{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6GNTDXN5EZO4QQ6HKGUZPOOU6O","short_pith_number":"pith:6GNTDXN5","canonical_record":{"source":{"id":"2212.10380","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T16:03:25Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"006c1c6fb62eeb823b6517a065a4b02d48387a915c8e9cba55264ea318b99cfa","abstract_canon_sha256":"50baa4b99383945fb038f00b6aa3c4b60d50765cbc49abfdef548c6bf63e849e"},"schema_version":"1.0"},"canonical_sha256":"f19b31ddbd265dc843c751a997b9d4f38ce4b37086c145e3252d726650bef3a3","source":{"kind":"arxiv","id":"2212.10380","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10380","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10380v2","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10380","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"6GNTDXN5EZO4","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"6GNTDXN5EZO4QQ6H","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"6GNTDXN5","created_at":"2026-07-05T06:13:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6GNTDXN5EZO4QQ6HKGUZPOOU6O","target":"record","payload":{"canonical_record":{"source":{"id":"2212.10380","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T16:03:25Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"006c1c6fb62eeb823b6517a065a4b02d48387a915c8e9cba55264ea318b99cfa","abstract_canon_sha256":"50baa4b99383945fb038f00b6aa3c4b60d50765cbc49abfdef548c6bf63e849e"},"schema_version":"1.0"},"canonical_sha256":"f19b31ddbd265dc843c751a997b9d4f38ce4b37086c145e3252d726650bef3a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:18.476437Z","signature_b64":"m6fb/hqF4e7tri/OZI+pBOKrfnU/0/m9VKRYzkXTJ05U1IRGgi3QFL1cAZEczkDyPQtoXEJbtKQwgtBcu2JRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f19b31ddbd265dc843c751a997b9d4f38ce4b37086c145e3252d726650bef3a3","last_reissued_at":"2026-07-05T06:13:18.475920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:18.475920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.10380","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mNqExKgTpYNhuqenCpVgTOGfX3Qq8yfdJInENgfABhSVuN4i+X7myTl3rRlw+q9neeUGnXJAbf8Vf+w7Fpg/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:40:39.206690Z"},"content_sha256":"038ec6635bf8412ff6f4acde2fa4ab80838f5f4388342adbcdae6cef5b9b423f","schema_version":"1.0","event_id":"sha256:038ec6635bf8412ff6f4acde2fa4ab80838f5f4388342adbcdae6cef5b9b423f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6GNTDXN5EZO4QQ6HKGUZPOOU6O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Adi Zicher, Amir Globerson, Jonathan Berant, Liat Bezalel, Ori Ram, Yonatan Belinkov","submitted_at":"2022-12-20T16:03:25Z","abstract_excerpt":"Dual encoders are now the dominant architecture for dense retrieval. Yet, we have little understanding of how they represent text, and why this leads to good performance. In this work, we shed light on this question via distributions over the vocabulary. We propose to interpret the vector representations produced by dual encoders by projecting them into the model's vocabulary space. We show that the resulting projections contain rich semantic information, and draw connection between them and sparse retrieval. We find that this view can offer an explanation for some of the failure cases of dens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10380","kind":"arxiv","version":2},"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/2212.10380/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":"2026-07-05T06:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pwu1/5McHgtvGhKozpFOavMnM4nEjH+Q9XsLQJjfRhfa5GJPgqD9OlXUGwbJsolzahBN6qNNZ1jdrhB7pqh4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:40:39.207191Z"},"content_sha256":"2cac1cb47468ac64f300d0a4f5bec85a89aed6896fa1435026a293b0bcb8d12b","schema_version":"1.0","event_id":"sha256:2cac1cb47468ac64f300d0a4f5bec85a89aed6896fa1435026a293b0bcb8d12b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6GNTDXN5EZO4QQ6HKGUZPOOU6O/bundle.json","state_url":"https://pith.science/pith/6GNTDXN5EZO4QQ6HKGUZPOOU6O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6GNTDXN5EZO4QQ6HKGUZPOOU6O/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":"2026-08-08T14:40:39Z","links":{"resolver":"https://pith.science/pith/6GNTDXN5EZO4QQ6HKGUZPOOU6O","bundle":"https://pith.science/pith/6GNTDXN5EZO4QQ6HKGUZPOOU6O/bundle.json","state":"https://pith.science/pith/6GNTDXN5EZO4QQ6HKGUZPOOU6O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6GNTDXN5EZO4QQ6HKGUZPOOU6O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6GNTDXN5EZO4QQ6HKGUZPOOU6O","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":"50baa4b99383945fb038f00b6aa3c4b60d50765cbc49abfdef548c6bf63e849e","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T16:03:25Z","title_canon_sha256":"006c1c6fb62eeb823b6517a065a4b02d48387a915c8e9cba55264ea318b99cfa"},"schema_version":"1.0","source":{"id":"2212.10380","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10380","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10380v2","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10380","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"6GNTDXN5EZO4","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"6GNTDXN5EZO4QQ6H","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"6GNTDXN5","created_at":"2026-07-05T06:13:18Z"}],"graph_snapshots":[{"event_id":"sha256:2cac1cb47468ac64f300d0a4f5bec85a89aed6896fa1435026a293b0bcb8d12b","target":"graph","created_at":"2026-07-05T06:13:18Z","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/2212.10380/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dual encoders are now the dominant architecture for dense retrieval. Yet, we have little understanding of how they represent text, and why this leads to good performance. In this work, we shed light on this question via distributions over the vocabulary. We propose to interpret the vector representations produced by dual encoders by projecting them into the model's vocabulary space. We show that the resulting projections contain rich semantic information, and draw connection between them and sparse retrieval. We find that this view can offer an explanation for some of the failure cases of dens","authors_text":"Adi Zicher, Amir Globerson, Jonathan Berant, Liat Bezalel, Ori Ram, Yonatan Belinkov","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T16:03:25Z","title":"What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10380","kind":"arxiv","version":2},"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":"sha256:038ec6635bf8412ff6f4acde2fa4ab80838f5f4388342adbcdae6cef5b9b423f","target":"record","created_at":"2026-07-05T06:13:18Z","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":"50baa4b99383945fb038f00b6aa3c4b60d50765cbc49abfdef548c6bf63e849e","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T16:03:25Z","title_canon_sha256":"006c1c6fb62eeb823b6517a065a4b02d48387a915c8e9cba55264ea318b99cfa"},"schema_version":"1.0","source":{"id":"2212.10380","kind":"arxiv","version":2}},"canonical_sha256":"f19b31ddbd265dc843c751a997b9d4f38ce4b37086c145e3252d726650bef3a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f19b31ddbd265dc843c751a997b9d4f38ce4b37086c145e3252d726650bef3a3","first_computed_at":"2026-07-05T06:13:18.475920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:18.475920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m6fb/hqF4e7tri/OZI+pBOKrfnU/0/m9VKRYzkXTJ05U1IRGgi3QFL1cAZEczkDyPQtoXEJbtKQwgtBcu2JRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:18.476437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10380","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:038ec6635bf8412ff6f4acde2fa4ab80838f5f4388342adbcdae6cef5b9b423f","sha256:2cac1cb47468ac64f300d0a4f5bec85a89aed6896fa1435026a293b0bcb8d12b"],"state_sha256":"b3a8c138b0ed2a7f3e051d348bd560235989443ddf4b3d2c3bb506c92c949bc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GGv/X/xRJy1Jbfrm+gH5ctEOxvWLTjk/D//5N5guPvjjBuX+TO052IIop4yQuB2Z6XjpRa1H87HZpUoDc320Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:40:39.210991Z","bundle_sha256":"9d66c6394af5cbdf0386bf12887200eb3cb78b0159fe824c722e4c59a1e4a272"}}