{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7WZB32GHRD42JD5ATVURH464MZ","short_pith_number":"pith:7WZB32GH","canonical_record":{"source":{"id":"2007.07779","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-15T15:56:05Z","cross_cats_sorted":[],"title_canon_sha256":"118fe92e00006dd01e479d99197c3232b9e2a3ab0d3176aa17b87372246fac50","abstract_canon_sha256":"0d4144f217d1949142b96ca2cf1e05aada5758d45e8c784d6efdc3036f12e21b"},"schema_version":"1.0"},"canonical_sha256":"fdb21de8c788f9a48fa09d6913f3dc6653ffa12ac113da848e39f251ec437c2a","source":{"kind":"arxiv","id":"2007.07779","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.07779","created_at":"2026-07-05T01:40:34Z"},{"alias_kind":"arxiv_version","alias_value":"2007.07779v3","created_at":"2026-07-05T01:40:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.07779","created_at":"2026-07-05T01:40:34Z"},{"alias_kind":"pith_short_12","alias_value":"7WZB32GHRD42","created_at":"2026-07-05T01:40:34Z"},{"alias_kind":"pith_short_16","alias_value":"7WZB32GHRD42JD5A","created_at":"2026-07-05T01:40:34Z"},{"alias_kind":"pith_short_8","alias_value":"7WZB32GH","created_at":"2026-07-05T01:40:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7WZB32GHRD42JD5ATVURH464MZ","target":"record","payload":{"canonical_record":{"source":{"id":"2007.07779","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-15T15:56:05Z","cross_cats_sorted":[],"title_canon_sha256":"118fe92e00006dd01e479d99197c3232b9e2a3ab0d3176aa17b87372246fac50","abstract_canon_sha256":"0d4144f217d1949142b96ca2cf1e05aada5758d45e8c784d6efdc3036f12e21b"},"schema_version":"1.0"},"canonical_sha256":"fdb21de8c788f9a48fa09d6913f3dc6653ffa12ac113da848e39f251ec437c2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:34.706372Z","signature_b64":"II31Z9srFRFxknVbSLw1VIN+R6Af/kUGQRhZO3bVMsdEQ03Hyb8hn60z38tvk4QrWR7mgCGru49IbwxHgS7/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdb21de8c788f9a48fa09d6913f3dc6653ffa12ac113da848e39f251ec437c2a","last_reissued_at":"2026-07-05T01:40:34.705413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:34.705413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.07779","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:40:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TzncMbX4pzE07Af1eID6ddDVZxTfXk3qmF5VXgNA28qe3PSTwlIvLiDT0ZYiK7tQ4lZckheUiyUrWy6EbmxgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:45:35.056403Z"},"content_sha256":"6934f14f1b1073abfe0e3725703b0154732c2893807b00e9212cade638e4bebf","schema_version":"1.0","event_id":"sha256:6934f14f1b1073abfe0e3725703b0154732c2893807b00e9212cade638e4bebf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7WZB32GHRD42JD5ATVURH464MZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AdapterHub: A Framework for Adapting Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aishwarya Kamath, Andreas R\\\"uckl\\'e, Clifton Poth, Iryna Gurevych, Ivan Vuli\\'c, Jonas Pfeiffer, Kyunghyun Cho, Sebastian Ruder","submitted_at":"2020-07-15T15:56:05Z","abstract_excerpt":"The current modus operandi in NLP involves downloading and fine-tuning pre-trained models consisting of millions or billions of parameters. Storing and sharing such large trained models is expensive, slow, and time-consuming, which impedes progress towards more general and versatile NLP methods that learn from and for many tasks. Adapters -- small learnt bottleneck layers inserted within each layer of a pre-trained model -- ameliorate this issue by avoiding full fine-tuning of the entire model. However, sharing and integrating adapter layers is not straightforward. We propose AdapterHub, a fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.07779","kind":"arxiv","version":3},"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/2007.07779/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":"2026-07-05T01:40:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pCTmQuU0fxVotxCWYT404WIguLb8WeaNChzO4DmfQ60Aesr+d81+A/pwFnPtEiVUIqd2s8rZjuPsMgV7PjyVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:45:35.056774Z"},"content_sha256":"136b1ea682697742bedf166240d871fb5489898605940f613f17dde9cf641327","schema_version":"1.0","event_id":"sha256:136b1ea682697742bedf166240d871fb5489898605940f613f17dde9cf641327"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7WZB32GHRD42JD5ATVURH464MZ/bundle.json","state_url":"https://pith.science/pith/7WZB32GHRD42JD5ATVURH464MZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7WZB32GHRD42JD5ATVURH464MZ/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":"2026-07-06T18:45:35Z","links":{"resolver":"https://pith.science/pith/7WZB32GHRD42JD5ATVURH464MZ","bundle":"https://pith.science/pith/7WZB32GHRD42JD5ATVURH464MZ/bundle.json","state":"https://pith.science/pith/7WZB32GHRD42JD5ATVURH464MZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7WZB32GHRD42JD5ATVURH464MZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7WZB32GHRD42JD5ATVURH464MZ","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":"0d4144f217d1949142b96ca2cf1e05aada5758d45e8c784d6efdc3036f12e21b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-15T15:56:05Z","title_canon_sha256":"118fe92e00006dd01e479d99197c3232b9e2a3ab0d3176aa17b87372246fac50"},"schema_version":"1.0","source":{"id":"2007.07779","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.07779","created_at":"2026-07-05T01:40:34Z"},{"alias_kind":"arxiv_version","alias_value":"2007.07779v3","created_at":"2026-07-05T01:40:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.07779","created_at":"2026-07-05T01:40:34Z"},{"alias_kind":"pith_short_12","alias_value":"7WZB32GHRD42","created_at":"2026-07-05T01:40:34Z"},{"alias_kind":"pith_short_16","alias_value":"7WZB32GHRD42JD5A","created_at":"2026-07-05T01:40:34Z"},{"alias_kind":"pith_short_8","alias_value":"7WZB32GH","created_at":"2026-07-05T01:40:34Z"}],"graph_snapshots":[{"event_id":"sha256:136b1ea682697742bedf166240d871fb5489898605940f613f17dde9cf641327","target":"graph","created_at":"2026-07-05T01:40:34Z","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/2007.07779/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The current modus operandi in NLP involves downloading and fine-tuning pre-trained models consisting of millions or billions of parameters. Storing and sharing such large trained models is expensive, slow, and time-consuming, which impedes progress towards more general and versatile NLP methods that learn from and for many tasks. Adapters -- small learnt bottleneck layers inserted within each layer of a pre-trained model -- ameliorate this issue by avoiding full fine-tuning of the entire model. However, sharing and integrating adapter layers is not straightforward. We propose AdapterHub, a fra","authors_text":"Aishwarya Kamath, Andreas R\\\"uckl\\'e, Clifton Poth, Iryna Gurevych, Ivan Vuli\\'c, Jonas Pfeiffer, Kyunghyun Cho, Sebastian Ruder","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-15T15:56:05Z","title":"AdapterHub: A Framework for Adapting Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.07779","kind":"arxiv","version":3},"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":"sha256:6934f14f1b1073abfe0e3725703b0154732c2893807b00e9212cade638e4bebf","target":"record","created_at":"2026-07-05T01:40:34Z","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":"0d4144f217d1949142b96ca2cf1e05aada5758d45e8c784d6efdc3036f12e21b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-15T15:56:05Z","title_canon_sha256":"118fe92e00006dd01e479d99197c3232b9e2a3ab0d3176aa17b87372246fac50"},"schema_version":"1.0","source":{"id":"2007.07779","kind":"arxiv","version":3}},"canonical_sha256":"fdb21de8c788f9a48fa09d6913f3dc6653ffa12ac113da848e39f251ec437c2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdb21de8c788f9a48fa09d6913f3dc6653ffa12ac113da848e39f251ec437c2a","first_computed_at":"2026-07-05T01:40:34.705413Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:40:34.705413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"II31Z9srFRFxknVbSLw1VIN+R6Af/kUGQRhZO3bVMsdEQ03Hyb8hn60z38tvk4QrWR7mgCGru49IbwxHgS7/AA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:40:34.706372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.07779","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6934f14f1b1073abfe0e3725703b0154732c2893807b00e9212cade638e4bebf","sha256:136b1ea682697742bedf166240d871fb5489898605940f613f17dde9cf641327"],"state_sha256":"b675021c8d3b8649a5ad66d79ecd75116ddcd30427a7a3df3d3d4e1ebda579d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3RMmzxkLKh4U17fZGBaxCYKr6bbub31fRPRmlFUZRCZVYrHhnBCq11z1fUhc3Lrr6pzlCyBGDOBxC1vdWuyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:45:35.058647Z","bundle_sha256":"8518e4e7983708ed9dc5dde5dfa9e31cad9f4acb34a582a138248d8a856afdac"}}