{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LS3E7LKANDQE5A3OZ2PYKL2E63","short_pith_number":"pith:LS3E7LKA","schema_version":"1.0","canonical_sha256":"5cb64fad4068e04e836ece9f852f44f6c7e41593ae8bcfa3ddf52f5005025d14","source":{"kind":"arxiv","id":"2506.17629","version":2},"attestation_state":"computed","paper":{"title":"CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Kailing Li, Qi'ao Xu, Tianwen Qian, Xiaoling Wang, Yang Jiao, Yuqian Fu","submitted_at":"2025-06-21T08:11:40Z","abstract_excerpt":"Embodied Visual Reasoning (EVR) seeks to follow complex, free-form instructions based on egocentric video, enabling semantic understanding and spatiotemporal reasoning in dynamic environments. Despite its promising potential, EVR encounters significant challenges stemming from the diversity of complex instructions and the intricate spatiotemporal dynamics in long-term egocentric videos. Prior solutions either employ Large Language Models (LLMs) over static video captions, which often omit critical visual details, or rely on end-to-end Vision-Language Models (VLMs) that struggle with stepwise c"},"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":"2506.17629","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-21T08:11:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"80c0fc09ff018a3d1d75038993e00130aacf945772c19978980e5c468cfb3d8e","abstract_canon_sha256":"8629fc8b939170dee0d406e692fddc28dc153efc442455ba0c7708e598a120bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:51.983714Z","signature_b64":"D5UCFDlgPKjZurPwmnFoNBZHHDSX6MeJAB9D+g9Avc7MLKEe6236VyRlD7d5VjzxsF52p2uhLAWi2TjqhIkLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cb64fad4068e04e836ece9f852f44f6c7e41593ae8bcfa3ddf52f5005025d14","last_reissued_at":"2026-05-26T02:03:51.982741Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:51.982741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Kailing Li, Qi'ao Xu, Tianwen Qian, Xiaoling Wang, Yang Jiao, Yuqian Fu","submitted_at":"2025-06-21T08:11:40Z","abstract_excerpt":"Embodied Visual Reasoning (EVR) seeks to follow complex, free-form instructions based on egocentric video, enabling semantic understanding and spatiotemporal reasoning in dynamic environments. Despite its promising potential, EVR encounters significant challenges stemming from the diversity of complex instructions and the intricate spatiotemporal dynamics in long-term egocentric videos. Prior solutions either employ Large Language Models (LLMs) over static video captions, which often omit critical visual details, or rely on end-to-end Vision-Language Models (VLMs) that struggle with stepwise c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17629","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/2506.17629/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":"2506.17629","created_at":"2026-05-26T02:03:51.982881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17629v2","created_at":"2026-05-26T02:03:51.982881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17629","created_at":"2026-05-26T02:03:51.982881+00:00"},{"alias_kind":"pith_short_12","alias_value":"LS3E7LKANDQE","created_at":"2026-05-26T02:03:51.982881+00:00"},{"alias_kind":"pith_short_16","alias_value":"LS3E7LKANDQE5A3O","created_at":"2026-05-26T02:03:51.982881+00:00"},{"alias_kind":"pith_short_8","alias_value":"LS3E7LKA","created_at":"2026-05-26T02:03:51.982881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2511.20886","citing_title":"V$^{2}$-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2512.03666","citing_title":"ToG-Bench: Task-Oriented Spatio-Temporal Grounding in Egocentric Videos","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2602.14122","citing_title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LS3E7LKANDQE5A3OZ2PYKL2E63","json":"https://pith.science/pith/LS3E7LKANDQE5A3OZ2PYKL2E63.json","graph_json":"https://pith.science/api/pith-number/LS3E7LKANDQE5A3OZ2PYKL2E63/graph.json","events_json":"https://pith.science/api/pith-number/LS3E7LKANDQE5A3OZ2PYKL2E63/events.json","paper":"https://pith.science/paper/LS3E7LKA"},"agent_actions":{"view_html":"https://pith.science/pith/LS3E7LKANDQE5A3OZ2PYKL2E63","download_json":"https://pith.science/pith/LS3E7LKANDQE5A3OZ2PYKL2E63.json","view_paper":"https://pith.science/paper/LS3E7LKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17629&json=true","fetch_graph":"https://pith.science/api/pith-number/LS3E7LKANDQE5A3OZ2PYKL2E63/graph.json","fetch_events":"https://pith.science/api/pith-number/LS3E7LKANDQE5A3OZ2PYKL2E63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LS3E7LKANDQE5A3OZ2PYKL2E63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LS3E7LKANDQE5A3OZ2PYKL2E63/action/storage_attestation","attest_author":"https://pith.science/pith/LS3E7LKANDQE5A3OZ2PYKL2E63/action/author_attestation","sign_citation":"https://pith.science/pith/LS3E7LKANDQE5A3OZ2PYKL2E63/action/citation_signature","submit_replication":"https://pith.science/pith/LS3E7LKANDQE5A3OZ2PYKL2E63/action/replication_record"}},"created_at":"2026-05-26T02:03:51.982881+00:00","updated_at":"2026-05-26T02:03:51.982881+00:00"}