{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HQW2UOVXIWPEMQVJREFFRFVGLQ","short_pith_number":"pith:HQW2UOVX","canonical_record":{"source":{"id":"1910.05276","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-11T16:10:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"80149e4b5812aa1c489a405aa933c62be56698780d5993dfc2bf90d762b0828a","abstract_canon_sha256":"9e47f92c8b4e918bfa59903290bc37ae6250d720d9ab5d6ca34f45494b37e58f"},"schema_version":"1.0"},"canonical_sha256":"3c2daa3ab7459e4642a9890a5896a65c05981f3e016a468feb1ffc0dbc6dc471","source":{"kind":"arxiv","id":"1910.05276","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05276","created_at":"2026-07-05T00:11:27Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05276v1","created_at":"2026-07-05T00:11:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05276","created_at":"2026-07-05T00:11:27Z"},{"alias_kind":"pith_short_12","alias_value":"HQW2UOVXIWPE","created_at":"2026-07-05T00:11:27Z"},{"alias_kind":"pith_short_16","alias_value":"HQW2UOVXIWPEMQVJ","created_at":"2026-07-05T00:11:27Z"},{"alias_kind":"pith_short_8","alias_value":"HQW2UOVX","created_at":"2026-07-05T00:11:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HQW2UOVXIWPEMQVJREFFRFVGLQ","target":"record","payload":{"canonical_record":{"source":{"id":"1910.05276","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-11T16:10:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"80149e4b5812aa1c489a405aa933c62be56698780d5993dfc2bf90d762b0828a","abstract_canon_sha256":"9e47f92c8b4e918bfa59903290bc37ae6250d720d9ab5d6ca34f45494b37e58f"},"schema_version":"1.0"},"canonical_sha256":"3c2daa3ab7459e4642a9890a5896a65c05981f3e016a468feb1ffc0dbc6dc471","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:27.463982Z","signature_b64":"EsBP1hsJtxF4/hJMSV3Att+9j/EDlr5VG/oqi5DsycNG7FOzxFIFnpGZhLEZFhwm9P4BwdEYB60Pe17oIJkKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c2daa3ab7459e4642a9890a5896a65c05981f3e016a468feb1ffc0dbc6dc471","last_reissued_at":"2026-07-05T00:11:27.463573Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:27.463573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.05276","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":"2026-07-05T00:11:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qUmJZ1FvWj4qaIKng9DQP7pNVUt0IZgEYymC19d+R1nQrIr4ZIqRnYXn20ettuL3TUobT4gQcOpApHe8fjipAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:00:51.446635Z"},"content_sha256":"c0ddb5e61430b34ffd9fe0a696ec6727d1593a3ae83fea5f59e49c7e4bd209fc","schema_version":"1.0","event_id":"sha256:c0ddb5e61430b34ffd9fe0a696ec6727d1593a3ae83fea5f59e49c7e4bd209fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HQW2UOVXIWPEMQVJREFFRFVGLQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Benjamin Hoover, Hendrik Strobelt, Sebastian Gehrmann","submitted_at":"2019-10-11T16:10:55Z","abstract_excerpt":"Large language models can produce powerful contextual representations that lead to improvements across many NLP tasks. Since these models are typically guided by a sequence of learned self attention mechanisms and may comprise undesired inductive biases, it is paramount to be able to explore what the attention has learned. While static analyses of these models lead to targeted insights, interactive tools are more dynamic and can help humans better gain an intuition for the model-internal reasoning process. We present exBERT, an interactive tool named after the popular BERT language model, that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05276","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/1910.05276/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":"2026-07-05T00:11:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LB/FGG5cQ1wAlsvqjfremQ8Ll7NwnFJJ0hbyju8QXOWd/wt7SkYY4M3Dhdt9kMiFNcgfxekoQQw7JLQzrr+hBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:00:51.447164Z"},"content_sha256":"70bee474db7841eb06f43ce8fda596fe177ad9cca84db8d50a7fdbaa5e37411f","schema_version":"1.0","event_id":"sha256:70bee474db7841eb06f43ce8fda596fe177ad9cca84db8d50a7fdbaa5e37411f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HQW2UOVXIWPEMQVJREFFRFVGLQ/bundle.json","state_url":"https://pith.science/pith/HQW2UOVXIWPEMQVJREFFRFVGLQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HQW2UOVXIWPEMQVJREFFRFVGLQ/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":"2026-08-20T04:00:51Z","links":{"resolver":"https://pith.science/pith/HQW2UOVXIWPEMQVJREFFRFVGLQ","bundle":"https://pith.science/pith/HQW2UOVXIWPEMQVJREFFRFVGLQ/bundle.json","state":"https://pith.science/pith/HQW2UOVXIWPEMQVJREFFRFVGLQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HQW2UOVXIWPEMQVJREFFRFVGLQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HQW2UOVXIWPEMQVJREFFRFVGLQ","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":"9e47f92c8b4e918bfa59903290bc37ae6250d720d9ab5d6ca34f45494b37e58f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-11T16:10:55Z","title_canon_sha256":"80149e4b5812aa1c489a405aa933c62be56698780d5993dfc2bf90d762b0828a"},"schema_version":"1.0","source":{"id":"1910.05276","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05276","created_at":"2026-07-05T00:11:27Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05276v1","created_at":"2026-07-05T00:11:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05276","created_at":"2026-07-05T00:11:27Z"},{"alias_kind":"pith_short_12","alias_value":"HQW2UOVXIWPE","created_at":"2026-07-05T00:11:27Z"},{"alias_kind":"pith_short_16","alias_value":"HQW2UOVXIWPEMQVJ","created_at":"2026-07-05T00:11:27Z"},{"alias_kind":"pith_short_8","alias_value":"HQW2UOVX","created_at":"2026-07-05T00:11:27Z"}],"graph_snapshots":[{"event_id":"sha256:70bee474db7841eb06f43ce8fda596fe177ad9cca84db8d50a7fdbaa5e37411f","target":"graph","created_at":"2026-07-05T00:11:27Z","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/1910.05276/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models can produce powerful contextual representations that lead to improvements across many NLP tasks. Since these models are typically guided by a sequence of learned self attention mechanisms and may comprise undesired inductive biases, it is paramount to be able to explore what the attention has learned. While static analyses of these models lead to targeted insights, interactive tools are more dynamic and can help humans better gain an intuition for the model-internal reasoning process. We present exBERT, an interactive tool named after the popular BERT language model, that","authors_text":"Benjamin Hoover, Hendrik Strobelt, Sebastian Gehrmann","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-11T16:10:55Z","title":"exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05276","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:c0ddb5e61430b34ffd9fe0a696ec6727d1593a3ae83fea5f59e49c7e4bd209fc","target":"record","created_at":"2026-07-05T00:11:27Z","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":"9e47f92c8b4e918bfa59903290bc37ae6250d720d9ab5d6ca34f45494b37e58f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-11T16:10:55Z","title_canon_sha256":"80149e4b5812aa1c489a405aa933c62be56698780d5993dfc2bf90d762b0828a"},"schema_version":"1.0","source":{"id":"1910.05276","kind":"arxiv","version":1}},"canonical_sha256":"3c2daa3ab7459e4642a9890a5896a65c05981f3e016a468feb1ffc0dbc6dc471","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c2daa3ab7459e4642a9890a5896a65c05981f3e016a468feb1ffc0dbc6dc471","first_computed_at":"2026-07-05T00:11:27.463573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:11:27.463573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EsBP1hsJtxF4/hJMSV3Att+9j/EDlr5VG/oqi5DsycNG7FOzxFIFnpGZhLEZFhwm9P4BwdEYB60Pe17oIJkKBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:11:27.463982Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.05276","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0ddb5e61430b34ffd9fe0a696ec6727d1593a3ae83fea5f59e49c7e4bd209fc","sha256:70bee474db7841eb06f43ce8fda596fe177ad9cca84db8d50a7fdbaa5e37411f"],"state_sha256":"cc974b6ac4c90232e6eb3a85a7da1b000d370a6271ba552b7753a52c925c8015"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yUkCpZzjbACSl86J1pM96w5jVV2FV5Q3+fmihyG0Z73cuI+F1JH4Up9O1Rpf+RnRRHkTdWX8DkHQ4ItXmqrOCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T04:00:51.452126Z","bundle_sha256":"7d92f95d7c465541c81355814935e2131e2b774cea82ca12fe8043f80e82355f"}}