{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FHWNFW5GCLMB27FSTJJEAIDYCT","short_pith_number":"pith:FHWNFW5G","canonical_record":{"source":{"id":"2606.29445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T15:11:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e35a895b9241a773aa34892365a3ea63fbf10586af4a1b6017a13de585434f8","abstract_canon_sha256":"db206a34ef40a1e6bc41c34caf53727d2c5833a32f99e26a57bfdbac2e355916"},"schema_version":"1.0"},"canonical_sha256":"29ecd2dba612d81d7cb29a5240207814dbf7412f786d5b8b0427bcdb2a2490e9","source":{"kind":"arxiv","id":"2606.29445","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29445","created_at":"2026-06-30T01:18:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29445v1","created_at":"2026-06-30T01:18:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29445","created_at":"2026-06-30T01:18:06Z"},{"alias_kind":"pith_short_12","alias_value":"FHWNFW5GCLMB","created_at":"2026-06-30T01:18:06Z"},{"alias_kind":"pith_short_16","alias_value":"FHWNFW5GCLMB27FS","created_at":"2026-06-30T01:18:06Z"},{"alias_kind":"pith_short_8","alias_value":"FHWNFW5G","created_at":"2026-06-30T01:18:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FHWNFW5GCLMB27FSTJJEAIDYCT","target":"record","payload":{"canonical_record":{"source":{"id":"2606.29445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T15:11:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e35a895b9241a773aa34892365a3ea63fbf10586af4a1b6017a13de585434f8","abstract_canon_sha256":"db206a34ef40a1e6bc41c34caf53727d2c5833a32f99e26a57bfdbac2e355916"},"schema_version":"1.0"},"canonical_sha256":"29ecd2dba612d81d7cb29a5240207814dbf7412f786d5b8b0427bcdb2a2490e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:06.781951Z","signature_b64":"FdG8n2n8IE3oNZrZWSaFVyuKBmcC9iuxrBcs/YIF9UOLwWhs6R1jZZHV2DeUwXpaxeDylBmGpX1I6jzppfsjCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29ecd2dba612d81d7cb29a5240207814dbf7412f786d5b8b0427bcdb2a2490e9","last_reissued_at":"2026-06-30T01:18:06.781285Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:06.781285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.29445","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:18:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pGyzpHDsAodv+p8jbOtm4XhdUhroGalBSb4/BKPawzG5+W7R08KN45nopR0K2lI9dlPH01Wo8tt953sGGKC3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T16:54:46.163217Z"},"content_sha256":"3cea4987f6cffe819bfb002c91c8b4ac608a6c30621194ef4eec52c4dbcdc354","schema_version":"1.0","event_id":"sha256:3cea4987f6cffe819bfb002c91c8b4ac608a6c30621194ef4eec52c4dbcdc354"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FHWNFW5GCLMB27FSTJJEAIDYCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Meng-Hao Guo, Qingle Liu, Runqi Yin, Shuojin Yang, Sunqi Fan","submitted_at":"2026-06-28T15:11:19Z","abstract_excerpt":"Video understanding is a fundamental capability for multimodal intelligence, and recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance on Video Question Answering (VideoQA) benchmarks. However, existing benchmarks primarily evaluate whether models can perceive shallow visual cues, while rarely examining whether MLLMs can learn deeper knowledge or procedural skills from video tutorials and generalize them to downstream long-horizon agentic tasks. To address this gap, we introduce VG-GUIBench (Video-Guided GUI Benchmark), a new benchmark designed to evaluate whethe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29445","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/2606.29445/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":"2026-06-30T01:18:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d4y6Poown26VL3RV/pB9Ate/2FLlKHB0BPApqVxU4LpbwHELpphcD/gbPHzrgBLvoeKGnKsVyDb2nndGIy9gBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T16:54:46.164123Z"},"content_sha256":"65af00640571ac7c209e20bae2e3108845570d696f7bbde2795e14aebdab8127","schema_version":"1.0","event_id":"sha256:65af00640571ac7c209e20bae2e3108845570d696f7bbde2795e14aebdab8127"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FHWNFW5GCLMB27FSTJJEAIDYCT/bundle.json","state_url":"https://pith.science/pith/FHWNFW5GCLMB27FSTJJEAIDYCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FHWNFW5GCLMB27FSTJJEAIDYCT/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":"2026-06-30T16:54:46Z","links":{"resolver":"https://pith.science/pith/FHWNFW5GCLMB27FSTJJEAIDYCT","bundle":"https://pith.science/pith/FHWNFW5GCLMB27FSTJJEAIDYCT/bundle.json","state":"https://pith.science/pith/FHWNFW5GCLMB27FSTJJEAIDYCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FHWNFW5GCLMB27FSTJJEAIDYCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FHWNFW5GCLMB27FSTJJEAIDYCT","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":"db206a34ef40a1e6bc41c34caf53727d2c5833a32f99e26a57bfdbac2e355916","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T15:11:19Z","title_canon_sha256":"9e35a895b9241a773aa34892365a3ea63fbf10586af4a1b6017a13de585434f8"},"schema_version":"1.0","source":{"id":"2606.29445","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29445","created_at":"2026-06-30T01:18:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29445v1","created_at":"2026-06-30T01:18:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29445","created_at":"2026-06-30T01:18:06Z"},{"alias_kind":"pith_short_12","alias_value":"FHWNFW5GCLMB","created_at":"2026-06-30T01:18:06Z"},{"alias_kind":"pith_short_16","alias_value":"FHWNFW5GCLMB27FS","created_at":"2026-06-30T01:18:06Z"},{"alias_kind":"pith_short_8","alias_value":"FHWNFW5G","created_at":"2026-06-30T01:18:06Z"}],"graph_snapshots":[{"event_id":"sha256:65af00640571ac7c209e20bae2e3108845570d696f7bbde2795e14aebdab8127","target":"graph","created_at":"2026-06-30T01:18:06Z","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/2606.29445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video understanding is a fundamental capability for multimodal intelligence, and recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance on Video Question Answering (VideoQA) benchmarks. However, existing benchmarks primarily evaluate whether models can perceive shallow visual cues, while rarely examining whether MLLMs can learn deeper knowledge or procedural skills from video tutorials and generalize them to downstream long-horizon agentic tasks. To address this gap, we introduce VG-GUIBench (Video-Guided GUI Benchmark), a new benchmark designed to evaluate whethe","authors_text":"Meng-Hao Guo, Qingle Liu, Runqi Yin, Shuojin Yang, Sunqi Fan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T15:11:19Z","title":"Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29445","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":"sha256:3cea4987f6cffe819bfb002c91c8b4ac608a6c30621194ef4eec52c4dbcdc354","target":"record","created_at":"2026-06-30T01:18:06Z","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":"db206a34ef40a1e6bc41c34caf53727d2c5833a32f99e26a57bfdbac2e355916","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T15:11:19Z","title_canon_sha256":"9e35a895b9241a773aa34892365a3ea63fbf10586af4a1b6017a13de585434f8"},"schema_version":"1.0","source":{"id":"2606.29445","kind":"arxiv","version":1}},"canonical_sha256":"29ecd2dba612d81d7cb29a5240207814dbf7412f786d5b8b0427bcdb2a2490e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29ecd2dba612d81d7cb29a5240207814dbf7412f786d5b8b0427bcdb2a2490e9","first_computed_at":"2026-06-30T01:18:06.781285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:06.781285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FdG8n2n8IE3oNZrZWSaFVyuKBmcC9iuxrBcs/YIF9UOLwWhs6R1jZZHV2DeUwXpaxeDylBmGpX1I6jzppfsjCQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:06.781951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29445","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cea4987f6cffe819bfb002c91c8b4ac608a6c30621194ef4eec52c4dbcdc354","sha256:65af00640571ac7c209e20bae2e3108845570d696f7bbde2795e14aebdab8127"],"state_sha256":"fd52e9ca35342914e6bef138bf80ff9213786842123d4697d53528ce3ac01ebb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"afdLvbvoEWpCmmtETmI8YNTaNUfkOsEklSGB4E9Lk5ftx0mW7PuJyIZXMQIwZW07J9R9dYy39liRuaUOBlZLDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T16:54:46.168039Z","bundle_sha256":"e64b60556b70497f9ee042e71ea6e533cc2fae7660e50b953b642683a8b7e8bd"}}