{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HFGYQ3JCMQCRZSCA26YUJ7EYQM","short_pith_number":"pith:HFGYQ3JC","canonical_record":{"source":{"id":"2406.13719","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-19T17:22:11Z","cross_cats_sorted":[],"title_canon_sha256":"db3bec164fca303837525212d1b47f36ef8932ca88c13fc2f21e5c64b77711b3","abstract_canon_sha256":"97791966abd30bfb96649276454cfd21e1ced425365bb7448b1e4c8fe79d0be8"},"schema_version":"1.0"},"canonical_sha256":"394d886d2264051cc840d7b144fc988339381b9fb2ac4ff266c4fb559440ade4","source":{"kind":"arxiv","id":"2406.13719","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13719","created_at":"2026-07-05T08:34:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13719v1","created_at":"2026-07-05T08:34:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13719","created_at":"2026-07-05T08:34:33Z"},{"alias_kind":"pith_short_12","alias_value":"HFGYQ3JCMQCR","created_at":"2026-07-05T08:34:33Z"},{"alias_kind":"pith_short_16","alias_value":"HFGYQ3JCMQCRZSCA","created_at":"2026-07-05T08:34:33Z"},{"alias_kind":"pith_short_8","alias_value":"HFGYQ3JC","created_at":"2026-07-05T08:34:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HFGYQ3JCMQCRZSCA26YUJ7EYQM","target":"record","payload":{"canonical_record":{"source":{"id":"2406.13719","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-19T17:22:11Z","cross_cats_sorted":[],"title_canon_sha256":"db3bec164fca303837525212d1b47f36ef8932ca88c13fc2f21e5c64b77711b3","abstract_canon_sha256":"97791966abd30bfb96649276454cfd21e1ced425365bb7448b1e4c8fe79d0be8"},"schema_version":"1.0"},"canonical_sha256":"394d886d2264051cc840d7b144fc988339381b9fb2ac4ff266c4fb559440ade4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:33.709113Z","signature_b64":"3tf3y1o5p+qUYVjyptJ8g65ezLAiBZ491arAXk1V91wrGoeda8ESBTWl9Rbd/FYf2tQlNxNBHD2nzMMILNuRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"394d886d2264051cc840d7b144fc988339381b9fb2ac4ff266c4fb559440ade4","last_reissued_at":"2026-07-05T08:34:33.708624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:33.708624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.13719","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":"2026-07-05T08:34:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vH2TMOdAfEHIBpKUjuoeldmcFkG5uiNaLnIOYBOLSfZKaCpJb4VrQBbal+COfbRAUkiU9pqMn/fEK6Heh+l5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:52:03.166341Z"},"content_sha256":"53ae52be1f7dad1777f1672a3bf3556924862458f3f2e10c3a9855454eb440dc","schema_version":"1.0","event_id":"sha256:53ae52be1f7dad1777f1672a3bf3556924862458f3f2e10c3a9855454eb440dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HFGYQ3JCMQCRZSCA26YUJ7EYQM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GUI Action Narrator: Where and When Did That Action Take Place?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Difei Gao, Hengxu Wang, Kevin Qinghong Lin, Mike Zheng Shou, Peiran Li, Qinchen Wu, Weichen Zhang, Xiangwu Guo, Zhuoyu Wu","submitted_at":"2024-06-19T17:22:11Z","abstract_excerpt":"The advent of Multimodal LLMs has significantly enhanced image OCR recognition capabilities, making GUI automation a viable reality for increasing efficiency in digital tasks. One fundamental aspect of developing a GUI automation system is understanding primitive GUI actions. This comprehension is crucial as it enables agents to learn from user demonstrations, an essential element of automation. To rigorously evaluate such capabilities, we developed a video captioning benchmark for GUI actions, comprising 4,189 diverse video captioning samples. This task presents unique challenges compared to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13719","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/2406.13719/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":"2026-07-05T08:34:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5r4LCpzmmza31zxz60Lk6P9AwGBMUDPhn9IdNqd8EfSDLy7BPASqLzJunc0OHHDqvu0WTSO2O6pTyz6yvJsRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:52:03.166847Z"},"content_sha256":"bbe37f9006284a886acfbf68330308951294c45eb39c3ba71729ad926cc8ed3c","schema_version":"1.0","event_id":"sha256:bbe37f9006284a886acfbf68330308951294c45eb39c3ba71729ad926cc8ed3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HFGYQ3JCMQCRZSCA26YUJ7EYQM/bundle.json","state_url":"https://pith.science/pith/HFGYQ3JCMQCRZSCA26YUJ7EYQM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HFGYQ3JCMQCRZSCA26YUJ7EYQM/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":"2026-08-06T05:52:03Z","links":{"resolver":"https://pith.science/pith/HFGYQ3JCMQCRZSCA26YUJ7EYQM","bundle":"https://pith.science/pith/HFGYQ3JCMQCRZSCA26YUJ7EYQM/bundle.json","state":"https://pith.science/pith/HFGYQ3JCMQCRZSCA26YUJ7EYQM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HFGYQ3JCMQCRZSCA26YUJ7EYQM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HFGYQ3JCMQCRZSCA26YUJ7EYQM","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":"97791966abd30bfb96649276454cfd21e1ced425365bb7448b1e4c8fe79d0be8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-19T17:22:11Z","title_canon_sha256":"db3bec164fca303837525212d1b47f36ef8932ca88c13fc2f21e5c64b77711b3"},"schema_version":"1.0","source":{"id":"2406.13719","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13719","created_at":"2026-07-05T08:34:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13719v1","created_at":"2026-07-05T08:34:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13719","created_at":"2026-07-05T08:34:33Z"},{"alias_kind":"pith_short_12","alias_value":"HFGYQ3JCMQCR","created_at":"2026-07-05T08:34:33Z"},{"alias_kind":"pith_short_16","alias_value":"HFGYQ3JCMQCRZSCA","created_at":"2026-07-05T08:34:33Z"},{"alias_kind":"pith_short_8","alias_value":"HFGYQ3JC","created_at":"2026-07-05T08:34:33Z"}],"graph_snapshots":[{"event_id":"sha256:bbe37f9006284a886acfbf68330308951294c45eb39c3ba71729ad926cc8ed3c","target":"graph","created_at":"2026-07-05T08:34:33Z","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/2406.13719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of Multimodal LLMs has significantly enhanced image OCR recognition capabilities, making GUI automation a viable reality for increasing efficiency in digital tasks. One fundamental aspect of developing a GUI automation system is understanding primitive GUI actions. This comprehension is crucial as it enables agents to learn from user demonstrations, an essential element of automation. To rigorously evaluate such capabilities, we developed a video captioning benchmark for GUI actions, comprising 4,189 diverse video captioning samples. This task presents unique challenges compared to ","authors_text":"Difei Gao, Hengxu Wang, Kevin Qinghong Lin, Mike Zheng Shou, Peiran Li, Qinchen Wu, Weichen Zhang, Xiangwu Guo, Zhuoyu Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-19T17:22:11Z","title":"GUI Action Narrator: Where and When Did That Action Take Place?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13719","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":"sha256:53ae52be1f7dad1777f1672a3bf3556924862458f3f2e10c3a9855454eb440dc","target":"record","created_at":"2026-07-05T08:34:33Z","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":"97791966abd30bfb96649276454cfd21e1ced425365bb7448b1e4c8fe79d0be8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-19T17:22:11Z","title_canon_sha256":"db3bec164fca303837525212d1b47f36ef8932ca88c13fc2f21e5c64b77711b3"},"schema_version":"1.0","source":{"id":"2406.13719","kind":"arxiv","version":1}},"canonical_sha256":"394d886d2264051cc840d7b144fc988339381b9fb2ac4ff266c4fb559440ade4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"394d886d2264051cc840d7b144fc988339381b9fb2ac4ff266c4fb559440ade4","first_computed_at":"2026-07-05T08:34:33.708624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:33.708624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3tf3y1o5p+qUYVjyptJ8g65ezLAiBZ491arAXk1V91wrGoeda8ESBTWl9Rbd/FYf2tQlNxNBHD2nzMMILNuRBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:33.709113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13719","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53ae52be1f7dad1777f1672a3bf3556924862458f3f2e10c3a9855454eb440dc","sha256:bbe37f9006284a886acfbf68330308951294c45eb39c3ba71729ad926cc8ed3c"],"state_sha256":"d2ba27b1c61215438b7ae55834a0bd182e11eb4d239fb9acd994b854ea5c29a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f/i/xlHuBD6EEB98dplBB/AlCYvA+Bc/gnz3nTIa1lc4ySIKAFaFITS1P6gI9vPWUk/3kymW70Or8j2erh0NBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:52:03.170598Z","bundle_sha256":"083db1ef8d0809aa8b9d0f19cfe442b4514ef382452d34149853ba15a2a1bc23"}}