{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3DCBNSTCH4KPGPNRPZYGOWJ7XB","short_pith_number":"pith:3DCBNSTC","schema_version":"1.0","canonical_sha256":"d8c416ca623f14f33db17e7067593fb8409578384a93ee9d7c182c18d561f925","source":{"kind":"arxiv","id":"2409.14908","version":2},"attestation_state":"computed","paper":{"title":"KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bo Yu, Junzhe Zhao, Sai Hou, Shuai Liang, Wenhao Sun, Xing Hu, Yiming Gan, Yinhe Han, Zixuan Wang","submitted_at":"2024-09-23T11:02:46Z","abstract_excerpt":"Embodied AI agents responsible for executing interconnected, long-sequence household tasks often face difficulties with in-context memory, leading to inefficiencies and errors in task execution. To address this issue, we introduce KARMA, an innovative memory system that integrates long-term and short-term memory modules, enhancing large language models (LLMs) for planning in embodied agents through memory-augmented prompting. KARMA distinguishes between long-term and short-term memory, with long-term memory capturing comprehensive 3D scene graphs as representations of the environment, while sh"},"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":"2409.14908","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-23T11:02:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"63226c31389e4e200d23753fccdb72b6c6d95b7dc6261885d278d455e3130f76","abstract_canon_sha256":"1b8e955c1852b3409a697bcbed7f173bf12afbfb77b70677dbb62bb23a2b6395"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:28.948630Z","signature_b64":"54EzNrtPotHI2k7jgsmHBcsSKquRwN5Qcm8CMaKsSdh5w40bDcneNj7m7f224sSsx2S/YwfgXzkQx3ew5UdQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8c416ca623f14f33db17e7067593fb8409578384a93ee9d7c182c18d561f925","last_reissued_at":"2026-07-05T10:36:28.948134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:28.948134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bo Yu, Junzhe Zhao, Sai Hou, Shuai Liang, Wenhao Sun, Xing Hu, Yiming Gan, Yinhe Han, Zixuan Wang","submitted_at":"2024-09-23T11:02:46Z","abstract_excerpt":"Embodied AI agents responsible for executing interconnected, long-sequence household tasks often face difficulties with in-context memory, leading to inefficiencies and errors in task execution. To address this issue, we introduce KARMA, an innovative memory system that integrates long-term and short-term memory modules, enhancing large language models (LLMs) for planning in embodied agents through memory-augmented prompting. KARMA distinguishes between long-term and short-term memory, with long-term memory capturing comprehensive 3D scene graphs as representations of the environment, while sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14908","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/2409.14908/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":"2409.14908","created_at":"2026-07-05T10:36:28.948193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14908v2","created_at":"2026-07-05T10:36:28.948193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14908","created_at":"2026-07-05T10:36:28.948193+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DCBNSTCH4KP","created_at":"2026-07-05T10:36:28.948193+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DCBNSTCH4KPGPNR","created_at":"2026-07-05T10:36:28.948193+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DCBNSTC","created_at":"2026-07-05T10:36:28.948193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18144","citing_title":"Memory as a Wasting Asset: Pricing Flash Endurance for Embodied Agents, and the Limits of Doing So","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":273,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DCBNSTCH4KPGPNRPZYGOWJ7XB","json":"https://pith.science/pith/3DCBNSTCH4KPGPNRPZYGOWJ7XB.json","graph_json":"https://pith.science/api/pith-number/3DCBNSTCH4KPGPNRPZYGOWJ7XB/graph.json","events_json":"https://pith.science/api/pith-number/3DCBNSTCH4KPGPNRPZYGOWJ7XB/events.json","paper":"https://pith.science/paper/3DCBNSTC"},"agent_actions":{"view_html":"https://pith.science/pith/3DCBNSTCH4KPGPNRPZYGOWJ7XB","download_json":"https://pith.science/pith/3DCBNSTCH4KPGPNRPZYGOWJ7XB.json","view_paper":"https://pith.science/paper/3DCBNSTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14908&json=true","fetch_graph":"https://pith.science/api/pith-number/3DCBNSTCH4KPGPNRPZYGOWJ7XB/graph.json","fetch_events":"https://pith.science/api/pith-number/3DCBNSTCH4KPGPNRPZYGOWJ7XB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DCBNSTCH4KPGPNRPZYGOWJ7XB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DCBNSTCH4KPGPNRPZYGOWJ7XB/action/storage_attestation","attest_author":"https://pith.science/pith/3DCBNSTCH4KPGPNRPZYGOWJ7XB/action/author_attestation","sign_citation":"https://pith.science/pith/3DCBNSTCH4KPGPNRPZYGOWJ7XB/action/citation_signature","submit_replication":"https://pith.science/pith/3DCBNSTCH4KPGPNRPZYGOWJ7XB/action/replication_record"}},"created_at":"2026-07-05T10:36:28.948193+00:00","updated_at":"2026-07-05T10:36:28.948193+00:00"}