{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:A2KBZDEVVQUX6K3ARH73BGFQFS","short_pith_number":"pith:A2KBZDEV","canonical_record":{"source":{"id":"2311.09048","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T15:38:28Z","cross_cats_sorted":[],"title_canon_sha256":"87a3c033b0bb5e25cd39258f87e37bfeb62b5620e8fc1ed59de6cc16ffb3ca89","abstract_canon_sha256":"9c1264770b9d5b3e60c44f57f3838e7d573383df271dc0536b9a4d08dab29c5d"},"schema_version":"1.0"},"canonical_sha256":"06941c8c95ac297f2b6089ffb098b02c8107d26c257da6498941e32767d2eedc","source":{"kind":"arxiv","id":"2311.09048","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09048","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09048v3","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09048","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"A2KBZDEVVQUX","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"A2KBZDEVVQUX6K3A","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"A2KBZDEV","created_at":"2026-07-05T08:28:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:A2KBZDEVVQUX6K3ARH73BGFQFS","target":"record","payload":{"canonical_record":{"source":{"id":"2311.09048","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T15:38:28Z","cross_cats_sorted":[],"title_canon_sha256":"87a3c033b0bb5e25cd39258f87e37bfeb62b5620e8fc1ed59de6cc16ffb3ca89","abstract_canon_sha256":"9c1264770b9d5b3e60c44f57f3838e7d573383df271dc0536b9a4d08dab29c5d"},"schema_version":"1.0"},"canonical_sha256":"06941c8c95ac297f2b6089ffb098b02c8107d26c257da6498941e32767d2eedc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:03.597581Z","signature_b64":"jWbgv+6yu1ZxvtOx0/NBWwT6pxpasYxc/TnIjFCrKzG6+0ZM9O2IlYFheu9LZrYnBIT4q6N5u0Ds7GPXS6W/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06941c8c95ac297f2b6089ffb098b02c8107d26c257da6498941e32767d2eedc","last_reissued_at":"2026-07-05T08:28:03.597150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:03.597150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.09048","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":"2026-07-05T08:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2kf0ttPMV0wB6xzpJDjEAMZiBYqUIUYgh4rO6VohK3JG+Bg/1IOg/Kbm++cTr5ovG3h5n+1abr11WRuW5qKBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:27:02.826113Z"},"content_sha256":"aaf1bc4b8c5901b9aa71b61844996af284413115272521d738437e328854ba52","schema_version":"1.0","event_id":"sha256:aaf1bc4b8c5901b9aa71b61844996af284413115272521d738437e328854ba52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:A2KBZDEVVQUX6K3ARH73BGFQFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GRASP: A novel benchmark for evaluating language GRounding And Situated Physics understanding in multimodal language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Annika Richter, Cornelius Wolff, Elia Bruni, Mario Holubar, Serwan Jassim, Xenia Ohmer","submitted_at":"2023-11-15T15:38:28Z","abstract_excerpt":"This paper presents GRASP, a novel benchmark to evaluate the language grounding and physical understanding capabilities of video-based multimodal large language models (LLMs). This evaluation is accomplished via a two-tier approach leveraging Unity simulations. The first level tests for language grounding by assessing a model's ability to relate simple textual descriptions with visual information. The second level evaluates the model's understanding of \"Intuitive Physics\" principles, such as object permanence and continuity. In addition to releasing the benchmark, we use it to evaluate several"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09048","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/2311.09048/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":"2026-07-05T08:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CYXDIRAdQul7aF1mwJ//9FoS9gKmaxTMq7FjybsRwftYxxZMnCTYtBfnEAT2p2HXcKTtTerCdEnPsVxePoxPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:27:02.826955Z"},"content_sha256":"fe4bc2e001f70cc59d94db16a33dac2a65e4648788cfb97a5664069edab04430","schema_version":"1.0","event_id":"sha256:fe4bc2e001f70cc59d94db16a33dac2a65e4648788cfb97a5664069edab04430"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A2KBZDEVVQUX6K3ARH73BGFQFS/bundle.json","state_url":"https://pith.science/pith/A2KBZDEVVQUX6K3ARH73BGFQFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A2KBZDEVVQUX6K3ARH73BGFQFS/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":"2026-08-06T04:27:02Z","links":{"resolver":"https://pith.science/pith/A2KBZDEVVQUX6K3ARH73BGFQFS","bundle":"https://pith.science/pith/A2KBZDEVVQUX6K3ARH73BGFQFS/bundle.json","state":"https://pith.science/pith/A2KBZDEVVQUX6K3ARH73BGFQFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A2KBZDEVVQUX6K3ARH73BGFQFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:A2KBZDEVVQUX6K3ARH73BGFQFS","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":"9c1264770b9d5b3e60c44f57f3838e7d573383df271dc0536b9a4d08dab29c5d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T15:38:28Z","title_canon_sha256":"87a3c033b0bb5e25cd39258f87e37bfeb62b5620e8fc1ed59de6cc16ffb3ca89"},"schema_version":"1.0","source":{"id":"2311.09048","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09048","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09048v3","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09048","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"A2KBZDEVVQUX","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"A2KBZDEVVQUX6K3A","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"A2KBZDEV","created_at":"2026-07-05T08:28:03Z"}],"graph_snapshots":[{"event_id":"sha256:fe4bc2e001f70cc59d94db16a33dac2a65e4648788cfb97a5664069edab04430","target":"graph","created_at":"2026-07-05T08:28:03Z","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/2311.09048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents GRASP, a novel benchmark to evaluate the language grounding and physical understanding capabilities of video-based multimodal large language models (LLMs). This evaluation is accomplished via a two-tier approach leveraging Unity simulations. The first level tests for language grounding by assessing a model's ability to relate simple textual descriptions with visual information. The second level evaluates the model's understanding of \"Intuitive Physics\" principles, such as object permanence and continuity. In addition to releasing the benchmark, we use it to evaluate several","authors_text":"Annika Richter, Cornelius Wolff, Elia Bruni, Mario Holubar, Serwan Jassim, Xenia Ohmer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T15:38:28Z","title":"GRASP: A novel benchmark for evaluating language GRounding And Situated Physics understanding in multimodal language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09048","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:aaf1bc4b8c5901b9aa71b61844996af284413115272521d738437e328854ba52","target":"record","created_at":"2026-07-05T08:28:03Z","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":"9c1264770b9d5b3e60c44f57f3838e7d573383df271dc0536b9a4d08dab29c5d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T15:38:28Z","title_canon_sha256":"87a3c033b0bb5e25cd39258f87e37bfeb62b5620e8fc1ed59de6cc16ffb3ca89"},"schema_version":"1.0","source":{"id":"2311.09048","kind":"arxiv","version":3}},"canonical_sha256":"06941c8c95ac297f2b6089ffb098b02c8107d26c257da6498941e32767d2eedc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06941c8c95ac297f2b6089ffb098b02c8107d26c257da6498941e32767d2eedc","first_computed_at":"2026-07-05T08:28:03.597150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:03.597150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jWbgv+6yu1ZxvtOx0/NBWwT6pxpasYxc/TnIjFCrKzG6+0ZM9O2IlYFheu9LZrYnBIT4q6N5u0Ds7GPXS6W/DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:03.597581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09048","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaf1bc4b8c5901b9aa71b61844996af284413115272521d738437e328854ba52","sha256:fe4bc2e001f70cc59d94db16a33dac2a65e4648788cfb97a5664069edab04430"],"state_sha256":"dfb62935cfe9657f4d694a9bc491408a06c633eeba0e870a5f70baa83eb86179"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RfDB4mzBfLpqN063kZPCAJL9gk38x59v7c92yCX4eQzbA5g6ivaITbRYJ3y8R6H2Ce1mCEyQosPWEcSjonqBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:27:02.834741Z","bundle_sha256":"ad3d16a3dd4b8b1a0c3a3c987eaf4e535bb29a8ccf0647eca467a45e0c35777a"}}