{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:O6BF2CAS2NZMXB3GB2D2NZSK4E","short_pith_number":"pith:O6BF2CAS","canonical_record":{"source":{"id":"2505.09694","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T18:00:19Z","cross_cats_sorted":[],"title_canon_sha256":"f823565b1e02f13f941e3fd398812e129c0ff8e5fd22211097b75254187493bb","abstract_canon_sha256":"b59e88dd78e07dc0e07c590d7f6926b72cb956d7f2ece4e168d14251cf8314b7"},"schema_version":"1.0"},"canonical_sha256":"77825d0812d372cb87660e87a6e64ae104ffeb78acf03e5a9219f47d055dc929","source":{"kind":"arxiv","id":"2505.09694","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09694","created_at":"2026-07-05T11:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09694v2","created_at":"2026-07-05T11:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09694","created_at":"2026-07-05T11:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"O6BF2CAS2NZM","created_at":"2026-07-05T11:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"O6BF2CAS2NZMXB3G","created_at":"2026-07-05T11:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"O6BF2CAS","created_at":"2026-07-05T11:04:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:O6BF2CAS2NZMXB3GB2D2NZSK4E","target":"record","payload":{"canonical_record":{"source":{"id":"2505.09694","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T18:00:19Z","cross_cats_sorted":[],"title_canon_sha256":"f823565b1e02f13f941e3fd398812e129c0ff8e5fd22211097b75254187493bb","abstract_canon_sha256":"b59e88dd78e07dc0e07c590d7f6926b72cb956d7f2ece4e168d14251cf8314b7"},"schema_version":"1.0"},"canonical_sha256":"77825d0812d372cb87660e87a6e64ae104ffeb78acf03e5a9219f47d055dc929","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:51.612861Z","signature_b64":"7lRRlzt9CW95QTf/koPI8qpxl7nrQ+uFu2gWPDZnkbFG8QBIUyLRqRo5ZYDCo1YJxHwnwW57waFq0/WWcnDpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77825d0812d372cb87660e87a6e64ae104ffeb78acf03e5a9219f47d055dc929","last_reissued_at":"2026-07-05T11:04:51.612295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:51.612295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.09694","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":"2026-07-05T11:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z8ofg2Fh3O2WVBZpA5vjKyCwopQD4qSOhnlU1RT8D6rkBlqDTvnIKliCCrQpS4/yBNjt2QeVkaKtHhSSMVG6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:07:49.771258Z"},"content_sha256":"483ec00ca111a3beebd18313131913eadd68cec0681879b0928288ce250740b0","schema_version":"1.0","event_id":"sha256:483ec00ca111a3beebd18313131913eadd68cec0681879b0928288ce250740b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:O6BF2CAS2NZMXB3GB2D2NZSK4E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guanghui Ren, Hu Yue, Liliang Chen, Maoqing Yao, Pengfei Zhou, Shengcong Chen, Siyuan Huang, Yue Liao","submitted_at":"2025-05-14T18:00:19Z","abstract_excerpt":"Recent advances in creative AI have enabled the synthesis of high-fidelity images and videos conditioned on language instructions. Building on these developments, text-to-video diffusion models have evolved into embodied world models (EWMs) capable of generating physically plausible scenes from language commands, effectively bridging vision and action in embodied AI applications. This work addresses the critical challenge of evaluating EWMs beyond general perceptual metrics to ensure the generation of physically grounded and action-consistent behaviors. We propose the Embodied World Model Benc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09694","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/2505.09694/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":"2026-07-05T11:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nw0DEmz5YdAqqNyuRwU7N83TD361FCMvQDkuABITdslei8puc6CpzExOIjJ4SlK19ZO0BgtLVbk3lmF5qKLsAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:07:49.772197Z"},"content_sha256":"934e1163b20786534a1df24edfac7150236b5a292eb6c572ff6c3389251b4c12","schema_version":"1.0","event_id":"sha256:934e1163b20786534a1df24edfac7150236b5a292eb6c572ff6c3389251b4c12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O6BF2CAS2NZMXB3GB2D2NZSK4E/bundle.json","state_url":"https://pith.science/pith/O6BF2CAS2NZMXB3GB2D2NZSK4E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O6BF2CAS2NZMXB3GB2D2NZSK4E/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":"2026-08-05T05:07:49Z","links":{"resolver":"https://pith.science/pith/O6BF2CAS2NZMXB3GB2D2NZSK4E","bundle":"https://pith.science/pith/O6BF2CAS2NZMXB3GB2D2NZSK4E/bundle.json","state":"https://pith.science/pith/O6BF2CAS2NZMXB3GB2D2NZSK4E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O6BF2CAS2NZMXB3GB2D2NZSK4E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O6BF2CAS2NZMXB3GB2D2NZSK4E","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":"b59e88dd78e07dc0e07c590d7f6926b72cb956d7f2ece4e168d14251cf8314b7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T18:00:19Z","title_canon_sha256":"f823565b1e02f13f941e3fd398812e129c0ff8e5fd22211097b75254187493bb"},"schema_version":"1.0","source":{"id":"2505.09694","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09694","created_at":"2026-07-05T11:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09694v2","created_at":"2026-07-05T11:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09694","created_at":"2026-07-05T11:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"O6BF2CAS2NZM","created_at":"2026-07-05T11:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"O6BF2CAS2NZMXB3G","created_at":"2026-07-05T11:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"O6BF2CAS","created_at":"2026-07-05T11:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:934e1163b20786534a1df24edfac7150236b5a292eb6c572ff6c3389251b4c12","target":"graph","created_at":"2026-07-05T11:04:51Z","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/2505.09694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in creative AI have enabled the synthesis of high-fidelity images and videos conditioned on language instructions. Building on these developments, text-to-video diffusion models have evolved into embodied world models (EWMs) capable of generating physically plausible scenes from language commands, effectively bridging vision and action in embodied AI applications. This work addresses the critical challenge of evaluating EWMs beyond general perceptual metrics to ensure the generation of physically grounded and action-consistent behaviors. We propose the Embodied World Model Benc","authors_text":"Guanghui Ren, Hu Yue, Liliang Chen, Maoqing Yao, Pengfei Zhou, Shengcong Chen, Siyuan Huang, Yue Liao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T18:00:19Z","title":"EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09694","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":"sha256:483ec00ca111a3beebd18313131913eadd68cec0681879b0928288ce250740b0","target":"record","created_at":"2026-07-05T11:04:51Z","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":"b59e88dd78e07dc0e07c590d7f6926b72cb956d7f2ece4e168d14251cf8314b7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T18:00:19Z","title_canon_sha256":"f823565b1e02f13f941e3fd398812e129c0ff8e5fd22211097b75254187493bb"},"schema_version":"1.0","source":{"id":"2505.09694","kind":"arxiv","version":2}},"canonical_sha256":"77825d0812d372cb87660e87a6e64ae104ffeb78acf03e5a9219f47d055dc929","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77825d0812d372cb87660e87a6e64ae104ffeb78acf03e5a9219f47d055dc929","first_computed_at":"2026-07-05T11:04:51.612295Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:51.612295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7lRRlzt9CW95QTf/koPI8qpxl7nrQ+uFu2gWPDZnkbFG8QBIUyLRqRo5ZYDCo1YJxHwnwW57waFq0/WWcnDpAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:51.612861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.09694","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:483ec00ca111a3beebd18313131913eadd68cec0681879b0928288ce250740b0","sha256:934e1163b20786534a1df24edfac7150236b5a292eb6c572ff6c3389251b4c12"],"state_sha256":"7dd0d811e07db4408ac7dceaab957a4dafb4b41c286eb353ca25376a34888aec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pM/NOnqI8fakblb7xWdHsL4JTw5ELT6auViB3eZ+fzX0DDfzyAPItWQZFg5UFPJezPBdh988LvgQ75YaCagUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T05:07:49.779609Z","bundle_sha256":"2b9ea2cf52a12654e4180fc364620c8fb8dab090f394729200bac391368a5f6e"}}