{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RLKEZFWWC4ROM2B34EC2AKKJ7W","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":"8d467d18113208aaa29a6d0bcf148447bde3a40095f21d8c383eec3dd6807437","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T11:54:55Z","title_canon_sha256":"a06473a087928fb0f3e23f654dd7def3943ee51260a139d5e5c8acf6a6fceeee"},"schema_version":"1.0","source":{"id":"2412.00161","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00161","created_at":"2026-07-05T10:41:18Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00161v2","created_at":"2026-07-05T10:41:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00161","created_at":"2026-07-05T10:41:18Z"},{"alias_kind":"pith_short_12","alias_value":"RLKEZFWWC4RO","created_at":"2026-07-05T10:41:18Z"},{"alias_kind":"pith_short_16","alias_value":"RLKEZFWWC4ROM2B3","created_at":"2026-07-05T10:41:18Z"},{"alias_kind":"pith_short_8","alias_value":"RLKEZFWW","created_at":"2026-07-05T10:41:18Z"}],"graph_snapshots":[{"event_id":"sha256:a1b125cdd9f529786ee4616eff61ff6eaea1dcc98473a3aaeb4ceba148d307fc","target":"graph","created_at":"2026-07-05T10:41:18Z","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/2412.00161/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Large Language Models (Video-LLMs) have recently shown strong performance in basic video understanding tasks, such as captioning and coarse-grained question answering, but struggle with compositional reasoning that requires multi-step spatio-temporal inference across object relations, interactions, and events. The hurdles to enhancing this capability include extensive manual labor, the lack of spatio-temporal compositionality in existing data and the absence of explicit reasoning supervision. In this paper, we propose STEP, a novel graph-guided self-training method that enables Video-LLM","authors_text":"Haiyi Qiu, Juncheng Li, Kaihang Pan, Long Qian, Minghe Gao, Qifan Yu, Siliang Tang, Tat-Seng Chua, Wenjie Wang, Yueting Zhuang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T11:54:55Z","title":"STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00161","kind":"arxiv","version":2},"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":"sha256:2335014136545294ecbdf157a77872004c863489a24745fd75c12f5fe4f1d2ff","target":"record","created_at":"2026-07-05T10:41:18Z","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":"8d467d18113208aaa29a6d0bcf148447bde3a40095f21d8c383eec3dd6807437","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T11:54:55Z","title_canon_sha256":"a06473a087928fb0f3e23f654dd7def3943ee51260a139d5e5c8acf6a6fceeee"},"schema_version":"1.0","source":{"id":"2412.00161","kind":"arxiv","version":2}},"canonical_sha256":"8ad44c96d61722e6683be105a02949fdabef950933a3868cc1fad99bb98e69e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ad44c96d61722e6683be105a02949fdabef950933a3868cc1fad99bb98e69e9","first_computed_at":"2026-07-05T10:41:18.039226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:18.039226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EiMFRmhSR37JE6pmZam3FXOe6E5lX/tr/zuRbv1zD/C8jMoNCtZ6aF3Lcw4HwU9g9It1SYSsOejksrEaXsGGCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:18.039758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00161","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2335014136545294ecbdf157a77872004c863489a24745fd75c12f5fe4f1d2ff","sha256:a1b125cdd9f529786ee4616eff61ff6eaea1dcc98473a3aaeb4ceba148d307fc"],"state_sha256":"52e3c82a1e8f3526fa649c0189d519e6cb9b9f10cb294803da289b815d207651"}