{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7YCT6GPLDBNFAPUYRWAIQTDHXO","short_pith_number":"pith:7YCT6GPL","canonical_record":{"source":{"id":"2212.04501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-08T18:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"b58d3176bf6cc16350c745a2532095f345e721cb837ef9360429ea5eff9d6df3","abstract_canon_sha256":"a07019e0d71558c444ea819d1e492d6cc8f75cb06bdc2ba3410b94dbe4eff650"},"schema_version":"1.0"},"canonical_sha256":"fe053f19eb185a503e988d80884c67bbbad349cdb98b380cf8e59144ac93d3c3","source":{"kind":"arxiv","id":"2212.04501","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.04501","created_at":"2026-07-05T05:23:41Z"},{"alias_kind":"arxiv_version","alias_value":"2212.04501v1","created_at":"2026-07-05T05:23:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04501","created_at":"2026-07-05T05:23:41Z"},{"alias_kind":"pith_short_12","alias_value":"7YCT6GPLDBNF","created_at":"2026-07-05T05:23:41Z"},{"alias_kind":"pith_short_16","alias_value":"7YCT6GPLDBNFAPUY","created_at":"2026-07-05T05:23:41Z"},{"alias_kind":"pith_short_8","alias_value":"7YCT6GPL","created_at":"2026-07-05T05:23:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7YCT6GPLDBNFAPUYRWAIQTDHXO","target":"record","payload":{"canonical_record":{"source":{"id":"2212.04501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-08T18:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"b58d3176bf6cc16350c745a2532095f345e721cb837ef9360429ea5eff9d6df3","abstract_canon_sha256":"a07019e0d71558c444ea819d1e492d6cc8f75cb06bdc2ba3410b94dbe4eff650"},"schema_version":"1.0"},"canonical_sha256":"fe053f19eb185a503e988d80884c67bbbad349cdb98b380cf8e59144ac93d3c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:41.594680Z","signature_b64":"hbMMpzlG8WgbjjK9S4UQ3Yanxogz/aNgg0Z4DwDZ6Urhibjf5C+PsW99G0mgdhvu0hutjCxPYkIviw2SJ5BEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe053f19eb185a503e988d80884c67bbbad349cdb98b380cf8e59144ac93d3c3","last_reissued_at":"2026-07-05T05:23:41.593748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:41.593748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.04501","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:23:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TTv90I+Kpkw3zyyBAFcY44XBZssiYSLIVbKRsSuIemjzegJvSxfZePkbm6++9w6IfPky7TK+EdkZoiwR+h0uAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:14:11.992818Z"},"content_sha256":"056b2b343aa82e71e852bc22d25ace21bc7088e5dc8028de6c7b0f30990c2582","schema_version":"1.0","event_id":"sha256:056b2b343aa82e71e852bc22d25ace21bc7088e5dc8028de6c7b0f30990c2582"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7YCT6GPLDBNFAPUYRWAIQTDHXO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Video Representations from Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ishan Misra, Philipp Kr\\\"ahenb\\\"uhl, Rohit Girdhar, Yue Zhao","submitted_at":"2022-12-08T18:59:59Z","abstract_excerpt":"We introduce LaViLa, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be conditioned on visual input, and finetune them to create automatic video narrators. Our auto-generated narrations offer a number of advantages, including dense coverage of long videos, better temporal synchronization of the visual information and text, and much higher diversity of text. The video-text embedding learned contrastively with these additional auto-generated narrations outperforms the previous state-of-the-art on multiple firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04501","kind":"arxiv","version":1},"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/2212.04501/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":"2026-07-05T05:23:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FT+wm8Wnlt/SOcyAv3tv8PqWvZPy8U4N5Y3nH371a03dCCxWOb7baSdf9/1zkxU6TYrFwQeZ1/jaGxgOiEudDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:14:11.993319Z"},"content_sha256":"1627fe55d5b6171b9826f30e9309de68970556763d911e3cb65472d4a2359749","schema_version":"1.0","event_id":"sha256:1627fe55d5b6171b9826f30e9309de68970556763d911e3cb65472d4a2359749"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO/bundle.json","state_url":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO/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":"2026-08-08T09:14:11Z","links":{"resolver":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO","bundle":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO/bundle.json","state":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7YCT6GPLDBNFAPUYRWAIQTDHXO","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":"a07019e0d71558c444ea819d1e492d6cc8f75cb06bdc2ba3410b94dbe4eff650","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-08T18:59:59Z","title_canon_sha256":"b58d3176bf6cc16350c745a2532095f345e721cb837ef9360429ea5eff9d6df3"},"schema_version":"1.0","source":{"id":"2212.04501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.04501","created_at":"2026-07-05T05:23:41Z"},{"alias_kind":"arxiv_version","alias_value":"2212.04501v1","created_at":"2026-07-05T05:23:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04501","created_at":"2026-07-05T05:23:41Z"},{"alias_kind":"pith_short_12","alias_value":"7YCT6GPLDBNF","created_at":"2026-07-05T05:23:41Z"},{"alias_kind":"pith_short_16","alias_value":"7YCT6GPLDBNFAPUY","created_at":"2026-07-05T05:23:41Z"},{"alias_kind":"pith_short_8","alias_value":"7YCT6GPL","created_at":"2026-07-05T05:23:41Z"}],"graph_snapshots":[{"event_id":"sha256:1627fe55d5b6171b9826f30e9309de68970556763d911e3cb65472d4a2359749","target":"graph","created_at":"2026-07-05T05:23:41Z","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/2212.04501/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce LaViLa, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be conditioned on visual input, and finetune them to create automatic video narrators. Our auto-generated narrations offer a number of advantages, including dense coverage of long videos, better temporal synchronization of the visual information and text, and much higher diversity of text. The video-text embedding learned contrastively with these additional auto-generated narrations outperforms the previous state-of-the-art on multiple firs","authors_text":"Ishan Misra, Philipp Kr\\\"ahenb\\\"uhl, Rohit Girdhar, Yue Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-08T18:59:59Z","title":"Learning Video Representations from Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04501","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":"sha256:056b2b343aa82e71e852bc22d25ace21bc7088e5dc8028de6c7b0f30990c2582","target":"record","created_at":"2026-07-05T05:23:41Z","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":"a07019e0d71558c444ea819d1e492d6cc8f75cb06bdc2ba3410b94dbe4eff650","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-08T18:59:59Z","title_canon_sha256":"b58d3176bf6cc16350c745a2532095f345e721cb837ef9360429ea5eff9d6df3"},"schema_version":"1.0","source":{"id":"2212.04501","kind":"arxiv","version":1}},"canonical_sha256":"fe053f19eb185a503e988d80884c67bbbad349cdb98b380cf8e59144ac93d3c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe053f19eb185a503e988d80884c67bbbad349cdb98b380cf8e59144ac93d3c3","first_computed_at":"2026-07-05T05:23:41.593748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:41.593748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hbMMpzlG8WgbjjK9S4UQ3Yanxogz/aNgg0Z4DwDZ6Urhibjf5C+PsW99G0mgdhvu0hutjCxPYkIviw2SJ5BEAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:41.594680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.04501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:056b2b343aa82e71e852bc22d25ace21bc7088e5dc8028de6c7b0f30990c2582","sha256:1627fe55d5b6171b9826f30e9309de68970556763d911e3cb65472d4a2359749"],"state_sha256":"da28086e089fe835e9849ca8bb875ace8abf53c8ef02dc8d8ff2e4716ca595ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kqpa2satmlP9W7maIydlM/aIZVPxjDisl+lcMwMcAOfglgYyVhHfd5NvBcMPwkEeMOUlgk5uAGi0MfYrEWEPAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:14:11.998610Z","bundle_sha256":"f6a257732451c210b7be2b90f0605c8d2f0016f784a880b5547a34f29018c47b"}}