{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L35R3C4E2O7ASJFMXY7V4YVAJ3","short_pith_number":"pith:L35R3C4E","schema_version":"1.0","canonical_sha256":"5efb1d8b84d3be0924acbe3f5e62a04ec3b0e4a981cfc99e87133c824c4ecffe","source":{"kind":"arxiv","id":"2412.18966","version":1},"attestation_state":"computed","paper":{"title":"ModelGrow: Continual Text-to-Video Pre-training with Model Expansion and Language Understanding Enhancement","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiaxin Xie, Liya Ji, Qifeng Chen, Runtao Liu, Yazhou Xing, Yingqing He, Zhaoyang Liu, Zhefan Rao, Ziqiao Peng","submitted_at":"2024-12-25T18:58:07Z","abstract_excerpt":"Text-to-video (T2V) generation has gained significant attention recently. However, the costs of training a T2V model from scratch remain persistently high, and there is considerable room for improving the generation performance, especially under limited computation resources. This work explores the continual general pre-training of text-to-video models, enabling the model to \"grow\" its abilities based on a pre-trained foundation, analogous to how humans acquire new knowledge based on past experiences. There is a lack of extensive study of the continual pre-training techniques in T2V generation"},"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":"2412.18966","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-25T18:58:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f98f39bf216b2519e36b04631908e9f53a931d552edb4adea9d78e3d29784e89","abstract_canon_sha256":"4cfb02f3447e7dcf9e56e8b775a116f13a725ed7a2b1f6bfa2fe6235ecf711ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:13.960059Z","signature_b64":"MtOkmuI5jYe7keou3WbwOI5MNi2rHPV5tG9E3PSJphHPNl38IphJHhiq2ji+LCP19Q+KiSxzKZZwg8g1wwZsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5efb1d8b84d3be0924acbe3f5e62a04ec3b0e4a981cfc99e87133c824c4ecffe","last_reissued_at":"2026-07-05T09:54:13.959707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:13.959707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ModelGrow: Continual Text-to-Video Pre-training with Model Expansion and Language Understanding Enhancement","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiaxin Xie, Liya Ji, Qifeng Chen, Runtao Liu, Yazhou Xing, Yingqing He, Zhaoyang Liu, Zhefan Rao, Ziqiao Peng","submitted_at":"2024-12-25T18:58:07Z","abstract_excerpt":"Text-to-video (T2V) generation has gained significant attention recently. However, the costs of training a T2V model from scratch remain persistently high, and there is considerable room for improving the generation performance, especially under limited computation resources. This work explores the continual general pre-training of text-to-video models, enabling the model to \"grow\" its abilities based on a pre-trained foundation, analogous to how humans acquire new knowledge based on past experiences. There is a lack of extensive study of the continual pre-training techniques in T2V generation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18966","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/2412.18966/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":"2412.18966","created_at":"2026-07-05T09:54:13.959763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18966v1","created_at":"2026-07-05T09:54:13.959763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18966","created_at":"2026-07-05T09:54:13.959763+00:00"},{"alias_kind":"pith_short_12","alias_value":"L35R3C4E2O7A","created_at":"2026-07-05T09:54:13.959763+00:00"},{"alias_kind":"pith_short_16","alias_value":"L35R3C4E2O7ASJFM","created_at":"2026-07-05T09:54:13.959763+00:00"},{"alias_kind":"pith_short_8","alias_value":"L35R3C4E","created_at":"2026-07-05T09:54:13.959763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L35R3C4E2O7ASJFMXY7V4YVAJ3","json":"https://pith.science/pith/L35R3C4E2O7ASJFMXY7V4YVAJ3.json","graph_json":"https://pith.science/api/pith-number/L35R3C4E2O7ASJFMXY7V4YVAJ3/graph.json","events_json":"https://pith.science/api/pith-number/L35R3C4E2O7ASJFMXY7V4YVAJ3/events.json","paper":"https://pith.science/paper/L35R3C4E"},"agent_actions":{"view_html":"https://pith.science/pith/L35R3C4E2O7ASJFMXY7V4YVAJ3","download_json":"https://pith.science/pith/L35R3C4E2O7ASJFMXY7V4YVAJ3.json","view_paper":"https://pith.science/paper/L35R3C4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18966&json=true","fetch_graph":"https://pith.science/api/pith-number/L35R3C4E2O7ASJFMXY7V4YVAJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/L35R3C4E2O7ASJFMXY7V4YVAJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L35R3C4E2O7ASJFMXY7V4YVAJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L35R3C4E2O7ASJFMXY7V4YVAJ3/action/storage_attestation","attest_author":"https://pith.science/pith/L35R3C4E2O7ASJFMXY7V4YVAJ3/action/author_attestation","sign_citation":"https://pith.science/pith/L35R3C4E2O7ASJFMXY7V4YVAJ3/action/citation_signature","submit_replication":"https://pith.science/pith/L35R3C4E2O7ASJFMXY7V4YVAJ3/action/replication_record"}},"created_at":"2026-07-05T09:54:13.959763+00:00","updated_at":"2026-07-05T09:54:13.959763+00:00"}