{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MOTN2NH4VL3P3IH66YPNAZTUSC","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":"443885ba5bbdbd1cbf8f1f8c102fa3ac662f3cc84bbb2c17717c8182e6610c91","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T02:44:27Z","title_canon_sha256":"c4be6e52aa63d1cc2cd78104dd34f1f82abbc09bc830de7c02214c496e323f24"},"schema_version":"1.0","source":{"id":"2605.21917","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21917","created_at":"2026-05-22T01:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21917v1","created_at":"2026-05-22T01:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21917","created_at":"2026-05-22T01:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"MOTN2NH4VL3P","created_at":"2026-05-22T01:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"MOTN2NH4VL3P3IH6","created_at":"2026-05-22T01:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"MOTN2NH4","created_at":"2026-05-22T01:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:ce43226b5c7a29a2a93a985f37ff8814e22f527953f2a4e8f3bcf51ef1c98deb","target":"graph","created_at":"2026-05-22T01:04:14Z","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/2605.21917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training Vision Language Models (VLMs) for video event reasoning requires high-quality structured annotations capturing not only what happened, but when, where, why, and with what consequence, at a scale manual labelling cannot support. We present MAVEN (Multi-stage Agentic Video Event aNnotation), a multi-stage agentic pipeline that turns raw videos into multi-task training data with Chain-of-Thought (CoT) reasoning traces, organized around a designated Event of Focus. At its core, MAVEN synthesizes a Multi-Scale Spatio-Temporal Event Description (MSTED) from three complementary caption level","authors_text":"Han Zhang, Tian Zheng, Tomasz Kornuta, Vidya Murali, Wanting Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T02:44:27Z","title":"MAVEN: A Multi-stage Agentic Annotation Pipeline for Video Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21917","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":"sha256:7468cea62773fa0d681f48fc64186d1a5e237ed867f13f605e3191247edcad8d","target":"record","created_at":"2026-05-22T01:04:14Z","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":"443885ba5bbdbd1cbf8f1f8c102fa3ac662f3cc84bbb2c17717c8182e6610c91","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T02:44:27Z","title_canon_sha256":"c4be6e52aa63d1cc2cd78104dd34f1f82abbc09bc830de7c02214c496e323f24"},"schema_version":"1.0","source":{"id":"2605.21917","kind":"arxiv","version":1}},"canonical_sha256":"63a6dd34fcaaf6fda0fef61ed0667490a18fb0ad4bc57e21578748ad85caac79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63a6dd34fcaaf6fda0fef61ed0667490a18fb0ad4bc57e21578748ad85caac79","first_computed_at":"2026-05-22T01:04:14.561991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:14.561991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qW8BgT9pS39bnMLgm5Jj7rlSpAqsFMoyCVVuN3fCE8GnWJaW29ur0VFLff1w5h8SpHx0T8i8jFmFTXPv1OoKAA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:14.562864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21917","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7468cea62773fa0d681f48fc64186d1a5e237ed867f13f605e3191247edcad8d","sha256:ce43226b5c7a29a2a93a985f37ff8814e22f527953f2a4e8f3bcf51ef1c98deb"],"state_sha256":"3642e1875e2f1b71a6d7c8ff9d214d4ebccc7d1ad1bf7b15b78bde425d8cb2c4"}