{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DRCDPD46QJKQ263GWJWI4GKIWW","short_pith_number":"pith:DRCDPD46","canonical_record":{"source":{"id":"2410.07166","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:59:00Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"02ccadb96dc33cc6621cfede8d70b4ddee806c999f2828a852d7ded04c5c041b","abstract_canon_sha256":"7c4400462621adda5ce586eebda37968ffe20fb67b0e09bc0b1d9a608c43f350"},"schema_version":"1.0"},"canonical_sha256":"1c44378f9e82550d7b66b26c8e1948b5bea77cddb58c28a635a1b01b61ef5465","source":{"kind":"arxiv","id":"2410.07166","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07166","created_at":"2026-07-05T10:02:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07166v3","created_at":"2026-07-05T10:02:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07166","created_at":"2026-07-05T10:02:53Z"},{"alias_kind":"pith_short_12","alias_value":"DRCDPD46QJKQ","created_at":"2026-07-05T10:02:53Z"},{"alias_kind":"pith_short_16","alias_value":"DRCDPD46QJKQ263G","created_at":"2026-07-05T10:02:53Z"},{"alias_kind":"pith_short_8","alias_value":"DRCDPD46","created_at":"2026-07-05T10:02:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DRCDPD46QJKQ263GWJWI4GKIWW","target":"record","payload":{"canonical_record":{"source":{"id":"2410.07166","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:59:00Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"02ccadb96dc33cc6621cfede8d70b4ddee806c999f2828a852d7ded04c5c041b","abstract_canon_sha256":"7c4400462621adda5ce586eebda37968ffe20fb67b0e09bc0b1d9a608c43f350"},"schema_version":"1.0"},"canonical_sha256":"1c44378f9e82550d7b66b26c8e1948b5bea77cddb58c28a635a1b01b61ef5465","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:53.096464Z","signature_b64":"WAa8+usLTV/ErjLAiVGc1+zoUvXwZhBSRzGkVA04Mvv+S+G7k0l3nqT42TFlPa52zqzAjdaq28IBRsjmBp/3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c44378f9e82550d7b66b26c8e1948b5bea77cddb58c28a635a1b01b61ef5465","last_reissued_at":"2026-07-05T10:02:53.096016Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:53.096016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.07166","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IwsGZjxS25vRaFDN4wBYjJ+dbLeMF2aDcJGMl3LkX1fphShDQBO7kcKehVO5eJw67P4fw87ojFWmp3Qr0Es0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:48:07.158392Z"},"content_sha256":"9833f4628c40ec1c387f6d1e179521e207acb519457d0d39e84ecb763311c045","schema_version":"1.0","event_id":"sha256:9833f4628c40ec1c387f6d1e179521e207acb519457d0d39e84ecb763311c045"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DRCDPD46QJKQ263GWJWI4GKIWW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CL","authors_text":"Cem Gokmen, Jiajun Wu, Jiayuan Mao, Kangrui Wang, Li Erran Li, Li Fei-Fei, Manling Li, Percy Liang, Qineng Wang, Ruohan Zhang, Sanjana Srivastava, Shiyu Zhao, Tony Lee, Weiyu Liu, Yu Zhou","submitted_at":"2024-10-09T17:59:00Z","abstract_excerpt":"We aim to evaluate Large Language Models (LLMs) for embodied decision making. While a significant body of work has been leveraging LLMs for decision making in embodied environments, we still lack a systematic understanding of their performance because they are usually applied in different domains, for different purposes, and built based on different inputs and outputs. Furthermore, existing evaluations tend to rely solely on a final success rate, making it difficult to pinpoint what ability is missing in LLMs and where the problem lies, which in turn blocks embodied agents from leveraging LLMs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07166","kind":"arxiv","version":3},"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/2410.07166/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GmrM1zv0IMQHWk2lpjysSCFpRC+13FDgdzgqXCJueIMlVH4DxPakdA4m0Rj74TXWGoH3aMwJHgvoj4lRQKFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:48:07.158769Z"},"content_sha256":"e7911c0ac8b4bdf3a36cd24577d4bd96fc26b78bc488a31ca6db5ae7140b073f","schema_version":"1.0","event_id":"sha256:e7911c0ac8b4bdf3a36cd24577d4bd96fc26b78bc488a31ca6db5ae7140b073f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DRCDPD46QJKQ263GWJWI4GKIWW/bundle.json","state_url":"https://pith.science/pith/DRCDPD46QJKQ263GWJWI4GKIWW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DRCDPD46QJKQ263GWJWI4GKIWW/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":"2026-07-06T10:48:07Z","links":{"resolver":"https://pith.science/pith/DRCDPD46QJKQ263GWJWI4GKIWW","bundle":"https://pith.science/pith/DRCDPD46QJKQ263GWJWI4GKIWW/bundle.json","state":"https://pith.science/pith/DRCDPD46QJKQ263GWJWI4GKIWW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DRCDPD46QJKQ263GWJWI4GKIWW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DRCDPD46QJKQ263GWJWI4GKIWW","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":"7c4400462621adda5ce586eebda37968ffe20fb67b0e09bc0b1d9a608c43f350","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:59:00Z","title_canon_sha256":"02ccadb96dc33cc6621cfede8d70b4ddee806c999f2828a852d7ded04c5c041b"},"schema_version":"1.0","source":{"id":"2410.07166","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07166","created_at":"2026-07-05T10:02:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07166v3","created_at":"2026-07-05T10:02:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07166","created_at":"2026-07-05T10:02:53Z"},{"alias_kind":"pith_short_12","alias_value":"DRCDPD46QJKQ","created_at":"2026-07-05T10:02:53Z"},{"alias_kind":"pith_short_16","alias_value":"DRCDPD46QJKQ263G","created_at":"2026-07-05T10:02:53Z"},{"alias_kind":"pith_short_8","alias_value":"DRCDPD46","created_at":"2026-07-05T10:02:53Z"}],"graph_snapshots":[{"event_id":"sha256:e7911c0ac8b4bdf3a36cd24577d4bd96fc26b78bc488a31ca6db5ae7140b073f","target":"graph","created_at":"2026-07-05T10:02:53Z","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":[],"endpoint":"/pith/2410.07166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We aim to evaluate Large Language Models (LLMs) for embodied decision making. While a significant body of work has been leveraging LLMs for decision making in embodied environments, we still lack a systematic understanding of their performance because they are usually applied in different domains, for different purposes, and built based on different inputs and outputs. Furthermore, existing evaluations tend to rely solely on a final success rate, making it difficult to pinpoint what ability is missing in LLMs and where the problem lies, which in turn blocks embodied agents from leveraging LLMs","authors_text":"Cem Gokmen, Jiajun Wu, Jiayuan Mao, Kangrui Wang, Li Erran Li, Li Fei-Fei, Manling Li, Percy Liang, Qineng Wang, Ruohan Zhang, Sanjana Srivastava, Shiyu Zhao, Tony Lee, Weiyu Liu, Yu Zhou","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:59:00Z","title":"Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07166","kind":"arxiv","version":3},"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":"sha256:9833f4628c40ec1c387f6d1e179521e207acb519457d0d39e84ecb763311c045","target":"record","created_at":"2026-07-05T10:02:53Z","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":"7c4400462621adda5ce586eebda37968ffe20fb67b0e09bc0b1d9a608c43f350","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:59:00Z","title_canon_sha256":"02ccadb96dc33cc6621cfede8d70b4ddee806c999f2828a852d7ded04c5c041b"},"schema_version":"1.0","source":{"id":"2410.07166","kind":"arxiv","version":3}},"canonical_sha256":"1c44378f9e82550d7b66b26c8e1948b5bea77cddb58c28a635a1b01b61ef5465","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c44378f9e82550d7b66b26c8e1948b5bea77cddb58c28a635a1b01b61ef5465","first_computed_at":"2026-07-05T10:02:53.096016Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:53.096016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WAa8+usLTV/ErjLAiVGc1+zoUvXwZhBSRzGkVA04Mvv+S+G7k0l3nqT42TFlPa52zqzAjdaq28IBRsjmBp/3DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:53.096464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07166","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9833f4628c40ec1c387f6d1e179521e207acb519457d0d39e84ecb763311c045","sha256:e7911c0ac8b4bdf3a36cd24577d4bd96fc26b78bc488a31ca6db5ae7140b073f"],"state_sha256":"8745370f0e4d469e68cf393db0e0375126d6242f78137e9ed6e570cd926fb6ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YRLn+oVUlUad2CBh9lDeRDt8omdx472S1HMKkUhoypjkx4bMpspb/MIQQ9lbUW9F691wIqaZo04SIzNPp0n2Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:48:07.160756Z","bundle_sha256":"7df80296ef96d5cac4d1966698ed806f62aab5b899ed3b5b35ef0f05d48877f7"}}