{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LRL5ZS4LZHAB5NHFCMKCKMK3I5","short_pith_number":"pith:LRL5ZS4L","schema_version":"1.0","canonical_sha256":"5c57dccb8bc9c01eb4e5131425315b477f63a39c7186b45d23ac7690b1854a08","source":{"kind":"arxiv","id":"2603.09731","version":3},"attestation_state":"computed","paper":{"title":"EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chaoqun Du, Chengjun Yu, Pengfei Yu, Wei Zhai, Xuhan Zhu, Yang Cao, Zheng-Jun Zha","submitted_at":"2026-03-10T14:33:44Z","abstract_excerpt":"Multimodal large language models (MLLMs) are increasingly considered as a foundation for embodied agents, yet it remains unclear whether they can reliably reason about the long-term physical consequences of actions from an egocentric viewpoint. We study this gap through a new task, Egocentric Scene Prediction with LOng-horizon REasoning: given an initial-scene image and a sequence of atomic action descriptions, a model is asked to predict the final scene after all actions are executed. To enable systematic evaluation, we introduce EXPLORE-Bench, a benchmark curated from real first-person video"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.09731","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-10T14:33:44Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f80a48a690bcec60e6e321c8cf9632165ea32bed163af88bbbd3dfc64d28baec","abstract_canon_sha256":"7d75c88f19592566dbd1fe95977cbd000f0c05d741f7dcc0dd56f21de6fe9eff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:29.866585Z","signature_b64":"5jlNLp2kbSSTyyldRPtd3Vp6sVMIj6Ioff80tAopFt2gJVnF4z3QDpFtaHfv6En2UcaK1Ppgg6rjPAiY69yzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c57dccb8bc9c01eb4e5131425315b477f63a39c7186b45d23ac7690b1854a08","last_reissued_at":"2026-06-29T01:14:29.866081Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:29.866081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chaoqun Du, Chengjun Yu, Pengfei Yu, Wei Zhai, Xuhan Zhu, Yang Cao, Zheng-Jun Zha","submitted_at":"2026-03-10T14:33:44Z","abstract_excerpt":"Multimodal large language models (MLLMs) are increasingly considered as a foundation for embodied agents, yet it remains unclear whether they can reliably reason about the long-term physical consequences of actions from an egocentric viewpoint. We study this gap through a new task, Egocentric Scene Prediction with LOng-horizon REasoning: given an initial-scene image and a sequence of atomic action descriptions, a model is asked to predict the final scene after all actions are executed. To enable systematic evaluation, we introduce EXPLORE-Bench, a benchmark curated from real first-person video"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.09731","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/2603.09731/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.09731","created_at":"2026-06-29T01:14:29.866136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.09731v3","created_at":"2026-06-29T01:14:29.866136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.09731","created_at":"2026-06-29T01:14:29.866136+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRL5ZS4LZHAB","created_at":"2026-06-29T01:14:29.866136+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRL5ZS4LZHAB5NHF","created_at":"2026-06-29T01:14:29.866136+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRL5ZS4L","created_at":"2026-06-29T01:14:29.866136+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.02425","citing_title":"Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRL5ZS4LZHAB5NHFCMKCKMK3I5","json":"https://pith.science/pith/LRL5ZS4LZHAB5NHFCMKCKMK3I5.json","graph_json":"https://pith.science/api/pith-number/LRL5ZS4LZHAB5NHFCMKCKMK3I5/graph.json","events_json":"https://pith.science/api/pith-number/LRL5ZS4LZHAB5NHFCMKCKMK3I5/events.json","paper":"https://pith.science/paper/LRL5ZS4L"},"agent_actions":{"view_html":"https://pith.science/pith/LRL5ZS4LZHAB5NHFCMKCKMK3I5","download_json":"https://pith.science/pith/LRL5ZS4LZHAB5NHFCMKCKMK3I5.json","view_paper":"https://pith.science/paper/LRL5ZS4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.09731&json=true","fetch_graph":"https://pith.science/api/pith-number/LRL5ZS4LZHAB5NHFCMKCKMK3I5/graph.json","fetch_events":"https://pith.science/api/pith-number/LRL5ZS4LZHAB5NHFCMKCKMK3I5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRL5ZS4LZHAB5NHFCMKCKMK3I5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRL5ZS4LZHAB5NHFCMKCKMK3I5/action/storage_attestation","attest_author":"https://pith.science/pith/LRL5ZS4LZHAB5NHFCMKCKMK3I5/action/author_attestation","sign_citation":"https://pith.science/pith/LRL5ZS4LZHAB5NHFCMKCKMK3I5/action/citation_signature","submit_replication":"https://pith.science/pith/LRL5ZS4LZHAB5NHFCMKCKMK3I5/action/replication_record"}},"created_at":"2026-06-29T01:14:29.866136+00:00","updated_at":"2026-06-29T01:14:29.866136+00:00"}