{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GA54D4Q2LXA6LZ4S2J3DM56ING","short_pith_number":"pith:GA54D4Q2","canonical_record":{"source":{"id":"2311.16714","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T11:53:56Z","cross_cats_sorted":[],"title_canon_sha256":"5d1e5d35bf2a66dfa8863ee85bf5dffd5f9b2e8fc2cf11a58722ab5058bdb04d","abstract_canon_sha256":"a245d47277a522bf3a653c990b2b1ac984d3ff5fd3864d1cf0d8e2c391f2e665"},"schema_version":"1.0"},"canonical_sha256":"303bc1f21a5dc1e5e792d2763677c869904f4bfddab067192a55e4b9bf758434","source":{"kind":"arxiv","id":"2311.16714","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.16714","created_at":"2026-07-05T08:02:03Z"},{"alias_kind":"arxiv_version","alias_value":"2311.16714v2","created_at":"2026-07-05T08:02:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16714","created_at":"2026-07-05T08:02:03Z"},{"alias_kind":"pith_short_12","alias_value":"GA54D4Q2LXA6","created_at":"2026-07-05T08:02:03Z"},{"alias_kind":"pith_short_16","alias_value":"GA54D4Q2LXA6LZ4S","created_at":"2026-07-05T08:02:03Z"},{"alias_kind":"pith_short_8","alias_value":"GA54D4Q2","created_at":"2026-07-05T08:02:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GA54D4Q2LXA6LZ4S2J3DM56ING","target":"record","payload":{"canonical_record":{"source":{"id":"2311.16714","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T11:53:56Z","cross_cats_sorted":[],"title_canon_sha256":"5d1e5d35bf2a66dfa8863ee85bf5dffd5f9b2e8fc2cf11a58722ab5058bdb04d","abstract_canon_sha256":"a245d47277a522bf3a653c990b2b1ac984d3ff5fd3864d1cf0d8e2c391f2e665"},"schema_version":"1.0"},"canonical_sha256":"303bc1f21a5dc1e5e792d2763677c869904f4bfddab067192a55e4b9bf758434","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:03.160011Z","signature_b64":"jSVMHkfamOX7805BHLwhhAhLDSUz8nqMEgENVmGCdHHeIwwmoaM1YzvMj5L0GiLR2LS17X7Igsw2DebXIZg3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"303bc1f21a5dc1e5e792d2763677c869904f4bfddab067192a55e4b9bf758434","last_reissued_at":"2026-07-05T08:02:03.159612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:03.159612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.16714","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":"2026-07-05T08:02:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xApXh5L7R5K8CkcfbTR506qqbb+AbCAsLZUvQRFUoJuZGMdzbryH4NfUKkXPXUW2zlwsqh3J4IFQLpTAgFJGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:59:23.499583Z"},"content_sha256":"c4d6462dbc70c413a42f6f4774015f26f12cd1f3210d07d67665c5a25d313bee","schema_version":"1.0","event_id":"sha256:c4d6462dbc70c413a42f6f4774015f26f12cd1f3210d07d67665c5a25d313bee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GA54D4Q2LXA6LZ4S2J3DM56ING","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dapeng Tao, Jing Jiang, Kanxue Li, Li Shen, Lusong Li, Tianyi Zhou, Xiaodong He, Yijun Yang, Yuhui Shi","submitted_at":"2023-11-28T11:53:56Z","abstract_excerpt":"While large language models (LLMs) excel in a simulated world of texts, they struggle to interact with the more realistic world without perceptions of other modalities such as visual or audio signals. Although vision-language models (VLMs) integrate LLM modules (1) aligned with static image features, and (2) may possess prior knowledge of world dynamics (as demonstrated in the text world), they have not been trained in an embodied visual world and thus cannot align with its dynamics. On the other hand, training an embodied agent in a noisy visual world without expert guidance is often challeng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16714","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/2311.16714/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":"2026-07-05T08:02:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GjU9Y+435Aftxw1GwYdOK6iQyYgAR7rIsKKB4YLg6Gz91mt+fcJ9t1EppeVLOJx0JyZQ//hEGOtz9Yn+10i1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:59:23.500719Z"},"content_sha256":"5580e69c3d9ade690bb60b55076888f48e16b29f509547bcb34fd28ed713c526","schema_version":"1.0","event_id":"sha256:5580e69c3d9ade690bb60b55076888f48e16b29f509547bcb34fd28ed713c526"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GA54D4Q2LXA6LZ4S2J3DM56ING/bundle.json","state_url":"https://pith.science/pith/GA54D4Q2LXA6LZ4S2J3DM56ING/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GA54D4Q2LXA6LZ4S2J3DM56ING/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":"2026-08-05T03:59:23Z","links":{"resolver":"https://pith.science/pith/GA54D4Q2LXA6LZ4S2J3DM56ING","bundle":"https://pith.science/pith/GA54D4Q2LXA6LZ4S2J3DM56ING/bundle.json","state":"https://pith.science/pith/GA54D4Q2LXA6LZ4S2J3DM56ING/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GA54D4Q2LXA6LZ4S2J3DM56ING/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GA54D4Q2LXA6LZ4S2J3DM56ING","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":"a245d47277a522bf3a653c990b2b1ac984d3ff5fd3864d1cf0d8e2c391f2e665","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T11:53:56Z","title_canon_sha256":"5d1e5d35bf2a66dfa8863ee85bf5dffd5f9b2e8fc2cf11a58722ab5058bdb04d"},"schema_version":"1.0","source":{"id":"2311.16714","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.16714","created_at":"2026-07-05T08:02:03Z"},{"alias_kind":"arxiv_version","alias_value":"2311.16714v2","created_at":"2026-07-05T08:02:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16714","created_at":"2026-07-05T08:02:03Z"},{"alias_kind":"pith_short_12","alias_value":"GA54D4Q2LXA6","created_at":"2026-07-05T08:02:03Z"},{"alias_kind":"pith_short_16","alias_value":"GA54D4Q2LXA6LZ4S","created_at":"2026-07-05T08:02:03Z"},{"alias_kind":"pith_short_8","alias_value":"GA54D4Q2","created_at":"2026-07-05T08:02:03Z"}],"graph_snapshots":[{"event_id":"sha256:5580e69c3d9ade690bb60b55076888f48e16b29f509547bcb34fd28ed713c526","target":"graph","created_at":"2026-07-05T08:02:03Z","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/2311.16714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language models (LLMs) excel in a simulated world of texts, they struggle to interact with the more realistic world without perceptions of other modalities such as visual or audio signals. Although vision-language models (VLMs) integrate LLM modules (1) aligned with static image features, and (2) may possess prior knowledge of world dynamics (as demonstrated in the text world), they have not been trained in an embodied visual world and thus cannot align with its dynamics. On the other hand, training an embodied agent in a noisy visual world without expert guidance is often challeng","authors_text":"Dapeng Tao, Jing Jiang, Kanxue Li, Li Shen, Lusong Li, Tianyi Zhou, Xiaodong He, Yijun Yang, Yuhui Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T11:53:56Z","title":"Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16714","kind":"arxiv","version":2},"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:c4d6462dbc70c413a42f6f4774015f26f12cd1f3210d07d67665c5a25d313bee","target":"record","created_at":"2026-07-05T08:02:03Z","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":"a245d47277a522bf3a653c990b2b1ac984d3ff5fd3864d1cf0d8e2c391f2e665","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T11:53:56Z","title_canon_sha256":"5d1e5d35bf2a66dfa8863ee85bf5dffd5f9b2e8fc2cf11a58722ab5058bdb04d"},"schema_version":"1.0","source":{"id":"2311.16714","kind":"arxiv","version":2}},"canonical_sha256":"303bc1f21a5dc1e5e792d2763677c869904f4bfddab067192a55e4b9bf758434","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"303bc1f21a5dc1e5e792d2763677c869904f4bfddab067192a55e4b9bf758434","first_computed_at":"2026-07-05T08:02:03.159612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:03.159612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jSVMHkfamOX7805BHLwhhAhLDSUz8nqMEgENVmGCdHHeIwwmoaM1YzvMj5L0GiLR2LS17X7Igsw2DebXIZg3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:03.160011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.16714","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4d6462dbc70c413a42f6f4774015f26f12cd1f3210d07d67665c5a25d313bee","sha256:5580e69c3d9ade690bb60b55076888f48e16b29f509547bcb34fd28ed713c526"],"state_sha256":"1294c29edbc7dda9482b8c7409910740b7efcb2d3482411fa2c9a383d45f6842"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MoFArFzh5KVEyJOVmBQkzLH5v1BrgZ6VizvKTClhLv6x5Ngqemf/j80FYMEBlMOSCGejB9SVXPXVQOf9y8QuBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:59:23.505296Z","bundle_sha256":"69aa5b61b3337ea2ff3c97bf9b6d724b4f8660117b8716837ae154037b461593"}}