{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FUK6BPLV4ZUFX6LYQP65WOLTTD","short_pith_number":"pith:FUK6BPLV","schema_version":"1.0","canonical_sha256":"2d15e0bd75e6685bf97883fddb397398efc2184297c8484561ebed35aa24b85b","source":{"kind":"arxiv","id":"2607.02991","version":1},"attestation_state":"computed","paper":{"title":"GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Yang, Fang Liu, Gerhard Hancke, Huankang Guan, Jinpeng Chen, Ke Xu, Rui Liu, Rynson W.H. Lau, Xudong Lu, Yuhao Liu","submitted_at":"2026-07-03T06:00:04Z","abstract_excerpt":"While multimodal Large Language Models (MLLMs) excel at offline video understanding, an interesting question of how far they are from serving as a real-time procedural coach remains unknown. Such a role typically requires an MLLM to continuously monitor the execution, detect mistakes, and provide corrective guidance in a closed-loop interaction. In this paper, we construct GuideMe, the first multi-domain benchmark for streaming video that supports training and evaluation of MLLMs for closed-loop interactive task guidance. It comprises 2,458 videos spanning 223.7 hours across diverse domains (\\"},"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":"2607.02991","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T06:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"c2e6cff8264ff10c827f9c5a8e3b6c0c2e0786fc2e874bdd8a6d49e5fed0b432","abstract_canon_sha256":"31439bddf77d7d6a90e47a943f88e8365db9509c680888dff4e4344c42cb164a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:38.811605Z","signature_b64":"UcDFFX3N2xtLHnyfGtcTFLy7NGI37vUfn0XjAVmtvyWPCWdv0QzK2xO6dtlj4DXbckM3dK2WsICy8VTPXMSHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d15e0bd75e6685bf97883fddb397398efc2184297c8484561ebed35aa24b85b","last_reissued_at":"2026-07-07T01:16:38.811148Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:38.811148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Yang, Fang Liu, Gerhard Hancke, Huankang Guan, Jinpeng Chen, Ke Xu, Rui Liu, Rynson W.H. Lau, Xudong Lu, Yuhao Liu","submitted_at":"2026-07-03T06:00:04Z","abstract_excerpt":"While multimodal Large Language Models (MLLMs) excel at offline video understanding, an interesting question of how far they are from serving as a real-time procedural coach remains unknown. Such a role typically requires an MLLM to continuously monitor the execution, detect mistakes, and provide corrective guidance in a closed-loop interaction. In this paper, we construct GuideMe, the first multi-domain benchmark for streaming video that supports training and evaluation of MLLMs for closed-loop interactive task guidance. It comprises 2,458 videos spanning 223.7 hours across diverse domains (\\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02991","kind":"arxiv","version":1},"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/2607.02991/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":"2607.02991","created_at":"2026-07-07T01:16:38.811218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02991v1","created_at":"2026-07-07T01:16:38.811218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02991","created_at":"2026-07-07T01:16:38.811218+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUK6BPLV4ZUF","created_at":"2026-07-07T01:16:38.811218+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUK6BPLV4ZUFX6LY","created_at":"2026-07-07T01:16:38.811218+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUK6BPLV","created_at":"2026-07-07T01:16:38.811218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FUK6BPLV4ZUFX6LYQP65WOLTTD","json":"https://pith.science/pith/FUK6BPLV4ZUFX6LYQP65WOLTTD.json","graph_json":"https://pith.science/api/pith-number/FUK6BPLV4ZUFX6LYQP65WOLTTD/graph.json","events_json":"https://pith.science/api/pith-number/FUK6BPLV4ZUFX6LYQP65WOLTTD/events.json","paper":"https://pith.science/paper/FUK6BPLV"},"agent_actions":{"view_html":"https://pith.science/pith/FUK6BPLV4ZUFX6LYQP65WOLTTD","download_json":"https://pith.science/pith/FUK6BPLV4ZUFX6LYQP65WOLTTD.json","view_paper":"https://pith.science/paper/FUK6BPLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02991&json=true","fetch_graph":"https://pith.science/api/pith-number/FUK6BPLV4ZUFX6LYQP65WOLTTD/graph.json","fetch_events":"https://pith.science/api/pith-number/FUK6BPLV4ZUFX6LYQP65WOLTTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUK6BPLV4ZUFX6LYQP65WOLTTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUK6BPLV4ZUFX6LYQP65WOLTTD/action/storage_attestation","attest_author":"https://pith.science/pith/FUK6BPLV4ZUFX6LYQP65WOLTTD/action/author_attestation","sign_citation":"https://pith.science/pith/FUK6BPLV4ZUFX6LYQP65WOLTTD/action/citation_signature","submit_replication":"https://pith.science/pith/FUK6BPLV4ZUFX6LYQP65WOLTTD/action/replication_record"}},"created_at":"2026-07-07T01:16:38.811218+00:00","updated_at":"2026-07-07T01:16:38.811218+00:00"}