{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FQH4YXYCEQ2XRXBUAV64SUYZMZ","short_pith_number":"pith:FQH4YXYC","canonical_record":{"source":{"id":"2410.19100","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T19:03:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d72fedb3b6e9c537d960b41263a530f84f5d678539c0b2756bfac2b764a8e51","abstract_canon_sha256":"caf2005ebd3af02c85bb8d5eca2bbc1639c00f988a38d8f5938e719f9495669b"},"schema_version":"1.0"},"canonical_sha256":"2c0fcc5f02243578dc34057dc95319665a2a42f8ecfdc2c5a039f43efcb22358","source":{"kind":"arxiv","id":"2410.19100","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19100","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19100v3","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19100","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"FQH4YXYCEQ2X","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"FQH4YXYCEQ2XRXBU","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"FQH4YXYC","created_at":"2026-07-05T10:14:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FQH4YXYCEQ2XRXBUAV64SUYZMZ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.19100","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T19:03:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d72fedb3b6e9c537d960b41263a530f84f5d678539c0b2756bfac2b764a8e51","abstract_canon_sha256":"caf2005ebd3af02c85bb8d5eca2bbc1639c00f988a38d8f5938e719f9495669b"},"schema_version":"1.0"},"canonical_sha256":"2c0fcc5f02243578dc34057dc95319665a2a42f8ecfdc2c5a039f43efcb22358","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:47.121356Z","signature_b64":"O+2CIX/ZYPr9063JNF9xXGA6wY7l85VMoSvrF93nFPzm1mt2RDv0RDUzf3Hibz3xdidNfd6tt7jkR+UReOOXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c0fcc5f02243578dc34057dc95319665a2a42f8ecfdc2c5a039f43efcb22358","last_reissued_at":"2026-07-05T10:14:47.120826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:47.120826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.19100","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UxEbCaZKnvhsct+3u/DntcxuH3bq0Aswbd6E5mxyZMfGtVqQwTNlIHez+onuu9IkxmJsLQiFF2fuLorNptvMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:18:07.080175Z"},"content_sha256":"020a8ca05a73d244c984d895ba7f8d0b0a0ce92aed083fc9ee0335eb02490f7c","schema_version":"1.0","event_id":"sha256:020a8ca05a73d244c984d895ba7f8d0b0a0ce92aed083fc9ee0335eb02490f7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FQH4YXYCEQ2XRXBUAV64SUYZMZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Charles Ding, Dan Zhao, Justin Lin, Kazuhito Koishida, Lawrence Jang, Paul Pu Liang, Rogerio Bonatti, Yinheng Li","submitted_at":"2024-10-24T19:03:01Z","abstract_excerpt":"Videos are often used to learn or extract the necessary information to complete tasks in ways different than what text and static imagery alone can provide. However, many existing agent benchmarks neglect long-context video understanding, instead focusing on text or static image inputs. To bridge this gap, we introduce VideoWebArena (VideoWA), a benchmark for evaluating the capabilities of long-context multimodal agents for video understanding. VideoWA consists of 2,021 web agent tasks based on manually crafted video tutorials, which total almost four hours of content. For our benchmark, we de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19100","kind":"arxiv","version":3},"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/2410.19100/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":"2026-07-05T10:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"adzberlhNdkb1YDfSG5eKYx1fI9tny9sQWNKKAj95XX8WSD3M1MzSA7r0xfZI73VQZhYMsqxJDnDzjDFLo58CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:18:07.081205Z"},"content_sha256":"7a7dd87c44a5ff1356a3ad9525b9badcb9821afb85972640c240f537e70b55d7","schema_version":"1.0","event_id":"sha256:7a7dd87c44a5ff1356a3ad9525b9badcb9821afb85972640c240f537e70b55d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FQH4YXYCEQ2XRXBUAV64SUYZMZ/bundle.json","state_url":"https://pith.science/pith/FQH4YXYCEQ2XRXBUAV64SUYZMZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FQH4YXYCEQ2XRXBUAV64SUYZMZ/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":"2026-08-13T16:18:07Z","links":{"resolver":"https://pith.science/pith/FQH4YXYCEQ2XRXBUAV64SUYZMZ","bundle":"https://pith.science/pith/FQH4YXYCEQ2XRXBUAV64SUYZMZ/bundle.json","state":"https://pith.science/pith/FQH4YXYCEQ2XRXBUAV64SUYZMZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FQH4YXYCEQ2XRXBUAV64SUYZMZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FQH4YXYCEQ2XRXBUAV64SUYZMZ","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":"caf2005ebd3af02c85bb8d5eca2bbc1639c00f988a38d8f5938e719f9495669b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T19:03:01Z","title_canon_sha256":"3d72fedb3b6e9c537d960b41263a530f84f5d678539c0b2756bfac2b764a8e51"},"schema_version":"1.0","source":{"id":"2410.19100","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19100","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19100v3","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19100","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"FQH4YXYCEQ2X","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"FQH4YXYCEQ2XRXBU","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"FQH4YXYC","created_at":"2026-07-05T10:14:47Z"}],"graph_snapshots":[{"event_id":"sha256:7a7dd87c44a5ff1356a3ad9525b9badcb9821afb85972640c240f537e70b55d7","target":"graph","created_at":"2026-07-05T10:14:47Z","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/2410.19100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Videos are often used to learn or extract the necessary information to complete tasks in ways different than what text and static imagery alone can provide. However, many existing agent benchmarks neglect long-context video understanding, instead focusing on text or static image inputs. To bridge this gap, we introduce VideoWebArena (VideoWA), a benchmark for evaluating the capabilities of long-context multimodal agents for video understanding. VideoWA consists of 2,021 web agent tasks based on manually crafted video tutorials, which total almost four hours of content. For our benchmark, we de","authors_text":"Charles Ding, Dan Zhao, Justin Lin, Kazuhito Koishida, Lawrence Jang, Paul Pu Liang, Rogerio Bonatti, Yinheng Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T19:03:01Z","title":"VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19100","kind":"arxiv","version":3},"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":"sha256:020a8ca05a73d244c984d895ba7f8d0b0a0ce92aed083fc9ee0335eb02490f7c","target":"record","created_at":"2026-07-05T10:14:47Z","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":"caf2005ebd3af02c85bb8d5eca2bbc1639c00f988a38d8f5938e719f9495669b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T19:03:01Z","title_canon_sha256":"3d72fedb3b6e9c537d960b41263a530f84f5d678539c0b2756bfac2b764a8e51"},"schema_version":"1.0","source":{"id":"2410.19100","kind":"arxiv","version":3}},"canonical_sha256":"2c0fcc5f02243578dc34057dc95319665a2a42f8ecfdc2c5a039f43efcb22358","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c0fcc5f02243578dc34057dc95319665a2a42f8ecfdc2c5a039f43efcb22358","first_computed_at":"2026-07-05T10:14:47.120826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:47.120826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O+2CIX/ZYPr9063JNF9xXGA6wY7l85VMoSvrF93nFPzm1mt2RDv0RDUzf3Hibz3xdidNfd6tt7jkR+UReOOXDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:47.121356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.19100","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:020a8ca05a73d244c984d895ba7f8d0b0a0ce92aed083fc9ee0335eb02490f7c","sha256:7a7dd87c44a5ff1356a3ad9525b9badcb9821afb85972640c240f537e70b55d7"],"state_sha256":"602dd0dba0cee11654e170e84cfb13d7917c2775f09252bfef631149f986d3f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nNQhQLCkFxQLvSVZj8gxFkm3tuth144yV4ZKvUiunQ1cGiHj6dfM7LaEg5QewBQAA8Mr+F/BnF7o+f1z1tl7Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T16:18:07.088648Z","bundle_sha256":"ec39dc407be2d3e3ab21eec7be29bcdca9168e2ca75b0008f5438d90bc5b69b6"}}