{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RLKEZFWWC4ROM2B34EC2AKKJ7W","short_pith_number":"pith:RLKEZFWW","canonical_record":{"source":{"id":"2412.00161","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T11:54:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a06473a087928fb0f3e23f654dd7def3943ee51260a139d5e5c8acf6a6fceeee","abstract_canon_sha256":"8d467d18113208aaa29a6d0bcf148447bde3a40095f21d8c383eec3dd6807437"},"schema_version":"1.0"},"canonical_sha256":"8ad44c96d61722e6683be105a02949fdabef950933a3868cc1fad99bb98e69e9","source":{"kind":"arxiv","id":"2412.00161","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RLKEZFWWC4ROM2B34EC2AKKJ7W","target":"record","payload":{"canonical_record":{"source":{"id":"2412.00161","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T11:54:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a06473a087928fb0f3e23f654dd7def3943ee51260a139d5e5c8acf6a6fceeee","abstract_canon_sha256":"8d467d18113208aaa29a6d0bcf148447bde3a40095f21d8c383eec3dd6807437"},"schema_version":"1.0"},"canonical_sha256":"8ad44c96d61722e6683be105a02949fdabef950933a3868cc1fad99bb98e69e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:18.039758Z","signature_b64":"EiMFRmhSR37JE6pmZam3FXOe6E5lX/tr/zuRbv1zD/C8jMoNCtZ6aF3Lcw4HwU9g9It1SYSsOejksrEaXsGGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ad44c96d61722e6683be105a02949fdabef950933a3868cc1fad99bb98e69e9","last_reissued_at":"2026-07-05T10:41:18.039226Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:18.039226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.00161","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:41:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ksRCzT/5SgaGNz6Z8c/tq+dJXQIAt3rYbPhxt4PwTu0RoP1jMg6MHJBxGMi0p0TwSQBAMNJRoTSiVjNZ5D9CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:51:01.466746Z"},"content_sha256":"2335014136545294ecbdf157a77872004c863489a24745fd75c12f5fe4f1d2ff","schema_version":"1.0","event_id":"sha256:2335014136545294ecbdf157a77872004c863489a24745fd75c12f5fe4f1d2ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RLKEZFWWC4ROM2B34EC2AKKJ7W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Haiyi Qiu, Juncheng Li, Kaihang Pan, Long Qian, Minghe Gao, Qifan Yu, Siliang Tang, Tat-Seng Chua, Wenjie Wang, Yueting Zhuang","submitted_at":"2024-11-29T11:54:55Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00161","kind":"arxiv","version":2},"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/2412.00161/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":"2026-07-05T10:41:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5PSqs1ASnWU65spFTkiHvLJJNHjTlMC1rZKXHmBNhoAIHNslgbgWgHjuzq4wo9mAzHcSQWR49mftRfLPq5zFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:51:01.467288Z"},"content_sha256":"a1b125cdd9f529786ee4616eff61ff6eaea1dcc98473a3aaeb4ceba148d307fc","schema_version":"1.0","event_id":"sha256:a1b125cdd9f529786ee4616eff61ff6eaea1dcc98473a3aaeb4ceba148d307fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLKEZFWWC4ROM2B34EC2AKKJ7W/bundle.json","state_url":"https://pith.science/pith/RLKEZFWWC4ROM2B34EC2AKKJ7W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLKEZFWWC4ROM2B34EC2AKKJ7W/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":"2026-08-08T08:51:01Z","links":{"resolver":"https://pith.science/pith/RLKEZFWWC4ROM2B34EC2AKKJ7W","bundle":"https://pith.science/pith/RLKEZFWWC4ROM2B34EC2AKKJ7W/bundle.json","state":"https://pith.science/pith/RLKEZFWWC4ROM2B34EC2AKKJ7W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLKEZFWWC4ROM2B34EC2AKKJ7W/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NbqrITy6UHIOTCqqzI+plSL70degCmmBb3ob6cuHJpfh9zP5oy6XsgyEdcBzp7gbymtiS+jK4zj0h3kHs5giAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:51:01.472132Z","bundle_sha256":"dd54254bb8d27df7aef6cc5247c2e20b3b5dfc0ab24d1aa5094a1aa7efe1a780"}}