{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7G55PM6XOQFYWEGNRWNSP6LG74","short_pith_number":"pith:7G55PM6X","canonical_record":{"source":{"id":"2008.09049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-20T16:03:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7f4013782dfe6c7ef4f405490673c11a9502d713f58553651ee5a6bf55e4e4b3","abstract_canon_sha256":"de11be590b26538e4e099eee2254424634e8d03c724ae37151eaefa83e2abd85"},"schema_version":"1.0"},"canonical_sha256":"f9bbd7b3d7740b8b10cd8d9b27f966ff18a616bf27f80691dbb3f2fae46b9803","source":{"kind":"arxiv","id":"2008.09049","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.09049","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"arxiv_version","alias_value":"2008.09049v1","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09049","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"pith_short_12","alias_value":"7G55PM6XOQFY","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"pith_short_16","alias_value":"7G55PM6XOQFYWEGN","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"pith_short_8","alias_value":"7G55PM6X","created_at":"2026-07-05T01:28:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7G55PM6XOQFYWEGNRWNSP6LG74","target":"record","payload":{"canonical_record":{"source":{"id":"2008.09049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-20T16:03:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7f4013782dfe6c7ef4f405490673c11a9502d713f58553651ee5a6bf55e4e4b3","abstract_canon_sha256":"de11be590b26538e4e099eee2254424634e8d03c724ae37151eaefa83e2abd85"},"schema_version":"1.0"},"canonical_sha256":"f9bbd7b3d7740b8b10cd8d9b27f966ff18a616bf27f80691dbb3f2fae46b9803","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:39.228691Z","signature_b64":"qZWqMy3CZnRJ874q+rOyadZl10UD9KuMpZQYtdJteZySpiGR/zyNolTf/XZ6KQZrWcjUkHW+VFjvcoHLm3fCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9bbd7b3d7740b8b10cd8d9b27f966ff18a616bf27f80691dbb3f2fae46b9803","last_reissued_at":"2026-07-05T01:28:39.228347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:39.228347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.09049","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":"2026-07-05T01:28:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oFWbgMQHMlVITVcW1Fmukx6hIPJsjKxz+UIUkkb1KR9HfjUW9cbEpOfUzsE0drD4AZQ6Wrm2YE+LAvyrg6CUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:52:12.305250Z"},"content_sha256":"4412cd58ab268cfe2d253f71f90ec9f748e5c80634fa0b25f0034d20e4cc70a6","schema_version":"1.0","event_id":"sha256:4412cd58ab268cfe2d253f71f90ec9f748e5c80634fa0b25f0034d20e4cc70a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7G55PM6XOQFYWEGNRWNSP6LG74","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discovering Useful Sentence Representations from Large Pretrained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Nishant Subramani, Nivedita Suresh","submitted_at":"2020-08-20T16:03:51Z","abstract_excerpt":"Despite the extensive success of pretrained language models as encoders for building NLP systems, they haven't seen prominence as decoders for sequence generation tasks. We explore the question of whether these models can be adapted to be used as universal decoders. To be considered \"universal,\" a decoder must have an implicit representation for any target sentence $s$, such that it can recover that sentence exactly when conditioned on its representation. For large transformer-based language models trained on vast amounts of English text, we investigate whether such representations can be easi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09049","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/2008.09049/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":"2026-07-05T01:28:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KYCXS3Vh26YOlYK6Iy3sCxexdIq4Ph5Hv7UIZDCjJqTmnafaCD/KDzhHIjyPhZenPVF04Pc7WvAfQc5VqZcgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:52:12.305826Z"},"content_sha256":"768fab2348bff68f73a6bf8a2c16cab8231754783038bfa7ad3337271f07f588","schema_version":"1.0","event_id":"sha256:768fab2348bff68f73a6bf8a2c16cab8231754783038bfa7ad3337271f07f588"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7G55PM6XOQFYWEGNRWNSP6LG74/bundle.json","state_url":"https://pith.science/pith/7G55PM6XOQFYWEGNRWNSP6LG74/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7G55PM6XOQFYWEGNRWNSP6LG74/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":"2026-08-19T03:52:12Z","links":{"resolver":"https://pith.science/pith/7G55PM6XOQFYWEGNRWNSP6LG74","bundle":"https://pith.science/pith/7G55PM6XOQFYWEGNRWNSP6LG74/bundle.json","state":"https://pith.science/pith/7G55PM6XOQFYWEGNRWNSP6LG74/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7G55PM6XOQFYWEGNRWNSP6LG74/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7G55PM6XOQFYWEGNRWNSP6LG74","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":"de11be590b26538e4e099eee2254424634e8d03c724ae37151eaefa83e2abd85","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-20T16:03:51Z","title_canon_sha256":"7f4013782dfe6c7ef4f405490673c11a9502d713f58553651ee5a6bf55e4e4b3"},"schema_version":"1.0","source":{"id":"2008.09049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.09049","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"arxiv_version","alias_value":"2008.09049v1","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09049","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"pith_short_12","alias_value":"7G55PM6XOQFY","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"pith_short_16","alias_value":"7G55PM6XOQFYWEGN","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"pith_short_8","alias_value":"7G55PM6X","created_at":"2026-07-05T01:28:39Z"}],"graph_snapshots":[{"event_id":"sha256:768fab2348bff68f73a6bf8a2c16cab8231754783038bfa7ad3337271f07f588","target":"graph","created_at":"2026-07-05T01:28:39Z","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/2008.09049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the extensive success of pretrained language models as encoders for building NLP systems, they haven't seen prominence as decoders for sequence generation tasks. We explore the question of whether these models can be adapted to be used as universal decoders. To be considered \"universal,\" a decoder must have an implicit representation for any target sentence $s$, such that it can recover that sentence exactly when conditioned on its representation. For large transformer-based language models trained on vast amounts of English text, we investigate whether such representations can be easi","authors_text":"Nishant Subramani, Nivedita Suresh","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-20T16:03:51Z","title":"Discovering Useful Sentence Representations from Large Pretrained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09049","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":"sha256:4412cd58ab268cfe2d253f71f90ec9f748e5c80634fa0b25f0034d20e4cc70a6","target":"record","created_at":"2026-07-05T01:28:39Z","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":"de11be590b26538e4e099eee2254424634e8d03c724ae37151eaefa83e2abd85","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-20T16:03:51Z","title_canon_sha256":"7f4013782dfe6c7ef4f405490673c11a9502d713f58553651ee5a6bf55e4e4b3"},"schema_version":"1.0","source":{"id":"2008.09049","kind":"arxiv","version":1}},"canonical_sha256":"f9bbd7b3d7740b8b10cd8d9b27f966ff18a616bf27f80691dbb3f2fae46b9803","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9bbd7b3d7740b8b10cd8d9b27f966ff18a616bf27f80691dbb3f2fae46b9803","first_computed_at":"2026-07-05T01:28:39.228347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:28:39.228347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qZWqMy3CZnRJ874q+rOyadZl10UD9KuMpZQYtdJteZySpiGR/zyNolTf/XZ6KQZrWcjUkHW+VFjvcoHLm3fCDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:28:39.228691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.09049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4412cd58ab268cfe2d253f71f90ec9f748e5c80634fa0b25f0034d20e4cc70a6","sha256:768fab2348bff68f73a6bf8a2c16cab8231754783038bfa7ad3337271f07f588"],"state_sha256":"68f29ae51e46b048ddd0714694abc10f71caac0a26c68643701f58a86c8d4c1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cRgyscbFf/cWDo97x99QOPMuNf6bFG0k75+Z5W+p97ezydp7qaVqeNcexxpdj52yCXf6SSeA/Zd9InK6ic3fDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T03:52:12.311279Z","bundle_sha256":"16c928e593516c925b44fbcc35f6ff22f0f56bd456b2659b961c62bb1fd8051a"}}