{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DFNIMTTEWTSRMD7V2V556MW2CB","short_pith_number":"pith:DFNIMTTE","canonical_record":{"source":{"id":"2503.20491","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T12:28:20Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"75b3c90d36548045bbb7be0e2c34d8ccb6070eabc8345449c206c4c02ff37d05","abstract_canon_sha256":"2cb148e9bfcc4817eff2c11f34347c96622888e56f0ef360f5ec9cc000c3f33f"},"schema_version":"1.0"},"canonical_sha256":"195a864e64b4e5160ff5d57bdf32da10786ce5489ed636ded19d94b400985dd6","source":{"kind":"arxiv","id":"2503.20491","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.20491","created_at":"2026-07-05T12:01:59Z"},{"alias_kind":"arxiv_version","alias_value":"2503.20491v2","created_at":"2026-07-05T12:01:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20491","created_at":"2026-07-05T12:01:59Z"},{"alias_kind":"pith_short_12","alias_value":"DFNIMTTEWTSR","created_at":"2026-07-05T12:01:59Z"},{"alias_kind":"pith_short_16","alias_value":"DFNIMTTEWTSRMD7V","created_at":"2026-07-05T12:01:59Z"},{"alias_kind":"pith_short_8","alias_value":"DFNIMTTE","created_at":"2026-07-05T12:01:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DFNIMTTEWTSRMD7V2V556MW2CB","target":"record","payload":{"canonical_record":{"source":{"id":"2503.20491","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T12:28:20Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"75b3c90d36548045bbb7be0e2c34d8ccb6070eabc8345449c206c4c02ff37d05","abstract_canon_sha256":"2cb148e9bfcc4817eff2c11f34347c96622888e56f0ef360f5ec9cc000c3f33f"},"schema_version":"1.0"},"canonical_sha256":"195a864e64b4e5160ff5d57bdf32da10786ce5489ed636ded19d94b400985dd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:59.455258Z","signature_b64":"l6bnSBQfGADAeUnL8E5xGP6Ht8wVarSgP5zP64oGVFvJFjFe2hsHxfZ1t2LrDDfnQx+HilhtrXkyPKc3SBZUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"195a864e64b4e5160ff5d57bdf32da10786ce5489ed636ded19d94b400985dd6","last_reissued_at":"2026-07-05T12:01:59.454660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:59.454660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.20491","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":"2026-07-05T12:01:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JbAfHNTHGjnCuAFMnEu4Aike7s1GBEl8OFCcZNEX8jGIZkJKQh4W9bv9KeHk5FEQIAA6wHsGYVd8qFT6Vr8LDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:45:17.074312Z"},"content_sha256":"d86f8535ec43237cd2a3fd592406c2eeaa06cdeb989f97b2c1f4d9cc8d6c7d77","schema_version":"1.0","event_id":"sha256:d86f8535ec43237cd2a3fd592406c2eeaa06cdeb989f97b2c1f4d9cc8d6c7d77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DFNIMTTEWTSRMD7V2V556MW2CB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VPO: Aligning Text-to-Video Generation Models with Prompt Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hongning Wang, Jiale Cheng, Jiayan Teng, Jiazheng Xu, Jie Tang, Minlie Huang, Ruiliang Lyu, Xiao Liu, Xiaotao Gu, Yida Lu, Yuxiao Dong, Zhuoyi Yang","submitted_at":"2025-03-26T12:28:20Z","abstract_excerpt":"Video generation models have achieved remarkable progress in text-to-video tasks. These models are typically trained on text-video pairs with highly detailed and carefully crafted descriptions, while real-world user inputs during inference are often concise, vague, or poorly structured. This gap makes prompt optimization crucial for generating high-quality videos. Current methods often rely on large language models (LLMs) to refine prompts through in-context learning, but suffer from several limitations: they may distort user intent, omit critical details, or introduce safety risks. Moreover, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20491","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/2503.20491/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":"2026-07-05T12:01:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NNJAMXYtDbWngz6pdYTx6Rn5itZAWWEXeputyL76ZNxt9U4PRxeV43rHbEqdYrJLREalmctEjwojPznhzdG2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:45:17.074903Z"},"content_sha256":"898741fa5fbd0253f71f9f7484940184fbb3a2c1eb064e57c9e4402307e8bd18","schema_version":"1.0","event_id":"sha256:898741fa5fbd0253f71f9f7484940184fbb3a2c1eb064e57c9e4402307e8bd18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DFNIMTTEWTSRMD7V2V556MW2CB/bundle.json","state_url":"https://pith.science/pith/DFNIMTTEWTSRMD7V2V556MW2CB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DFNIMTTEWTSRMD7V2V556MW2CB/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":"2026-08-06T06:45:17Z","links":{"resolver":"https://pith.science/pith/DFNIMTTEWTSRMD7V2V556MW2CB","bundle":"https://pith.science/pith/DFNIMTTEWTSRMD7V2V556MW2CB/bundle.json","state":"https://pith.science/pith/DFNIMTTEWTSRMD7V2V556MW2CB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DFNIMTTEWTSRMD7V2V556MW2CB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DFNIMTTEWTSRMD7V2V556MW2CB","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":"2cb148e9bfcc4817eff2c11f34347c96622888e56f0ef360f5ec9cc000c3f33f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T12:28:20Z","title_canon_sha256":"75b3c90d36548045bbb7be0e2c34d8ccb6070eabc8345449c206c4c02ff37d05"},"schema_version":"1.0","source":{"id":"2503.20491","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.20491","created_at":"2026-07-05T12:01:59Z"},{"alias_kind":"arxiv_version","alias_value":"2503.20491v2","created_at":"2026-07-05T12:01:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20491","created_at":"2026-07-05T12:01:59Z"},{"alias_kind":"pith_short_12","alias_value":"DFNIMTTEWTSR","created_at":"2026-07-05T12:01:59Z"},{"alias_kind":"pith_short_16","alias_value":"DFNIMTTEWTSRMD7V","created_at":"2026-07-05T12:01:59Z"},{"alias_kind":"pith_short_8","alias_value":"DFNIMTTE","created_at":"2026-07-05T12:01:59Z"}],"graph_snapshots":[{"event_id":"sha256:898741fa5fbd0253f71f9f7484940184fbb3a2c1eb064e57c9e4402307e8bd18","target":"graph","created_at":"2026-07-05T12:01:59Z","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/2503.20491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video generation models have achieved remarkable progress in text-to-video tasks. These models are typically trained on text-video pairs with highly detailed and carefully crafted descriptions, while real-world user inputs during inference are often concise, vague, or poorly structured. This gap makes prompt optimization crucial for generating high-quality videos. Current methods often rely on large language models (LLMs) to refine prompts through in-context learning, but suffer from several limitations: they may distort user intent, omit critical details, or introduce safety risks. Moreover, ","authors_text":"Hongning Wang, Jiale Cheng, Jiayan Teng, Jiazheng Xu, Jie Tang, Minlie Huang, Ruiliang Lyu, Xiao Liu, Xiaotao Gu, Yida Lu, Yuxiao Dong, Zhuoyi Yang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T12:28:20Z","title":"VPO: Aligning Text-to-Video Generation Models with Prompt Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20491","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:d86f8535ec43237cd2a3fd592406c2eeaa06cdeb989f97b2c1f4d9cc8d6c7d77","target":"record","created_at":"2026-07-05T12:01:59Z","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":"2cb148e9bfcc4817eff2c11f34347c96622888e56f0ef360f5ec9cc000c3f33f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T12:28:20Z","title_canon_sha256":"75b3c90d36548045bbb7be0e2c34d8ccb6070eabc8345449c206c4c02ff37d05"},"schema_version":"1.0","source":{"id":"2503.20491","kind":"arxiv","version":2}},"canonical_sha256":"195a864e64b4e5160ff5d57bdf32da10786ce5489ed636ded19d94b400985dd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"195a864e64b4e5160ff5d57bdf32da10786ce5489ed636ded19d94b400985dd6","first_computed_at":"2026-07-05T12:01:59.454660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:59.454660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l6bnSBQfGADAeUnL8E5xGP6Ht8wVarSgP5zP64oGVFvJFjFe2hsHxfZ1t2LrDDfnQx+HilhtrXkyPKc3SBZUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:59.455258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.20491","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d86f8535ec43237cd2a3fd592406c2eeaa06cdeb989f97b2c1f4d9cc8d6c7d77","sha256:898741fa5fbd0253f71f9f7484940184fbb3a2c1eb064e57c9e4402307e8bd18"],"state_sha256":"2db7d3b34c3ebfb60af275df64e3d434dada131e888eafee6570047cb6470429"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q0XSPkNg8OTRU9jrApQrEoeLtAQl9uNfYUa54zMvm08AIJFEyMc6PYpIvzz81YzoVFwyP89kbzfq0iOC1aNZCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:45:17.079952Z","bundle_sha256":"4e6c38b2ea54c018bd9f46cfbc4fba1b7499210657633ff17c39d833653aadc7"}}