrained LeWorldModel, whose latent geometry is regularized for smoothness and uniformity. Our key insight is that, under such geometry, planning can be amortized into a latent inverse-dynamics mapping instead of requiring online search. We therefore replace iterative pla"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Under such geometry, planning can be amortized into a latent inverse-dynamics mapping instead of requiring online search. Empirically, the GC-IDM matches or exceeds CEM in seven of eight environment-protocol settings while reducing per-decision cost by 100-130x.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the smoothness and uniformity regularization already present in the pretrained LeWorldModel is sufficient for a learned inverse-dynamics map to capture the planning structure that would otherwise require online search.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"In regularized latent spaces of world models, planning can be amortized into a goal-conditioned inverse dynamics model that matches CEM performance at 100-130x lower per-decision cost.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"In a pretrained world model whose latent space is regularized for smoothness and uniformity, a goal-conditioned inverse dynamics model can replace online search while matching its performance at far lower cost.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2202f9d84f78fcc559c8dba1494380c6ea42d63b587c5a393101dc099ac46d06"},"source":{"id":"2605.08732","kind":"arxiv","version":2},"verdict":{"id":"dc78a3c9-de34-4366-9a46-5359115c9a10","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T01:48:27.746074Z","strongest_claim":"Under such geometry, planning can be amortized into a latent inverse-dynamics mapping instead of requiring online search. Empirically, the GC-IDM matches or exceeds CEM in seven of eight environment-protocol settings while reducing per-decision cost by 100-130x.","one_line_summary":"In regularized latent spaces of world models, planning can be amortized into a goal-conditioned inverse dynamics model that matches CEM performance at 100-130x lower per-decision cost.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the smoothness and uniformity regularization already present in the pretrained LeWorldModel is sufficient for a learned inverse-dynamics map to capture the planning structure that would otherwise require online search.","pith_extraction_headline":"In a pretrained world model whose latent space is regularized for smoothness and uniformity, a goal-conditioned inverse dynamics model can replace online search while matching its performance at far lower cost."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08732/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T09:02:01.944203Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:35:37.212714Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T14:31:17.596485Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:50:48.989575Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"368724d88641112b646f152e62760005e93a14096d22eedd07f290468511c103"},"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":"dc78a3c9-de34-4366-9a46-5359115c9a10"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:04:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m+wgL7vKq5c6N7RQMbJ014WNVSGeHwiCg9cesS4qHuYAr1SPfutssiwv2d/MRBfe77nLh+P0qMoEuSM/YRV6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T00:25:49.778356Z"},"content_sha256":"df2d6e2e27c15549c516392a287df85e230c35c877ff25283bd49161a6b51952","schema_version":"1.0","event_id":"sha256:df2d6e2e27c15549c516392a287df85e230c35c877ff25283bd49161a6b51952"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KK5YAO5GQ7TYDNCULMR4KTM2IU/bundle.json","state_url":"https://pith.science/pith/KK5YAO5GQ7TYDNCULMR4KTM2IU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KK5YAO5GQ7TYDNCULMR4KTM2IU/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":"2026-06-09T00:25:49Z","links":{"resolver":"https://pith.science/pith/KK5YAO5GQ7TYDNCULMR4KTM2IU","bundle":"https://pith.science/pith/KK5YAO5GQ7TYDNCULMR4KTM2IU/bundle.json","state":"https://pith.science/pith/KK5YAO5GQ7TYDNCULMR4KTM2IU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KK5YAO5GQ7TYDNCULMR4KTM2IU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KK5YAO5GQ7TYDNCULMR4KTM2IU","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":"057bb88f7facbae970b49d2f09cfa2ff1f4a83b71c8e6b9bc34ef0ea6da34c82","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-09T06:36:23Z","title_canon_sha256":"dd19812f399afe97cf4ee42d5389ddd05896dc58cd2f7e0cfbd9337128612137"},"schema_version":"1.0","source":{"id":"2605.08732","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08732","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08732v2","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08732","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"KK5YAO5GQ7TY","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"KK5YAO5GQ7TYDNCU","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"KK5YAO5G","created_at":"2026-06-08T01:04:07Z"}],"graph_snapshots":[{"event_id":"sha256:df2d6e2e27c15549c516392a287df85e230c35c877ff25283bd49161a6b51952","target":"graph","created_at":"2026-06-08T01:04:07Z","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":"Under such geometry, planning can be amortized into a latent inverse-dynamics mapping instead of requiring online search. Empirically, the GC-IDM matches or exceeds CEM in seven of eight environment-protocol settings while reducing per-decision cost by 100-130x."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the smoothness and uniformity regularization already present in the pretrained LeWorldModel is sufficient for a learned inverse-dynamics map to capture the planning structure that would otherwise require online search."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"In regularized latent spaces of world models, planning can be amortized into a goal-conditioned inverse dynamics model that matches CEM performance at 100-130x lower per-decision cost."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"In a pretrained world model whose latent space is regularized for smoothness and uniformity, a goal-conditioned inverse dynamics model can replace online search while matching its performance at far lower cost."}],"snapshot_sha256":"2202f9d84f78fcc559c8dba1494380c6ea42d63b587c5a393101dc099ac46d06"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T09:02:01.944203Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T22:35:37.212714Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T14:31:17.596485Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T10:50:48.989575Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.08732/integrity.json","findings":[],"snapshot_sha256":"368724d88641112b646f152e62760005e93a14096d22eedd07f290468511c103","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern vision-based world models can represent observations as compact yet expressive latent manifolds, but fast goal-oriented planning in these spaces remains challenging. This raises a central question: when does a learned representation simplify control, rather than merely enabling prediction? We study this question in a pretrained LeWorldModel, whose latent geometry is regularized for smoothness and uniformity. Our key insight is that, under such geometry, planning can be amortized into a latent inverse-dynamics mapping instead of requiring online search. We therefore replace iterative pla","authors_text":"Hoang Nguyen, Xiaohao Xu, Xiaonan Huang","cross_cats":["cs.LG"],"headline":"In a pretrained world model whose latent space is regularized for smoothness and uniformity, a goal-conditioned inverse dynamics model can replace online search while matching its performance at far lower cost.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-09T06:36:23Z","title":"Latent Geometry Beyond Search: Amortizing Planning in World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.08732","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T01:48:27.746074Z","id":"dc78a3c9-de34-4366-9a46-5359115c9a10","model_set":{"reader":"grok-4.3"},"one_line_summary":"In regularized latent spaces of world models, planning can be amortized into a goal-conditioned inverse dynamics model that matches CEM performance at 100-130x lower per-decision cost.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"In a pretrained world model whose latent space is regularized for smoothness and uniformity, a goal-conditioned inverse dynamics model can replace online search while matching its performance at far lower cost.","strongest_claim":"Under such geometry, planning can be amortized into a latent inverse-dynamics mapping instead of requiring online search. Empirically, the GC-IDM matches or exceeds CEM in seven of eight environment-protocol settings while reducing per-decision cost by 100-130x.","weakest_assumption":"That the smoothness and uniformity regularization already present in the pretrained LeWorldModel is sufficient for a learned inverse-dynamics map to capture the planning structure that would otherwise require online search."}},"verdict_id":"dc78a3c9-de34-4366-9a46-5359115c9a10"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dd3e38a89ddd89cd49478c67e7deea05f51a377f4bd2ba483185667e67321473","target":"record","created_at":"2026-06-08T01:04:07Z","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":"057bb88f7facbae970b49d2f09cfa2ff1f4a83b71c8e6b9bc34ef0ea6da34c82","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-09T06:36:23Z","title_canon_sha256":"dd19812f399afe97cf4ee42d5389ddd05896dc58cd2f7e0cfbd9337128612137"},"schema_version":"1.0","source":{"id":"2605.08732","kind":"arxiv","version":2}},"canonical_sha256":"52bb803ba687e781b4545b23c54d9a450e28a7cf972bee8654287832638ae294","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52bb803ba687e781b4545b23c54d9a450e28a7cf972bee8654287832638ae294","first_computed_at":"2026-06-08T01:04:07.114185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:07.114185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uyDBCTpgZ5srrN2yqTh86RunS9ON2dnBi55o+WsH3iYSSNsfpZ+ntHIhwzrgo3rbDsEA+703Y02nQUDM8UZgCQ==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:07.114910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.08732","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd3e38a89ddd89cd49478c67e7deea05f51a377f4bd2ba483185667e67321473","sha256:df2d6e2e27c15549c516392a287df85e230c35c877ff25283bd49161a6b51952"],"state_sha256":"36892cfad43413691fd03371ba19843da8676b6057c752549011dc534413ea1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zkDXk4pNlJL4W2upqWWJjjdGKm1OeaOplJjDzs8g7lIAQQpJNgS88dxk5ZLWezZFZ4eiayQXY/sAavW9q5aHAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T00:25:49.780567Z","bundle_sha256":"629fb14e48ac9e7bf60ea392d7bbdfa2240aa3a53e26d4c4ad5181c82b8b7ef3"}}