{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BF3V5GZGVFBPEXLFATSAXBSGIS","short_pith_number":"pith:BF3V5GZG","canonical_record":{"source":{"id":"2401.06129","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T18:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"52d094e4e77abb8335748d97e4572e71a8c4f2feddd1cd1c11b34fb917a26209","abstract_canon_sha256":"1e9fa6fa95b823bdddf8f75a6a92f7a14ce3363351742e75ef3e4944b18075da"},"schema_version":"1.0"},"canonical_sha256":"09775e9b26a942f25d6504e40b864644b34155f6c99074121dec736bdfeb0da0","source":{"kind":"arxiv","id":"2401.06129","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06129","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06129v2","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06129","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"BF3V5GZGVFBP","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"BF3V5GZGVFBPEXLF","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"BF3V5GZG","created_at":"2026-07-05T08:08:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BF3V5GZGVFBPEXLFATSAXBSGIS","target":"record","payload":{"canonical_record":{"source":{"id":"2401.06129","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T18:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"52d094e4e77abb8335748d97e4572e71a8c4f2feddd1cd1c11b34fb917a26209","abstract_canon_sha256":"1e9fa6fa95b823bdddf8f75a6a92f7a14ce3363351742e75ef3e4944b18075da"},"schema_version":"1.0"},"canonical_sha256":"09775e9b26a942f25d6504e40b864644b34155f6c99074121dec736bdfeb0da0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:20.133795Z","signature_b64":"MUq39gMMzo9M4w4KLQdC9jF1T837yd3G7JCs7HlP31DyX1dvLFK+4vK0ebiuEzdgCfN3yTlcAqsv2AFbYC4JAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09775e9b26a942f25d6504e40b864644b34155f6c99074121dec736bdfeb0da0","last_reissued_at":"2026-07-05T08:08:20.133236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:20.133236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.06129","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":"2026-07-05T08:08:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SuneLvpMcerUluM4eciTsfEWoHY1YGl8YDEUf9KsdXrRjdBo+puPqVJOQi8TjLPeMrR93BgkoYIpc45mOIG+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:17:28.590667Z"},"content_sha256":"655277603ecbbffd1976556754457cee0c377f7ba515bb98fa645c4076538e27","schema_version":"1.0","event_id":"sha256:655277603ecbbffd1976556754457cee0c377f7ba515bb98fa645c4076538e27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BF3V5GZGVFBPEXLFATSAXBSGIS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distilling Vision-Language Models on Millions of Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Chun-Te Chu, Florian Schroff, Hartwig Adam, Hui Miao, Jialin Wu, Liangzhe Yuan, Long Zhao, Philipp Kr\\\"ahenb\\\"uhl, Ting Liu, Xingyi Zhou, Yue Zhao","submitted_at":"2024-01-11T18:59:53Z","abstract_excerpt":"The recent advance in vision-language models is largely attributed to the abundance of image-text data. We aim to replicate this success for video-language models, but there simply is not enough human-curated video-text data available. We thus resort to fine-tuning a video-language model from a strong image-language baseline with synthesized instructional data. The resulting video model by video-instruction-tuning (VIIT) is then used to auto-label millions of videos to generate high-quality captions. We show the adapted video-language model performs well on a wide range of video-language bench"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06129","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/2401.06129/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":"2026-07-05T08:08:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fkkfht13Wb/tWcJVuj43Yv4138sBIe0qDyYSYgizEtyTqc5/4fUy/i3eynPI00AaD/qHhGHS21kONjKlJIciCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:17:28.591329Z"},"content_sha256":"058bc230e721590188f744f5b9de1911ea8a3c7636f35d64b7bb5ded843c354c","schema_version":"1.0","event_id":"sha256:058bc230e721590188f744f5b9de1911ea8a3c7636f35d64b7bb5ded843c354c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BF3V5GZGVFBPEXLFATSAXBSGIS/bundle.json","state_url":"https://pith.science/pith/BF3V5GZGVFBPEXLFATSAXBSGIS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BF3V5GZGVFBPEXLFATSAXBSGIS/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":"2026-08-12T07:17:28Z","links":{"resolver":"https://pith.science/pith/BF3V5GZGVFBPEXLFATSAXBSGIS","bundle":"https://pith.science/pith/BF3V5GZGVFBPEXLFATSAXBSGIS/bundle.json","state":"https://pith.science/pith/BF3V5GZGVFBPEXLFATSAXBSGIS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BF3V5GZGVFBPEXLFATSAXBSGIS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BF3V5GZGVFBPEXLFATSAXBSGIS","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":"1e9fa6fa95b823bdddf8f75a6a92f7a14ce3363351742e75ef3e4944b18075da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T18:59:53Z","title_canon_sha256":"52d094e4e77abb8335748d97e4572e71a8c4f2feddd1cd1c11b34fb917a26209"},"schema_version":"1.0","source":{"id":"2401.06129","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06129","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06129v2","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06129","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"BF3V5GZGVFBP","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"BF3V5GZGVFBPEXLF","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"BF3V5GZG","created_at":"2026-07-05T08:08:20Z"}],"graph_snapshots":[{"event_id":"sha256:058bc230e721590188f744f5b9de1911ea8a3c7636f35d64b7bb5ded843c354c","target":"graph","created_at":"2026-07-05T08:08:20Z","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/2401.06129/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent advance in vision-language models is largely attributed to the abundance of image-text data. We aim to replicate this success for video-language models, but there simply is not enough human-curated video-text data available. We thus resort to fine-tuning a video-language model from a strong image-language baseline with synthesized instructional data. The resulting video model by video-instruction-tuning (VIIT) is then used to auto-label millions of videos to generate high-quality captions. We show the adapted video-language model performs well on a wide range of video-language bench","authors_text":"Boqing Gong, Chun-Te Chu, Florian Schroff, Hartwig Adam, Hui Miao, Jialin Wu, Liangzhe Yuan, Long Zhao, Philipp Kr\\\"ahenb\\\"uhl, Ting Liu, Xingyi Zhou, Yue Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T18:59:53Z","title":"Distilling Vision-Language Models on Millions of Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06129","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":"sha256:655277603ecbbffd1976556754457cee0c377f7ba515bb98fa645c4076538e27","target":"record","created_at":"2026-07-05T08:08:20Z","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":"1e9fa6fa95b823bdddf8f75a6a92f7a14ce3363351742e75ef3e4944b18075da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T18:59:53Z","title_canon_sha256":"52d094e4e77abb8335748d97e4572e71a8c4f2feddd1cd1c11b34fb917a26209"},"schema_version":"1.0","source":{"id":"2401.06129","kind":"arxiv","version":2}},"canonical_sha256":"09775e9b26a942f25d6504e40b864644b34155f6c99074121dec736bdfeb0da0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09775e9b26a942f25d6504e40b864644b34155f6c99074121dec736bdfeb0da0","first_computed_at":"2026-07-05T08:08:20.133236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:20.133236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MUq39gMMzo9M4w4KLQdC9jF1T837yd3G7JCs7HlP31DyX1dvLFK+4vK0ebiuEzdgCfN3yTlcAqsv2AFbYC4JAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:20.133795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06129","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:655277603ecbbffd1976556754457cee0c377f7ba515bb98fa645c4076538e27","sha256:058bc230e721590188f744f5b9de1911ea8a3c7636f35d64b7bb5ded843c354c"],"state_sha256":"1488157b4ad405d6ab3ff58ea03aabee763cb959966c604f721e5f94cf375e16"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BeegMxTOpYvuMJuUIhb7tlyLfdNVsyNX/vZuCrx1IHYB/fxHDnN96HmnwaHId4TOADw51YDiT+8kRWjuTb7iDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T07:17:28.597786Z","bundle_sha256":"26b9b2cb1c45c0d1310fa9af58d2c11bd4bf1d5cbc7d86baf9c74e8fa40a1cc5"}}