{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GJRY2JKJTS4BNOH7AHLHFVKCO5","short_pith_number":"pith:GJRY2JKJ","canonical_record":{"source":{"id":"2410.02768","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T05:17:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"79325986a1eaf3ca9538c6a5a2aaf298b4349ce848357e7612c734216981dd62","abstract_canon_sha256":"a49d05cefb135c276e319e754f09330b52cf341f4d0cceb017eb5f54d859e509"},"schema_version":"1.0"},"canonical_sha256":"32638d25499cb816b8ff01d672d5427761d27f20ca8bc64f8811e0d1a6ad9779","source":{"kind":"arxiv","id":"2410.02768","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02768","created_at":"2026-07-05T10:59:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02768v2","created_at":"2026-07-05T10:59:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02768","created_at":"2026-07-05T10:59:02Z"},{"alias_kind":"pith_short_12","alias_value":"GJRY2JKJTS4B","created_at":"2026-07-05T10:59:02Z"},{"alias_kind":"pith_short_16","alias_value":"GJRY2JKJTS4BNOH7","created_at":"2026-07-05T10:59:02Z"},{"alias_kind":"pith_short_8","alias_value":"GJRY2JKJ","created_at":"2026-07-05T10:59:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GJRY2JKJTS4BNOH7AHLHFVKCO5","target":"record","payload":{"canonical_record":{"source":{"id":"2410.02768","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T05:17:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"79325986a1eaf3ca9538c6a5a2aaf298b4349ce848357e7612c734216981dd62","abstract_canon_sha256":"a49d05cefb135c276e319e754f09330b52cf341f4d0cceb017eb5f54d859e509"},"schema_version":"1.0"},"canonical_sha256":"32638d25499cb816b8ff01d672d5427761d27f20ca8bc64f8811e0d1a6ad9779","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:02.363853Z","signature_b64":"mhSLS4OzZR+3rQ1dAIY/e2j9TakzxNgKANEfEeVvL+Js4+SBYXm+WnSBzBXbOjxFeRsL3POzU/jA57xCr8yMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32638d25499cb816b8ff01d672d5427761d27f20ca8bc64f8811e0d1a6ad9779","last_reissued_at":"2026-07-05T10:59:02.363347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:02.363347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.02768","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":"2026-07-05T10:59:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WKShfBnGWZDPZm4L5YY1QqUrs0Yer6Dfc0EPBSsh4FokaqgIPtMSxbr1IT/XkkfZdTQumut6CfFHUxUd7aOEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:00:03.417764Z"},"content_sha256":"af38bf353d291c8fe13198603e0f8535b5c09600dfea76485bc11d25f57197f2","schema_version":"1.0","event_id":"sha256:af38bf353d291c8fe13198603e0f8535b5c09600dfea76485bc11d25f57197f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GJRY2JKJTS4BNOH7AHLHFVKCO5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty-Guided Self-Questioning and Answering for Video-Language Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Han Fang, Haojian Huang, Hao Sun, Jin Chen, Kaijing Ma, Mehdi Hosseinzadeh, Zhe Liu","submitted_at":"2024-09-17T05:17:37Z","abstract_excerpt":"The development of multi-modal models has been rapidly advancing, with some demonstrating remarkable capabilities. However, annotating video-text pairs remains expensive and insufficient. Take video question answering (VideoQA) tasks as an example, human annotated questions and answers often cover only part of the video, since the corresponding text is often short and monotonous, leading to underutilization of video. To address this, we propose a Bootstrapping Video-Language Alignment framework (BoViLA), a self-training method that augments question samples during training process through LLM-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02768","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/2410.02768/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":"2026-07-05T10:59:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ChKQCPW7UKO7y3ea397UhO9ENenSZrbYk+e1+gTS5wM57VrPDubYxDVKxIR7rIig2iLfNNpJcE3w1F5XVthSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:00:03.418394Z"},"content_sha256":"47cb8da3ffdfea374f2abf623621c715c0c91f0c02d35528f18a526601c9ddde","schema_version":"1.0","event_id":"sha256:47cb8da3ffdfea374f2abf623621c715c0c91f0c02d35528f18a526601c9ddde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GJRY2JKJTS4BNOH7AHLHFVKCO5/bundle.json","state_url":"https://pith.science/pith/GJRY2JKJTS4BNOH7AHLHFVKCO5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GJRY2JKJTS4BNOH7AHLHFVKCO5/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":"2026-08-22T15:00:03Z","links":{"resolver":"https://pith.science/pith/GJRY2JKJTS4BNOH7AHLHFVKCO5","bundle":"https://pith.science/pith/GJRY2JKJTS4BNOH7AHLHFVKCO5/bundle.json","state":"https://pith.science/pith/GJRY2JKJTS4BNOH7AHLHFVKCO5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GJRY2JKJTS4BNOH7AHLHFVKCO5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GJRY2JKJTS4BNOH7AHLHFVKCO5","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":"a49d05cefb135c276e319e754f09330b52cf341f4d0cceb017eb5f54d859e509","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T05:17:37Z","title_canon_sha256":"79325986a1eaf3ca9538c6a5a2aaf298b4349ce848357e7612c734216981dd62"},"schema_version":"1.0","source":{"id":"2410.02768","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02768","created_at":"2026-07-05T10:59:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02768v2","created_at":"2026-07-05T10:59:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02768","created_at":"2026-07-05T10:59:02Z"},{"alias_kind":"pith_short_12","alias_value":"GJRY2JKJTS4B","created_at":"2026-07-05T10:59:02Z"},{"alias_kind":"pith_short_16","alias_value":"GJRY2JKJTS4BNOH7","created_at":"2026-07-05T10:59:02Z"},{"alias_kind":"pith_short_8","alias_value":"GJRY2JKJ","created_at":"2026-07-05T10:59:02Z"}],"graph_snapshots":[{"event_id":"sha256:47cb8da3ffdfea374f2abf623621c715c0c91f0c02d35528f18a526601c9ddde","target":"graph","created_at":"2026-07-05T10:59:02Z","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/2410.02768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of multi-modal models has been rapidly advancing, with some demonstrating remarkable capabilities. However, annotating video-text pairs remains expensive and insufficient. Take video question answering (VideoQA) tasks as an example, human annotated questions and answers often cover only part of the video, since the corresponding text is often short and monotonous, leading to underutilization of video. To address this, we propose a Bootstrapping Video-Language Alignment framework (BoViLA), a self-training method that augments question samples during training process through LLM-","authors_text":"Han Fang, Haojian Huang, Hao Sun, Jin Chen, Kaijing Ma, Mehdi Hosseinzadeh, Zhe Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T05:17:37Z","title":"Uncertainty-Guided Self-Questioning and Answering for Video-Language Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02768","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:af38bf353d291c8fe13198603e0f8535b5c09600dfea76485bc11d25f57197f2","target":"record","created_at":"2026-07-05T10:59:02Z","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":"a49d05cefb135c276e319e754f09330b52cf341f4d0cceb017eb5f54d859e509","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T05:17:37Z","title_canon_sha256":"79325986a1eaf3ca9538c6a5a2aaf298b4349ce848357e7612c734216981dd62"},"schema_version":"1.0","source":{"id":"2410.02768","kind":"arxiv","version":2}},"canonical_sha256":"32638d25499cb816b8ff01d672d5427761d27f20ca8bc64f8811e0d1a6ad9779","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32638d25499cb816b8ff01d672d5427761d27f20ca8bc64f8811e0d1a6ad9779","first_computed_at":"2026-07-05T10:59:02.363347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:02.363347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mhSLS4OzZR+3rQ1dAIY/e2j9TakzxNgKANEfEeVvL+Js4+SBYXm+WnSBzBXbOjxFeRsL3POzU/jA57xCr8yMCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:02.363853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02768","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af38bf353d291c8fe13198603e0f8535b5c09600dfea76485bc11d25f57197f2","sha256:47cb8da3ffdfea374f2abf623621c715c0c91f0c02d35528f18a526601c9ddde"],"state_sha256":"18a9ede69b77d86d9b4e208314e0f01548402169983615d532354607b36a0436"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"msSibL25xLVfJ53ol/bD7jB3+1Ojq6sjnBo8D8LEc3Ds1hnRpHZDRz64xnSEyJlj9q/GBDev0Mutb2d+cC0lBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T15:00:03.423260Z","bundle_sha256":"797dc4a30ad9516e9a46cfe3e42eb27ddea101fa3a00ce6c5353dd5ee14a770d"}}