{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5VQMO4GKOCHS6PHQ7OP2CTYK25","short_pith_number":"pith:5VQMO4GK","canonical_record":{"source":{"id":"2605.18556","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-18T15:37:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3956676b8e22251445faf8519ce1a49f17f03cd3b9210e312889cf332d0435b","abstract_canon_sha256":"fc10c19e0e18429e4c5c44ddb1eb91a0bf6f14e525ccdf78f5cad1cce73a8f8b"},"schema_version":"1.0"},"canonical_sha256":"ed60c770ca708f2f3cf0fb9fa14f0ad7524f4d282735e20304e1f284e0355a7a","source":{"kind":"arxiv","id":"2605.18556","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18556","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18556v1","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18556","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"5VQMO4GKOCHS","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"5VQMO4GKOCHS6PHQ","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"5VQMO4GK","created_at":"2026-05-20T00:06:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5VQMO4GKOCHS6PHQ7OP2CTYK25","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18556","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-18T15:37:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3956676b8e22251445faf8519ce1a49f17f03cd3b9210e312889cf332d0435b","abstract_canon_sha256":"fc10c19e0e18429e4c5c44ddb1eb91a0bf6f14e525ccdf78f5cad1cce73a8f8b"},"schema_version":"1.0"},"canonical_sha256":"ed60c770ca708f2f3cf0fb9fa14f0ad7524f4d282735e20304e1f284e0355a7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:07.567801Z","signature_b64":"jGtP0bKxxroj7VPHfRa6RwtVM39J/zESA4LW9Q85qekZDsqqHhAtc4gKdK1x6PqifuMKYeSEyC/9gwjITVRdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed60c770ca708f2f3cf0fb9fa14f0ad7524f4d282735e20304e1f284e0355a7a","last_reissued_at":"2026-05-20T00:06:07.567002Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:07.567002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18556","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":"2026-05-20T00:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OYxc6u27pZR/uFikuk+LG0si9oO8csK6F6PlaBf70NZkAoJZzb9iR3u0z3chjuHl9u1senXITXiRSJsNBpxdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T09:01:06.518025Z"},"content_sha256":"3002f6449bdfe92dc6e094236446d8b20d6907f631a49154bf1133fd75974e64","schema_version":"1.0","event_id":"sha256:3002f6449bdfe92dc6e094236446d8b20d6907f631a49154bf1133fd75974e64"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5VQMO4GKOCHS6PHQ7OP2CTYK25","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Key-Gram: Extensible World Knowledge for Embodied Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Botao Ren, Jingjing Fan, Siyuan Li, Zhidong Deng","submitted_at":"2026-05-18T15:37:02Z","abstract_excerpt":"Embodied control increasingly requires models to follow compositional language instructions while reasoning over dynamic visual states. However, current vision-language-action policies and world-action models often couple linguistic knowledge with visual computation in a shared backbone or conditioning pathway, leading to modality competition and making knowledge extension dependent on backbone updates. In this paper, we introduce Key-Gram, a conditional-memory framework that separates language-derived world knowledge from visual-state reasoning for embodied control. At its core is a memory mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18556","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/2605.18556/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.375941Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9793cf20da25b85e4c78927f56553aa44307557c012bd7e679778bd3a06c1500"},"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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"23sC0K7IrU100jcSxs+A5BTfvPU2YLReWuAfq5zPIdlo1x5+0th0VssHggSf90BpIIXawE4Nv9OkWL8yd2oTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T09:01:06.518424Z"},"content_sha256":"43faf6966d303d15d8165c9b598fdbaff31613854daf41da3810096a39a7dc62","schema_version":"1.0","event_id":"sha256:43faf6966d303d15d8165c9b598fdbaff31613854daf41da3810096a39a7dc62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5VQMO4GKOCHS6PHQ7OP2CTYK25/bundle.json","state_url":"https://pith.science/pith/5VQMO4GKOCHS6PHQ7OP2CTYK25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5VQMO4GKOCHS6PHQ7OP2CTYK25/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":"2026-06-04T09:01:06Z","links":{"resolver":"https://pith.science/pith/5VQMO4GKOCHS6PHQ7OP2CTYK25","bundle":"https://pith.science/pith/5VQMO4GKOCHS6PHQ7OP2CTYK25/bundle.json","state":"https://pith.science/pith/5VQMO4GKOCHS6PHQ7OP2CTYK25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5VQMO4GKOCHS6PHQ7OP2CTYK25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5VQMO4GKOCHS6PHQ7OP2CTYK25","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":"fc10c19e0e18429e4c5c44ddb1eb91a0bf6f14e525ccdf78f5cad1cce73a8f8b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-18T15:37:02Z","title_canon_sha256":"e3956676b8e22251445faf8519ce1a49f17f03cd3b9210e312889cf332d0435b"},"schema_version":"1.0","source":{"id":"2605.18556","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18556","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18556v1","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18556","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"5VQMO4GKOCHS","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"5VQMO4GKOCHS6PHQ","created_at":"2026-05-20T00:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"5VQMO4GK","created_at":"2026-05-20T00:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:43faf6966d303d15d8165c9b598fdbaff31613854daf41da3810096a39a7dc62","target":"graph","created_at":"2026-05-20T00:06:07Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.375941Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18556/integrity.json","findings":[],"snapshot_sha256":"9793cf20da25b85e4c78927f56553aa44307557c012bd7e679778bd3a06c1500","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embodied control increasingly requires models to follow compositional language instructions while reasoning over dynamic visual states. However, current vision-language-action policies and world-action models often couple linguistic knowledge with visual computation in a shared backbone or conditioning pathway, leading to modality competition and making knowledge extension dependent on backbone updates. In this paper, we introduce Key-Gram, a conditional-memory framework that separates language-derived world knowledge from visual-state reasoning for embodied control. At its core is a memory mo","authors_text":"Botao Ren, Jingjing Fan, Siyuan Li, Zhidong Deng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-18T15:37:02Z","title":"Key-Gram: Extensible World Knowledge for Embodied Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18556","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3002f6449bdfe92dc6e094236446d8b20d6907f631a49154bf1133fd75974e64","target":"record","created_at":"2026-05-20T00:06:07Z","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":"fc10c19e0e18429e4c5c44ddb1eb91a0bf6f14e525ccdf78f5cad1cce73a8f8b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-18T15:37:02Z","title_canon_sha256":"e3956676b8e22251445faf8519ce1a49f17f03cd3b9210e312889cf332d0435b"},"schema_version":"1.0","source":{"id":"2605.18556","kind":"arxiv","version":1}},"canonical_sha256":"ed60c770ca708f2f3cf0fb9fa14f0ad7524f4d282735e20304e1f284e0355a7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed60c770ca708f2f3cf0fb9fa14f0ad7524f4d282735e20304e1f284e0355a7a","first_computed_at":"2026-05-20T00:06:07.567002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:07.567002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jGtP0bKxxroj7VPHfRa6RwtVM39J/zESA4LW9Q85qekZDsqqHhAtc4gKdK1x6PqifuMKYeSEyC/9gwjITVRdAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:07.567801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18556","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3002f6449bdfe92dc6e094236446d8b20d6907f631a49154bf1133fd75974e64","sha256:43faf6966d303d15d8165c9b598fdbaff31613854daf41da3810096a39a7dc62"],"state_sha256":"a9bdac50aab5e33ad946f14b4ece1327ddfbddc373730a86a99b67b6220db378"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R7gcmlWloTPzzfqhmfBzKro0CGNRltcqO5/6uDqnfDb9C849av+Oub0Au+IIqiwAXFTrI3RbJE2Woh2L0qXBCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T09:01:06.520538Z","bundle_sha256":"028e32ffc839741de228f93f229e1747f3dc15cb7b613d6fe6c038bccd37954e"}}