{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CP4LJEE77I3GX3FSODJJSPIE2T","short_pith_number":"pith:CP4LJEE7","schema_version":"1.0","canonical_sha256":"13f8b4909ffa366becb270d2993d04d4cb470f58e9c99236edfecdc46d01d1dd","source":{"kind":"arxiv","id":"2211.09817","version":1},"attestation_state":"computed","paper":{"title":"On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Shiro Takagi","submitted_at":"2022-11-17T13:34:08Z","abstract_excerpt":"We empirically investigate how pre-training on data of different modalities, such as language and vision, affects fine-tuning of Transformer-based models to Mujoco offline reinforcement learning tasks. Analysis of the internal representation reveals that the pre-trained Transformers acquire largely different representations before and after pre-training, but acquire less information of data in fine-tuning than the randomly initialized one. A closer look at the parameter changes of the pre-trained Transformers reveals that their parameters do not change that much and that the bad performance of"},"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":"2211.09817","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-17T13:34:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c387695b8248ddf2b1e7935c18fa5d25b7f6acf94f0ef266478033d02d44b821","abstract_canon_sha256":"0ef93779f741ae2d4936da1dbb02a72e9972a2440206c8592f4c5f5c63828f1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:14.468352Z","signature_b64":"O1GWfwrkonKVuEs1xmGpKuRcBQgys3WnGri9LGFR3XFsFPFrlfqm3to4LPI1nLp9U95gGik4Ii2uC9SqOvu0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13f8b4909ffa366becb270d2993d04d4cb470f58e9c99236edfecdc46d01d1dd","last_reissued_at":"2026-07-05T05:17:14.467929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:14.467929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Shiro Takagi","submitted_at":"2022-11-17T13:34:08Z","abstract_excerpt":"We empirically investigate how pre-training on data of different modalities, such as language and vision, affects fine-tuning of Transformer-based models to Mujoco offline reinforcement learning tasks. Analysis of the internal representation reveals that the pre-trained Transformers acquire largely different representations before and after pre-training, but acquire less information of data in fine-tuning than the randomly initialized one. A closer look at the parameter changes of the pre-trained Transformers reveals that their parameters do not change that much and that the bad performance of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09817","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/2211.09817/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":"2211.09817","created_at":"2026-07-05T05:17:14.467988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09817v1","created_at":"2026-07-05T05:17:14.467988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09817","created_at":"2026-07-05T05:17:14.467988+00:00"},{"alias_kind":"pith_short_12","alias_value":"CP4LJEE77I3G","created_at":"2026-07-05T05:17:14.467988+00:00"},{"alias_kind":"pith_short_16","alias_value":"CP4LJEE77I3GX3FS","created_at":"2026-07-05T05:17:14.467988+00:00"},{"alias_kind":"pith_short_8","alias_value":"CP4LJEE7","created_at":"2026-07-05T05:17:14.467988+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/CP4LJEE77I3GX3FSODJJSPIE2T","json":"https://pith.science/pith/CP4LJEE77I3GX3FSODJJSPIE2T.json","graph_json":"https://pith.science/api/pith-number/CP4LJEE77I3GX3FSODJJSPIE2T/graph.json","events_json":"https://pith.science/api/pith-number/CP4LJEE77I3GX3FSODJJSPIE2T/events.json","paper":"https://pith.science/paper/CP4LJEE7"},"agent_actions":{"view_html":"https://pith.science/pith/CP4LJEE77I3GX3FSODJJSPIE2T","download_json":"https://pith.science/pith/CP4LJEE77I3GX3FSODJJSPIE2T.json","view_paper":"https://pith.science/paper/CP4LJEE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09817&json=true","fetch_graph":"https://pith.science/api/pith-number/CP4LJEE77I3GX3FSODJJSPIE2T/graph.json","fetch_events":"https://pith.science/api/pith-number/CP4LJEE77I3GX3FSODJJSPIE2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CP4LJEE77I3GX3FSODJJSPIE2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CP4LJEE77I3GX3FSODJJSPIE2T/action/storage_attestation","attest_author":"https://pith.science/pith/CP4LJEE77I3GX3FSODJJSPIE2T/action/author_attestation","sign_citation":"https://pith.science/pith/CP4LJEE77I3GX3FSODJJSPIE2T/action/citation_signature","submit_replication":"https://pith.science/pith/CP4LJEE77I3GX3FSODJJSPIE2T/action/replication_record"}},"created_at":"2026-07-05T05:17:14.467988+00:00","updated_at":"2026-07-05T05:17:14.467988+00:00"}