{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FUK6BPLV4ZUFX6LYQP65WOLTTD","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":"31439bddf77d7d6a90e47a943f88e8365db9509c680888dff4e4344c42cb164a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T06:00:04Z","title_canon_sha256":"c2e6cff8264ff10c827f9c5a8e3b6c0c2e0786fc2e874bdd8a6d49e5fed0b432"},"schema_version":"1.0","source":{"id":"2607.02991","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02991","created_at":"2026-07-07T01:16:38Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02991v1","created_at":"2026-07-07T01:16:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02991","created_at":"2026-07-07T01:16:38Z"},{"alias_kind":"pith_short_12","alias_value":"FUK6BPLV4ZUF","created_at":"2026-07-07T01:16:38Z"},{"alias_kind":"pith_short_16","alias_value":"FUK6BPLV4ZUFX6LY","created_at":"2026-07-07T01:16:38Z"},{"alias_kind":"pith_short_8","alias_value":"FUK6BPLV","created_at":"2026-07-07T01:16:38Z"}],"graph_snapshots":[{"event_id":"sha256:ba44708b7a34d5e0643a3b926f2b87ac0549f29d8df122fdf73660abed1c04eb","target":"graph","created_at":"2026-07-07T01:16:38Z","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/2607.02991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 (\\","authors_text":"Bo Yang, Fang Liu, Gerhard Hancke, Huankang Guan, Jinpeng Chen, Ke Xu, Rui Liu, Rynson W.H. Lau, Xudong Lu, Yuhao Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T06:00:04Z","title":"GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02991","kind":"arxiv","version":1},"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:b64eb80df71ea594d5b670381eac9295648a639a2f78d1a941e1392add9d5fa0","target":"record","created_at":"2026-07-07T01:16:38Z","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":"31439bddf77d7d6a90e47a943f88e8365db9509c680888dff4e4344c42cb164a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T06:00:04Z","title_canon_sha256":"c2e6cff8264ff10c827f9c5a8e3b6c0c2e0786fc2e874bdd8a6d49e5fed0b432"},"schema_version":"1.0","source":{"id":"2607.02991","kind":"arxiv","version":1}},"canonical_sha256":"2d15e0bd75e6685bf97883fddb397398efc2184297c8484561ebed35aa24b85b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d15e0bd75e6685bf97883fddb397398efc2184297c8484561ebed35aa24b85b","first_computed_at":"2026-07-07T01:16:38.811148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T01:16:38.811148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UcDFFX3N2xtLHnyfGtcTFLy7NGI37vUfn0XjAVmtvyWPCWdv0QzK2xO6dtlj4DXbckM3dK2WsICy8VTPXMSHCw==","signature_status":"signed_v1","signed_at":"2026-07-07T01:16:38.811605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02991","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b64eb80df71ea594d5b670381eac9295648a639a2f78d1a941e1392add9d5fa0","sha256:ba44708b7a34d5e0643a3b926f2b87ac0549f29d8df122fdf73660abed1c04eb"],"state_sha256":"c24a22e01aa827207842f512c3a2444c075a0aa12a8dca85e3d3c84a0c08a330"}