{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AAPZRMZNV4LYTNS35YY2W6HZ7D","short_pith_number":"pith:AAPZRMZN","canonical_record":{"source":{"id":"2506.12623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-14T20:39:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8c0b45b6b70738118e0f434c31fb410bce6c2f832995f68d6683a95725026b0c","abstract_canon_sha256":"7be012761d01e4289f0961406039266dc66924a0761641a010a2cd8a30112831"},"schema_version":"1.0"},"canonical_sha256":"001f98b32daf1789b65bee31ab78f9f8c8f1d6bd3e59323159ad8a870c338cd0","source":{"kind":"arxiv","id":"2506.12623","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12623","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12623v1","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12623","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"pith_short_12","alias_value":"AAPZRMZNV4LY","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"pith_short_16","alias_value":"AAPZRMZNV4LYTNS3","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"pith_short_8","alias_value":"AAPZRMZN","created_at":"2026-07-05T11:21:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AAPZRMZNV4LYTNS35YY2W6HZ7D","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-14T20:39:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8c0b45b6b70738118e0f434c31fb410bce6c2f832995f68d6683a95725026b0c","abstract_canon_sha256":"7be012761d01e4289f0961406039266dc66924a0761641a010a2cd8a30112831"},"schema_version":"1.0"},"canonical_sha256":"001f98b32daf1789b65bee31ab78f9f8c8f1d6bd3e59323159ad8a870c338cd0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:56.484158Z","signature_b64":"fIX2syt1UvIRhkHaELDKwDu9V61d/Zvtqihoed7Y7PVvB173bZtuJezTX/nOFCAXkFcGItolgbSNgANTiFn5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"001f98b32daf1789b65bee31ab78f9f8c8f1d6bd3e59323159ad8a870c338cd0","last_reissued_at":"2026-07-05T11:21:56.483686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:56.483686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12623","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":"2026-07-05T11:21:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7+CtFuTbjCUf+UprwhevFLErjAoRuZcm2JOjwUkDwyuPZay6Yz0SS+2b5DntX1/t73Qf2LaQhQTjhrnp015VDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:00:58.730231Z"},"content_sha256":"a80d027374b4c912eec6d1b7eca467a74d35d542ec5d61c1affc2ee93c5326f4","schema_version":"1.0","event_id":"sha256:a80d027374b4c912eec6d1b7eca467a74d35d542ec5d61c1affc2ee93c5326f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AAPZRMZNV4LYTNS35YY2W6HZ7D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MS4UI: A Dataset for Multi-modal Summarization of User Interface Instructional Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chen Sun, Franck Dernoncourt, Hao Tan, Jiuxiang Gu, Kushal Kafle, Seunghyun Yoon, Trung Bui, Yuan Zang","submitted_at":"2025-06-14T20:39:32Z","abstract_excerpt":"We study multi-modal summarization for instructional videos, whose goal is to provide users an efficient way to learn skills in the form of text instructions and key video frames. We observe that existing benchmarks focus on generic semantic-level video summarization, and are not suitable for providing step-by-step executable instructions and illustrations, both of which are crucial for instructional videos. We propose a novel benchmark for user interface (UI) instructional video summarization to fill the gap. We collect a dataset of 2,413 UI instructional videos, which spans over 167 hours. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12623","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/2506.12623/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":"2026-07-05T11:21:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOYTljlHgHyMidYEYhG4ml5u21ekzybOYPPEbuJ0qvgQFPBzuOQmFALx7H8mQcT5iCxnPecnRFg/UxOAclNNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:00:58.731159Z"},"content_sha256":"f8d9d58130b81c28d019af4ed6b4709a93a7467b446bd23cee4479dd9a72788a","schema_version":"1.0","event_id":"sha256:f8d9d58130b81c28d019af4ed6b4709a93a7467b446bd23cee4479dd9a72788a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AAPZRMZNV4LYTNS35YY2W6HZ7D/bundle.json","state_url":"https://pith.science/pith/AAPZRMZNV4LYTNS35YY2W6HZ7D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AAPZRMZNV4LYTNS35YY2W6HZ7D/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":"2026-08-10T00:00:58Z","links":{"resolver":"https://pith.science/pith/AAPZRMZNV4LYTNS35YY2W6HZ7D","bundle":"https://pith.science/pith/AAPZRMZNV4LYTNS35YY2W6HZ7D/bundle.json","state":"https://pith.science/pith/AAPZRMZNV4LYTNS35YY2W6HZ7D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AAPZRMZNV4LYTNS35YY2W6HZ7D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AAPZRMZNV4LYTNS35YY2W6HZ7D","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":"7be012761d01e4289f0961406039266dc66924a0761641a010a2cd8a30112831","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-14T20:39:32Z","title_canon_sha256":"8c0b45b6b70738118e0f434c31fb410bce6c2f832995f68d6683a95725026b0c"},"schema_version":"1.0","source":{"id":"2506.12623","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12623","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12623v1","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12623","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"pith_short_12","alias_value":"AAPZRMZNV4LY","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"pith_short_16","alias_value":"AAPZRMZNV4LYTNS3","created_at":"2026-07-05T11:21:56Z"},{"alias_kind":"pith_short_8","alias_value":"AAPZRMZN","created_at":"2026-07-05T11:21:56Z"}],"graph_snapshots":[{"event_id":"sha256:f8d9d58130b81c28d019af4ed6b4709a93a7467b446bd23cee4479dd9a72788a","target":"graph","created_at":"2026-07-05T11:21:56Z","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/2506.12623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study multi-modal summarization for instructional videos, whose goal is to provide users an efficient way to learn skills in the form of text instructions and key video frames. We observe that existing benchmarks focus on generic semantic-level video summarization, and are not suitable for providing step-by-step executable instructions and illustrations, both of which are crucial for instructional videos. We propose a novel benchmark for user interface (UI) instructional video summarization to fill the gap. We collect a dataset of 2,413 UI instructional videos, which spans over 167 hours. T","authors_text":"Chen Sun, Franck Dernoncourt, Hao Tan, Jiuxiang Gu, Kushal Kafle, Seunghyun Yoon, Trung Bui, Yuan Zang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-14T20:39:32Z","title":"MS4UI: A Dataset for Multi-modal Summarization of User Interface Instructional Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12623","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:a80d027374b4c912eec6d1b7eca467a74d35d542ec5d61c1affc2ee93c5326f4","target":"record","created_at":"2026-07-05T11:21:56Z","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":"7be012761d01e4289f0961406039266dc66924a0761641a010a2cd8a30112831","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-14T20:39:32Z","title_canon_sha256":"8c0b45b6b70738118e0f434c31fb410bce6c2f832995f68d6683a95725026b0c"},"schema_version":"1.0","source":{"id":"2506.12623","kind":"arxiv","version":1}},"canonical_sha256":"001f98b32daf1789b65bee31ab78f9f8c8f1d6bd3e59323159ad8a870c338cd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"001f98b32daf1789b65bee31ab78f9f8c8f1d6bd3e59323159ad8a870c338cd0","first_computed_at":"2026-07-05T11:21:56.483686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:56.483686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fIX2syt1UvIRhkHaELDKwDu9V61d/Zvtqihoed7Y7PVvB173bZtuJezTX/nOFCAXkFcGItolgbSNgANTiFn5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:56.484158Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12623","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a80d027374b4c912eec6d1b7eca467a74d35d542ec5d61c1affc2ee93c5326f4","sha256:f8d9d58130b81c28d019af4ed6b4709a93a7467b446bd23cee4479dd9a72788a"],"state_sha256":"58ef1e8547f4648f3f1a6efa847a23de575b42f61f096ee9e716c23a70c158b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fGGzludXlNhA/Cx8xqSFouCiyfwiGiKQDiSXuO6sgqWqN5EnBWj4FTf3qFWd/9ZHjdB8If14BS7XB5Fn7MshAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:00:58.783466Z","bundle_sha256":"011f49013822ed28a83e0c091d23add8870c0bf37312fd3087e2891886059000"}}