{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RHRYCPMEFGKS5IE7UBMYRHVTYV","short_pith_number":"pith:RHRYCPME","canonical_record":{"source":{"id":"2310.12100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T16:43:08Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"465836a1cfea6f0ce15814c25431794844c64c675faf25910c567ebbd01110b6","abstract_canon_sha256":"dc0dee03868f310da745fe9613748292c73688194efa3c19b4e41f21061deffe"},"schema_version":"1.0"},"canonical_sha256":"89e3813d8429952ea09fa059889eb3c558e85108faf5017f27284f9fd8c3d099","source":{"kind":"arxiv","id":"2310.12100","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12100","created_at":"2026-07-05T07:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12100v1","created_at":"2026-07-05T07:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12100","created_at":"2026-07-05T07:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"RHRYCPMEFGKS","created_at":"2026-07-05T07:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"RHRYCPMEFGKS5IE7","created_at":"2026-07-05T07:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"RHRYCPME","created_at":"2026-07-05T07:02:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RHRYCPMEFGKS5IE7UBMYRHVTYV","target":"record","payload":{"canonical_record":{"source":{"id":"2310.12100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T16:43:08Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"465836a1cfea6f0ce15814c25431794844c64c675faf25910c567ebbd01110b6","abstract_canon_sha256":"dc0dee03868f310da745fe9613748292c73688194efa3c19b4e41f21061deffe"},"schema_version":"1.0"},"canonical_sha256":"89e3813d8429952ea09fa059889eb3c558e85108faf5017f27284f9fd8c3d099","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:16.962862Z","signature_b64":"bmKZSiIS/ZYY2XPTV8PsWJJikhmI9Uqd9eG8D1JBgOivYY4xTshNEIJNjr5dlPWajeZpjJEiwmH64IZ2BoLFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89e3813d8429952ea09fa059889eb3c558e85108faf5017f27284f9fd8c3d099","last_reissued_at":"2026-07-05T07:02:16.962338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:16.962338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.12100","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":"2026-07-05T07:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E876fRHR7urHegWiCWeF9cIeFxPYblORBtuU7Q4wh397M0H5LGaG8hv6MrP7eibkxrm1nYQxgpoGMylP7Fw+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:06:51.713839Z"},"content_sha256":"84731046ad7264dbd969b0d35fbcc05728e1a8bab34eb47368eafc780280df66","schema_version":"1.0","event_id":"sha256:84731046ad7264dbd969b0d35fbcc05728e1a8bab34eb47368eafc780280df66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RHRYCPMEFGKS5IE7UBMYRHVTYV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Non-Intrusive Adaptation: Input-Centric Parameter-efficient Fine-Tuning for Versatile Multimodal Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.CL","authors_text":"Bo Pang, Chun-Ta Lu, Frederick Liu, Geoff Brown, Jiageng Zhang, Jialin Wu, Michael Bendersky, Radu Soricut, Tanmaya Dabral, Yaqing Wang, Yi Liang","submitted_at":"2023-10-18T16:43:08Z","abstract_excerpt":"Large language models (LLMs) and vision language models (VLMs) demonstrate excellent performance on a wide range of tasks by scaling up parameter counts from O(10^9) to O(10^{12}) levels and further beyond. These large scales make it impossible to adapt and deploy fully specialized models given a task of interest. Parameter-efficient fine-tuning (PEFT) emerges as a promising direction to tackle the adaptation and serving challenges for such large models. We categorize PEFT techniques into two types: intrusive and non-intrusive. Intrusive PEFT techniques directly change a model's internal archi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12100","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/2310.12100/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":"2026-07-05T07:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kAG2YsgHvW7s4tKAx/ZOwJgs0au7qFaQ7SD8FgllT/8bjk1rzPxHrcxE5CG3pWB8c4vxN3t/yHHb2aC0OWWtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:06:51.714712Z"},"content_sha256":"d40c51f2cb299ce1c146a4f0073a7d6ee2eab021450f4cda86f5ece35db46533","schema_version":"1.0","event_id":"sha256:d40c51f2cb299ce1c146a4f0073a7d6ee2eab021450f4cda86f5ece35db46533"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RHRYCPMEFGKS5IE7UBMYRHVTYV/bundle.json","state_url":"https://pith.science/pith/RHRYCPMEFGKS5IE7UBMYRHVTYV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RHRYCPMEFGKS5IE7UBMYRHVTYV/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":"2026-07-31T14:06:51Z","links":{"resolver":"https://pith.science/pith/RHRYCPMEFGKS5IE7UBMYRHVTYV","bundle":"https://pith.science/pith/RHRYCPMEFGKS5IE7UBMYRHVTYV/bundle.json","state":"https://pith.science/pith/RHRYCPMEFGKS5IE7UBMYRHVTYV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RHRYCPMEFGKS5IE7UBMYRHVTYV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RHRYCPMEFGKS5IE7UBMYRHVTYV","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":"dc0dee03868f310da745fe9613748292c73688194efa3c19b4e41f21061deffe","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T16:43:08Z","title_canon_sha256":"465836a1cfea6f0ce15814c25431794844c64c675faf25910c567ebbd01110b6"},"schema_version":"1.0","source":{"id":"2310.12100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12100","created_at":"2026-07-05T07:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12100v1","created_at":"2026-07-05T07:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12100","created_at":"2026-07-05T07:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"RHRYCPMEFGKS","created_at":"2026-07-05T07:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"RHRYCPMEFGKS5IE7","created_at":"2026-07-05T07:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"RHRYCPME","created_at":"2026-07-05T07:02:16Z"}],"graph_snapshots":[{"event_id":"sha256:d40c51f2cb299ce1c146a4f0073a7d6ee2eab021450f4cda86f5ece35db46533","target":"graph","created_at":"2026-07-05T07:02:16Z","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/2310.12100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) and vision language models (VLMs) demonstrate excellent performance on a wide range of tasks by scaling up parameter counts from O(10^9) to O(10^{12}) levels and further beyond. These large scales make it impossible to adapt and deploy fully specialized models given a task of interest. Parameter-efficient fine-tuning (PEFT) emerges as a promising direction to tackle the adaptation and serving challenges for such large models. We categorize PEFT techniques into two types: intrusive and non-intrusive. Intrusive PEFT techniques directly change a model's internal archi","authors_text":"Bo Pang, Chun-Ta Lu, Frederick Liu, Geoff Brown, Jiageng Zhang, Jialin Wu, Michael Bendersky, Radu Soricut, Tanmaya Dabral, Yaqing Wang, Yi Liang","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T16:43:08Z","title":"Non-Intrusive Adaptation: Input-Centric Parameter-efficient Fine-Tuning for Versatile Multimodal Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12100","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":"sha256:84731046ad7264dbd969b0d35fbcc05728e1a8bab34eb47368eafc780280df66","target":"record","created_at":"2026-07-05T07:02:16Z","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":"dc0dee03868f310da745fe9613748292c73688194efa3c19b4e41f21061deffe","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T16:43:08Z","title_canon_sha256":"465836a1cfea6f0ce15814c25431794844c64c675faf25910c567ebbd01110b6"},"schema_version":"1.0","source":{"id":"2310.12100","kind":"arxiv","version":1}},"canonical_sha256":"89e3813d8429952ea09fa059889eb3c558e85108faf5017f27284f9fd8c3d099","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89e3813d8429952ea09fa059889eb3c558e85108faf5017f27284f9fd8c3d099","first_computed_at":"2026-07-05T07:02:16.962338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:16.962338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bmKZSiIS/ZYY2XPTV8PsWJJikhmI9Uqd9eG8D1JBgOivYY4xTshNEIJNjr5dlPWajeZpjJEiwmH64IZ2BoLFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:16.962862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84731046ad7264dbd969b0d35fbcc05728e1a8bab34eb47368eafc780280df66","sha256:d40c51f2cb299ce1c146a4f0073a7d6ee2eab021450f4cda86f5ece35db46533"],"state_sha256":"096c9dc02c554cd86476e5b71ceb1987ae9756a6a310a79e5ce7a45dd8df45c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m6ddu3B6SM0nA2R0GZznZddLSddUmuigpm7svmMmE2gzNsP7dla1ms4VGWhQHeA81Rfe4Q6DV1msq8gD4yovAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T14:06:51.719631Z","bundle_sha256":"45db8a74cb1b63dd404d4e1801d0be7d81608b3624f164ae29e2762f8b9e7672"}}