{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JFYPIYP34NBQWHJTA634RA67FA","short_pith_number":"pith:JFYPIYP3","canonical_record":{"source":{"id":"2503.12542","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T15:24:11Z","cross_cats_sorted":[],"title_canon_sha256":"f5bc79f01f92b48c3c410250c578e5f78b2e4c56c4b561d437400d9ca5adc3b8","abstract_canon_sha256":"a8913977dbc0ed8ed9cbdcc0c76998c5341e66c2ead50c5478ff784178d05873"},"schema_version":"1.0"},"canonical_sha256":"4970f461fbe3430b1d3307b7c883df2838af770f5959f7c49da499b081e3428b","source":{"kind":"arxiv","id":"2503.12542","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12542","created_at":"2026-07-05T10:52:39Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12542v2","created_at":"2026-07-05T10:52:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12542","created_at":"2026-07-05T10:52:39Z"},{"alias_kind":"pith_short_12","alias_value":"JFYPIYP34NBQ","created_at":"2026-07-05T10:52:39Z"},{"alias_kind":"pith_short_16","alias_value":"JFYPIYP34NBQWHJT","created_at":"2026-07-05T10:52:39Z"},{"alias_kind":"pith_short_8","alias_value":"JFYPIYP3","created_at":"2026-07-05T10:52:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JFYPIYP34NBQWHJTA634RA67FA","target":"record","payload":{"canonical_record":{"source":{"id":"2503.12542","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T15:24:11Z","cross_cats_sorted":[],"title_canon_sha256":"f5bc79f01f92b48c3c410250c578e5f78b2e4c56c4b561d437400d9ca5adc3b8","abstract_canon_sha256":"a8913977dbc0ed8ed9cbdcc0c76998c5341e66c2ead50c5478ff784178d05873"},"schema_version":"1.0"},"canonical_sha256":"4970f461fbe3430b1d3307b7c883df2838af770f5959f7c49da499b081e3428b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:39.889558Z","signature_b64":"aHAScE2p/TJ/tigQqzSBV7EYSmBkL6GW89Edds5WfI839IigCq4FcKynkwr/8RKFsm+tYAk9w4pCOClkpHQwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4970f461fbe3430b1d3307b7c883df2838af770f5959f7c49da499b081e3428b","last_reissued_at":"2026-07-05T10:52:39.889060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:39.889060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.12542","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":"2026-07-05T10:52:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6HTPnJ163NWr9jZt6vL5Vgo+aPhF52pfSdprVQIOKGxsELVS+jF667aBAkD0UY91UnZFVinCKT2L1X20cvgEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:19:41.424043Z"},"content_sha256":"4e2829e4efc864a48cc612410e7907e564e1c7fb458eb1507dfb8c10046df2d4","schema_version":"1.0","event_id":"sha256:4e2829e4efc864a48cc612410e7907e564e1c7fb458eb1507dfb8c10046df2d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JFYPIYP34NBQWHJTA634RA67FA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junxiao Shen, Miao Liu, Peiran Wu, Yunze Liu","submitted_at":"2025-03-16T15:24:11Z","abstract_excerpt":"Humans excel at spatial-temporal reasoning, effortlessly interpreting dynamic visual events from an egocentric viewpoint. However, whether multimodal large language models (MLLMs) can similarly understand the 4D world remains uncertain. This paper explores multimodal spatial-temporal reasoning from an egocentric perspective, aiming to equip MLLMs with human-like reasoning capabilities. To support this objective, we introduce \\textbf{Ego-ST Bench}, a novel benchmark containing over 5,000 question-answer pairs across four categories, systematically evaluating spatial, temporal, and integrated sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12542","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/2503.12542/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":"2026-07-05T10:52:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RZWY/8RSRb+vjqhX7WB7dbkFOQwlY0dEj7SMeHbiq2T4h3yg+zvWUJY/E9Qq3oepaRxhEvmM24f1VjJk7rlDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:19:41.424430Z"},"content_sha256":"6115cbac26a79e0a7c6fd1ceba96cc9d7fcc031fa567d18c95c906c7a3998ad8","schema_version":"1.0","event_id":"sha256:6115cbac26a79e0a7c6fd1ceba96cc9d7fcc031fa567d18c95c906c7a3998ad8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JFYPIYP34NBQWHJTA634RA67FA/bundle.json","state_url":"https://pith.science/pith/JFYPIYP34NBQWHJTA634RA67FA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JFYPIYP34NBQWHJTA634RA67FA/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":"2026-07-07T09:19:41Z","links":{"resolver":"https://pith.science/pith/JFYPIYP34NBQWHJTA634RA67FA","bundle":"https://pith.science/pith/JFYPIYP34NBQWHJTA634RA67FA/bundle.json","state":"https://pith.science/pith/JFYPIYP34NBQWHJTA634RA67FA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JFYPIYP34NBQWHJTA634RA67FA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JFYPIYP34NBQWHJTA634RA67FA","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":"a8913977dbc0ed8ed9cbdcc0c76998c5341e66c2ead50c5478ff784178d05873","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T15:24:11Z","title_canon_sha256":"f5bc79f01f92b48c3c410250c578e5f78b2e4c56c4b561d437400d9ca5adc3b8"},"schema_version":"1.0","source":{"id":"2503.12542","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12542","created_at":"2026-07-05T10:52:39Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12542v2","created_at":"2026-07-05T10:52:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12542","created_at":"2026-07-05T10:52:39Z"},{"alias_kind":"pith_short_12","alias_value":"JFYPIYP34NBQ","created_at":"2026-07-05T10:52:39Z"},{"alias_kind":"pith_short_16","alias_value":"JFYPIYP34NBQWHJT","created_at":"2026-07-05T10:52:39Z"},{"alias_kind":"pith_short_8","alias_value":"JFYPIYP3","created_at":"2026-07-05T10:52:39Z"}],"graph_snapshots":[{"event_id":"sha256:6115cbac26a79e0a7c6fd1ceba96cc9d7fcc031fa567d18c95c906c7a3998ad8","target":"graph","created_at":"2026-07-05T10:52:39Z","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/2503.12542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans excel at spatial-temporal reasoning, effortlessly interpreting dynamic visual events from an egocentric viewpoint. However, whether multimodal large language models (MLLMs) can similarly understand the 4D world remains uncertain. This paper explores multimodal spatial-temporal reasoning from an egocentric perspective, aiming to equip MLLMs with human-like reasoning capabilities. To support this objective, we introduce \\textbf{Ego-ST Bench}, a novel benchmark containing over 5,000 question-answer pairs across four categories, systematically evaluating spatial, temporal, and integrated sp","authors_text":"Junxiao Shen, Miao Liu, Peiran Wu, Yunze Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T15:24:11Z","title":"ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12542","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":"sha256:4e2829e4efc864a48cc612410e7907e564e1c7fb458eb1507dfb8c10046df2d4","target":"record","created_at":"2026-07-05T10:52:39Z","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":"a8913977dbc0ed8ed9cbdcc0c76998c5341e66c2ead50c5478ff784178d05873","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T15:24:11Z","title_canon_sha256":"f5bc79f01f92b48c3c410250c578e5f78b2e4c56c4b561d437400d9ca5adc3b8"},"schema_version":"1.0","source":{"id":"2503.12542","kind":"arxiv","version":2}},"canonical_sha256":"4970f461fbe3430b1d3307b7c883df2838af770f5959f7c49da499b081e3428b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4970f461fbe3430b1d3307b7c883df2838af770f5959f7c49da499b081e3428b","first_computed_at":"2026-07-05T10:52:39.889060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:39.889060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aHAScE2p/TJ/tigQqzSBV7EYSmBkL6GW89Edds5WfI839IigCq4FcKynkwr/8RKFsm+tYAk9w4pCOClkpHQwAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:39.889558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12542","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e2829e4efc864a48cc612410e7907e564e1c7fb458eb1507dfb8c10046df2d4","sha256:6115cbac26a79e0a7c6fd1ceba96cc9d7fcc031fa567d18c95c906c7a3998ad8"],"state_sha256":"78e44151356ddb496eafcba755203c89892edc345df422c0aae3ab74c8a90b06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GtkH+Mzc+gwlS+FHAhzmQLYZtds/j7qSSKV7SuopSwdQtCin18NrbpgOHqCxVMTDnvf8aYgkVe0/JOorLrn2CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:19:41.426411Z","bundle_sha256":"d4be87bba25d576246bb2ea12545587785980f7d3c2da017c082f1bbded3417d"}}