{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OEIG65K5X4NPJAEATSOBAJOPIW","short_pith_number":"pith:OEIG65K5","canonical_record":{"source":{"id":"2412.10410","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-07T05:47:49Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"2120c7d2244c2e7f0b5bba763e9ed817738dabb7f92fdbce1c565df4801fea08","abstract_canon_sha256":"78cb403620b271cec3e369d9d5cd0ffaee90a878f9d7ba586907e9b6ca8cb05c"},"schema_version":"1.0"},"canonical_sha256":"71106f755dbf1af480809c9c1025cf459cf6b99a73323270e03e38583b635f65","source":{"kind":"arxiv","id":"2412.10410","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10410","created_at":"2026-07-05T09:49:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10410v1","created_at":"2026-07-05T09:49:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10410","created_at":"2026-07-05T09:49:15Z"},{"alias_kind":"pith_short_12","alias_value":"OEIG65K5X4NP","created_at":"2026-07-05T09:49:15Z"},{"alias_kind":"pith_short_16","alias_value":"OEIG65K5X4NPJAEA","created_at":"2026-07-05T09:49:15Z"},{"alias_kind":"pith_short_8","alias_value":"OEIG65K5","created_at":"2026-07-05T09:49:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OEIG65K5X4NPJAEATSOBAJOPIW","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10410","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-07T05:47:49Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"2120c7d2244c2e7f0b5bba763e9ed817738dabb7f92fdbce1c565df4801fea08","abstract_canon_sha256":"78cb403620b271cec3e369d9d5cd0ffaee90a878f9d7ba586907e9b6ca8cb05c"},"schema_version":"1.0"},"canonical_sha256":"71106f755dbf1af480809c9c1025cf459cf6b99a73323270e03e38583b635f65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:15.598881Z","signature_b64":"kPj0gSHQ4woOb0EA+GxEcVeyuJ953c72i5FZRpAvFXJvg+8RauVXoWyzlXj1loKsWh9Gm3dPJtZz2ARo/or3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71106f755dbf1af480809c9c1025cf459cf6b99a73323270e03e38583b635f65","last_reissued_at":"2026-07-05T09:49:15.598458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:15.598458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10410","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":"2026-07-05T09:49:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nm0syKAcrlKEp4bRXEFC7qP7N7ejyu+Xer0QNTuau/ga05aelGlc2kTOdq2KFaX06EIhBKFGX/ul5rGE9cz0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T16:52:24.065279Z"},"content_sha256":"408a798c58e58abdaec7c06af0562609c7a330d806049ce0fdfeb6c513539380","schema_version":"1.0","event_id":"sha256:408a798c58e58abdaec7c06af0562609c7a330d806049ce0fdfeb6c513539380"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OEIG65K5X4NPJAEATSOBAJOPIW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Anji Liu, Bowei Zhang, Haowei Lin, Shaofei Cai, Xiaojian Ma, Yitao Liang, Zihao Wang","submitted_at":"2024-12-07T05:47:49Z","abstract_excerpt":"Developing agents that can follow multimodal instructions remains a fundamental challenge in robotics and AI. Although large-scale pre-training on unlabeled datasets (no language instruction) has enabled agents to learn diverse behaviors, these agents often struggle with following instructions. While augmenting the dataset with instruction labels can mitigate this issue, acquiring such high-quality annotations at scale is impractical. To address this issue, we frame the problem as a semi-supervised learning task and introduce GROOT-2, a multimodal instructable agent trained using a novel appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10410","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/2412.10410/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":"2026-07-05T09:49:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6UQ7ToTQbmLKSy6WPHDRbPo+dwBVhdge3414PWdm3oIWKZCk/ANHYqmCFna212h4Mn5oBZXyCT68MAjYB6l2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T16:52:24.066106Z"},"content_sha256":"51b9f0309a9248c1adc32b102cf6382ce34da64a72463477dedab3f027d1cbf5","schema_version":"1.0","event_id":"sha256:51b9f0309a9248c1adc32b102cf6382ce34da64a72463477dedab3f027d1cbf5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OEIG65K5X4NPJAEATSOBAJOPIW/bundle.json","state_url":"https://pith.science/pith/OEIG65K5X4NPJAEATSOBAJOPIW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OEIG65K5X4NPJAEATSOBAJOPIW/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":"2026-08-12T16:52:24Z","links":{"resolver":"https://pith.science/pith/OEIG65K5X4NPJAEATSOBAJOPIW","bundle":"https://pith.science/pith/OEIG65K5X4NPJAEATSOBAJOPIW/bundle.json","state":"https://pith.science/pith/OEIG65K5X4NPJAEATSOBAJOPIW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OEIG65K5X4NPJAEATSOBAJOPIW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OEIG65K5X4NPJAEATSOBAJOPIW","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":"78cb403620b271cec3e369d9d5cd0ffaee90a878f9d7ba586907e9b6ca8cb05c","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-07T05:47:49Z","title_canon_sha256":"2120c7d2244c2e7f0b5bba763e9ed817738dabb7f92fdbce1c565df4801fea08"},"schema_version":"1.0","source":{"id":"2412.10410","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10410","created_at":"2026-07-05T09:49:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10410v1","created_at":"2026-07-05T09:49:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10410","created_at":"2026-07-05T09:49:15Z"},{"alias_kind":"pith_short_12","alias_value":"OEIG65K5X4NP","created_at":"2026-07-05T09:49:15Z"},{"alias_kind":"pith_short_16","alias_value":"OEIG65K5X4NPJAEA","created_at":"2026-07-05T09:49:15Z"},{"alias_kind":"pith_short_8","alias_value":"OEIG65K5","created_at":"2026-07-05T09:49:15Z"}],"graph_snapshots":[{"event_id":"sha256:51b9f0309a9248c1adc32b102cf6382ce34da64a72463477dedab3f027d1cbf5","target":"graph","created_at":"2026-07-05T09:49:15Z","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/2412.10410/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing agents that can follow multimodal instructions remains a fundamental challenge in robotics and AI. Although large-scale pre-training on unlabeled datasets (no language instruction) has enabled agents to learn diverse behaviors, these agents often struggle with following instructions. While augmenting the dataset with instruction labels can mitigate this issue, acquiring such high-quality annotations at scale is impractical. To address this issue, we frame the problem as a semi-supervised learning task and introduce GROOT-2, a multimodal instructable agent trained using a novel appro","authors_text":"Anji Liu, Bowei Zhang, Haowei Lin, Shaofei Cai, Xiaojian Ma, Yitao Liang, Zihao Wang","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-07T05:47:49Z","title":"GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10410","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":"sha256:408a798c58e58abdaec7c06af0562609c7a330d806049ce0fdfeb6c513539380","target":"record","created_at":"2026-07-05T09:49:15Z","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":"78cb403620b271cec3e369d9d5cd0ffaee90a878f9d7ba586907e9b6ca8cb05c","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-07T05:47:49Z","title_canon_sha256":"2120c7d2244c2e7f0b5bba763e9ed817738dabb7f92fdbce1c565df4801fea08"},"schema_version":"1.0","source":{"id":"2412.10410","kind":"arxiv","version":1}},"canonical_sha256":"71106f755dbf1af480809c9c1025cf459cf6b99a73323270e03e38583b635f65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71106f755dbf1af480809c9c1025cf459cf6b99a73323270e03e38583b635f65","first_computed_at":"2026-07-05T09:49:15.598458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:15.598458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kPj0gSHQ4woOb0EA+GxEcVeyuJ953c72i5FZRpAvFXJvg+8RauVXoWyzlXj1loKsWh9Gm3dPJtZz2ARo/or3CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:15.598881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10410","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:408a798c58e58abdaec7c06af0562609c7a330d806049ce0fdfeb6c513539380","sha256:51b9f0309a9248c1adc32b102cf6382ce34da64a72463477dedab3f027d1cbf5"],"state_sha256":"9432e4dbd6ed71ba4947a1a5d44b8bf53fc05aee9776fdd36b593a77577f6640"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0eSrzPxI608aslD3aV7jUMpGg8lqJAwG1AeCrcSI9ghg53wK7SNArl9G7UIBW/MvN/CZ3fW64KmCoMZWNg+EAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T16:52:24.074451Z","bundle_sha256":"446d8fd71bf3b5fa3ca45727106e7eefd65019385f644351f31c6c6d5ab505c0"}}