{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KOHOH3BBU2EEHU6QX3SISUSY4X","short_pith_number":"pith:KOHOH3BB","canonical_record":{"source":{"id":"2501.07818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T03:43:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5273b1ec0e017a4634814ad2f5b4a24eb442fb2d56c8332509524028d329cb42","abstract_canon_sha256":"0cd1cf4216b2a9a2abdfa9b7c248d94bb4ea405086a59cbdd9b8613ff897aea3"},"schema_version":"1.0"},"canonical_sha256":"538ee3ec21a68843d3d0bee4895258e5d4c63328477be0c312d2b2711f28aa23","source":{"kind":"arxiv","id":"2501.07818","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07818","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07818v1","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07818","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_12","alias_value":"KOHOH3BBU2EE","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_16","alias_value":"KOHOH3BBU2EEHU6Q","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_8","alias_value":"KOHOH3BB","created_at":"2026-07-05T10:00:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KOHOH3BBU2EEHU6QX3SISUSY4X","target":"record","payload":{"canonical_record":{"source":{"id":"2501.07818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T03:43:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5273b1ec0e017a4634814ad2f5b4a24eb442fb2d56c8332509524028d329cb42","abstract_canon_sha256":"0cd1cf4216b2a9a2abdfa9b7c248d94bb4ea405086a59cbdd9b8613ff897aea3"},"schema_version":"1.0"},"canonical_sha256":"538ee3ec21a68843d3d0bee4895258e5d4c63328477be0c312d2b2711f28aa23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:50.588887Z","signature_b64":"ScFp7rOGvke5iDLAIuexZiUQhtlnS8RwT4y63Tou2KMtRL3IjiuQNgHIyv6+KhjL0TloLLTRKRo5FcmthrK7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"538ee3ec21a68843d3d0bee4895258e5d4c63328477be0c312d2b2711f28aa23","last_reissued_at":"2026-07-05T10:00:50.588431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:50.588431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.07818","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":"2026-07-05T10:00:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/n6ew7OeqqLIT3Q+xGtCv9b7UcfrN4dbxs3JDyUTRoDOb0umylLvceH22FZgcWNkr5Kr8fDuUmb62BConuhGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:36:04.115566Z"},"content_sha256":"ef5369065e17d72bd7f462cced8cb1c08444b824e0119e819a499cf94eb314cd","schema_version":"1.0","event_id":"sha256:ef5369065e17d72bd7f462cced8cb1c08444b824e0119e819a499cf94eb314cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KOHOH3BBU2EEHU6QX3SISUSY4X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Multi-Encoder Frozen-Decoder Approach for Fine-Tuning Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Kaustubh D. Dhole","submitted_at":"2025-01-14T03:43:23Z","abstract_excerpt":"Among parameter-efficient fine-tuning methods, freezing has emerged as a popular strategy for speeding up training, reducing catastrophic forgetting, and improving downstream performance. We investigate the impact of freezing the decoder in a multi-task setup comprising diverse natural language tasks, aiming to reduce deployment overhead and enhance portability to novel tasks. Our experiments, conducted by fine-tuning both individual and multi-task setups on the AlexaTM model, reveal that freezing decoders is highly effective for tasks with natural language outputs and mitigates catastrophic f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07818","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/2501.07818/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":"2026-07-05T10:00:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IoNYpjopQyoe+eLS82cJYHMR6VzCYR+jGO9obmvSqMNHG28xGnHrBg8wzJomrnTOOuaFxXhyCUJa3jzcm8bKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:36:04.116440Z"},"content_sha256":"01e240a437891c97ebbfa1610b09d547427622d5a29515a47642e5bc953f9260","schema_version":"1.0","event_id":"sha256:01e240a437891c97ebbfa1610b09d547427622d5a29515a47642e5bc953f9260"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KOHOH3BBU2EEHU6QX3SISUSY4X/bundle.json","state_url":"https://pith.science/pith/KOHOH3BBU2EEHU6QX3SISUSY4X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KOHOH3BBU2EEHU6QX3SISUSY4X/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":"2026-08-17T18:36:04Z","links":{"resolver":"https://pith.science/pith/KOHOH3BBU2EEHU6QX3SISUSY4X","bundle":"https://pith.science/pith/KOHOH3BBU2EEHU6QX3SISUSY4X/bundle.json","state":"https://pith.science/pith/KOHOH3BBU2EEHU6QX3SISUSY4X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KOHOH3BBU2EEHU6QX3SISUSY4X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KOHOH3BBU2EEHU6QX3SISUSY4X","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":"0cd1cf4216b2a9a2abdfa9b7c248d94bb4ea405086a59cbdd9b8613ff897aea3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T03:43:23Z","title_canon_sha256":"5273b1ec0e017a4634814ad2f5b4a24eb442fb2d56c8332509524028d329cb42"},"schema_version":"1.0","source":{"id":"2501.07818","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07818","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07818v1","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07818","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_12","alias_value":"KOHOH3BBU2EE","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_16","alias_value":"KOHOH3BBU2EEHU6Q","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_8","alias_value":"KOHOH3BB","created_at":"2026-07-05T10:00:50Z"}],"graph_snapshots":[{"event_id":"sha256:01e240a437891c97ebbfa1610b09d547427622d5a29515a47642e5bc953f9260","target":"graph","created_at":"2026-07-05T10:00:50Z","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/2501.07818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Among parameter-efficient fine-tuning methods, freezing has emerged as a popular strategy for speeding up training, reducing catastrophic forgetting, and improving downstream performance. We investigate the impact of freezing the decoder in a multi-task setup comprising diverse natural language tasks, aiming to reduce deployment overhead and enhance portability to novel tasks. Our experiments, conducted by fine-tuning both individual and multi-task setups on the AlexaTM model, reveal that freezing decoders is highly effective for tasks with natural language outputs and mitigates catastrophic f","authors_text":"Kaustubh D. Dhole","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T03:43:23Z","title":"A Multi-Encoder Frozen-Decoder Approach for Fine-Tuning Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07818","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:ef5369065e17d72bd7f462cced8cb1c08444b824e0119e819a499cf94eb314cd","target":"record","created_at":"2026-07-05T10:00:50Z","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":"0cd1cf4216b2a9a2abdfa9b7c248d94bb4ea405086a59cbdd9b8613ff897aea3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T03:43:23Z","title_canon_sha256":"5273b1ec0e017a4634814ad2f5b4a24eb442fb2d56c8332509524028d329cb42"},"schema_version":"1.0","source":{"id":"2501.07818","kind":"arxiv","version":1}},"canonical_sha256":"538ee3ec21a68843d3d0bee4895258e5d4c63328477be0c312d2b2711f28aa23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"538ee3ec21a68843d3d0bee4895258e5d4c63328477be0c312d2b2711f28aa23","first_computed_at":"2026-07-05T10:00:50.588431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:50.588431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ScFp7rOGvke5iDLAIuexZiUQhtlnS8RwT4y63Tou2KMtRL3IjiuQNgHIyv6+KhjL0TloLLTRKRo5FcmthrK7Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:50.588887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07818","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef5369065e17d72bd7f462cced8cb1c08444b824e0119e819a499cf94eb314cd","sha256:01e240a437891c97ebbfa1610b09d547427622d5a29515a47642e5bc953f9260"],"state_sha256":"6ecfc0e273106d8552e60543c2b47c9375abbe0c5f168dc7f2b529f1c447ac43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GHHKZHrHW6kIyQGeEPNpm/gczEEBqBA0A7HmdDlZN8AMzR2IPhA4AhNm2enQkkLdKoD6en/X6UwxLFd4r99KAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:36:04.123133Z","bundle_sha256":"12c520939b1c51edd60ec9bf2da0c4fb05953c20a7c74c0921bbfac38ce7b0e9"}}