{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7SDQCRZW2PYCVXJ55C57ZDMDM3","short_pith_number":"pith:7SDQCRZW","schema_version":"1.0","canonical_sha256":"fc87014736d3f02add3de8bbfc8d8366dba901c6e993f216fc845d5c0cf1e010","source":{"kind":"arxiv","id":"2306.01872","version":1},"attestation_state":"computed","paper":{"title":"Probabilistic Adaptation of Text-to-Video Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Dai, Dale Schuurmans, Joshua B. Tenenbaum, Mengjiao Yang, Pieter Abbeel, Yilun Du","submitted_at":"2023-06-02T19:00:17Z","abstract_excerpt":"Large text-to-video models trained on internet-scale data have demonstrated exceptional capabilities in generating high-fidelity videos from arbitrary textual descriptions. However, adapting these models to tasks with limited domain-specific data, such as animation or robotics videos, poses a significant computational challenge, since finetuning a pretrained large model can be prohibitively expensive. Inspired by how a small modifiable component (e.g., prompts, prefix-tuning) can adapt a large language model to perform new tasks without requiring access to the model weights, we investigate how"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.01872","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-02T19:00:17Z","cross_cats_sorted":[],"title_canon_sha256":"b60e154e67c9c6995635ce89beb74a118d2a3b55945e5982c86b984d4fe08f56","abstract_canon_sha256":"2049aa65fc4e0ef44bc48170dc08ee1ffb6bd72f8c6b482ac73e4c9ca62433be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:10.491983Z","signature_b64":"3uEaVTLTlAk1JeAHczKtopgGIhLQFmuLqInunqfQHzkJAzonQaWuh4UFz4UdJ4apwvomWjdNjklpzsesk/g5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc87014736d3f02add3de8bbfc8d8366dba901c6e993f216fc845d5c0cf1e010","last_reissued_at":"2026-07-05T06:17:10.491568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:10.491568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Adaptation of Text-to-Video Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Dai, Dale Schuurmans, Joshua B. Tenenbaum, Mengjiao Yang, Pieter Abbeel, Yilun Du","submitted_at":"2023-06-02T19:00:17Z","abstract_excerpt":"Large text-to-video models trained on internet-scale data have demonstrated exceptional capabilities in generating high-fidelity videos from arbitrary textual descriptions. However, adapting these models to tasks with limited domain-specific data, such as animation or robotics videos, poses a significant computational challenge, since finetuning a pretrained large model can be prohibitively expensive. Inspired by how a small modifiable component (e.g., prompts, prefix-tuning) can adapt a large language model to perform new tasks without requiring access to the model weights, we investigate how"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01872","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/2306.01872/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.01872","created_at":"2026-07-05T06:17:10.491630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01872v1","created_at":"2026-07-05T06:17:10.491630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01872","created_at":"2026-07-05T06:17:10.491630+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SDQCRZW2PYC","created_at":"2026-07-05T06:17:10.491630+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SDQCRZW2PYCVXJ5","created_at":"2026-07-05T06:17:10.491630+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SDQCRZW","created_at":"2026-07-05T06:17:10.491630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02661","citing_title":"Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20206","citing_title":"RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2404.12377","citing_title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18258","citing_title":"Long-Text-to-Image Generation via Compositional Prompt Decomposition","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7SDQCRZW2PYCVXJ55C57ZDMDM3","json":"https://pith.science/pith/7SDQCRZW2PYCVXJ55C57ZDMDM3.json","graph_json":"https://pith.science/api/pith-number/7SDQCRZW2PYCVXJ55C57ZDMDM3/graph.json","events_json":"https://pith.science/api/pith-number/7SDQCRZW2PYCVXJ55C57ZDMDM3/events.json","paper":"https://pith.science/paper/7SDQCRZW"},"agent_actions":{"view_html":"https://pith.science/pith/7SDQCRZW2PYCVXJ55C57ZDMDM3","download_json":"https://pith.science/pith/7SDQCRZW2PYCVXJ55C57ZDMDM3.json","view_paper":"https://pith.science/paper/7SDQCRZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01872&json=true","fetch_graph":"https://pith.science/api/pith-number/7SDQCRZW2PYCVXJ55C57ZDMDM3/graph.json","fetch_events":"https://pith.science/api/pith-number/7SDQCRZW2PYCVXJ55C57ZDMDM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SDQCRZW2PYCVXJ55C57ZDMDM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SDQCRZW2PYCVXJ55C57ZDMDM3/action/storage_attestation","attest_author":"https://pith.science/pith/7SDQCRZW2PYCVXJ55C57ZDMDM3/action/author_attestation","sign_citation":"https://pith.science/pith/7SDQCRZW2PYCVXJ55C57ZDMDM3/action/citation_signature","submit_replication":"https://pith.science/pith/7SDQCRZW2PYCVXJ55C57ZDMDM3/action/replication_record"}},"created_at":"2026-07-05T06:17:10.491630+00:00","updated_at":"2026-07-05T06:17:10.491630+00:00"}