{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LDFUKAU67IAHZT7M43OP4NDOUV","short_pith_number":"pith:LDFUKAU6","canonical_record":{"source":{"id":"2005.00181","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T02:21:17Z","cross_cats_sorted":[],"title_canon_sha256":"ca232320bc2953582d9b7fefa899bd808d13c77cbcb560f4fffe4314c6918f00","abstract_canon_sha256":"55a6e358feafe88168dde6b64b0734d847b013ebab75394ac9a7ca2367bcb0f9"},"schema_version":"1.0"},"canonical_sha256":"58cb45029efa007ccfece6dcfe346ea5455ea56d0b0da95228ef9695cf46c759","source":{"kind":"arxiv","id":"2005.00181","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00181","created_at":"2026-07-05T02:15:57Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00181v3","created_at":"2026-07-05T02:15:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00181","created_at":"2026-07-05T02:15:57Z"},{"alias_kind":"pith_short_12","alias_value":"LDFUKAU67IAH","created_at":"2026-07-05T02:15:57Z"},{"alias_kind":"pith_short_16","alias_value":"LDFUKAU67IAHZT7M","created_at":"2026-07-05T02:15:57Z"},{"alias_kind":"pith_short_8","alias_value":"LDFUKAU6","created_at":"2026-07-05T02:15:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LDFUKAU67IAHZT7M43OP4NDOUV","target":"record","payload":{"canonical_record":{"source":{"id":"2005.00181","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T02:21:17Z","cross_cats_sorted":[],"title_canon_sha256":"ca232320bc2953582d9b7fefa899bd808d13c77cbcb560f4fffe4314c6918f00","abstract_canon_sha256":"55a6e358feafe88168dde6b64b0734d847b013ebab75394ac9a7ca2367bcb0f9"},"schema_version":"1.0"},"canonical_sha256":"58cb45029efa007ccfece6dcfe346ea5455ea56d0b0da95228ef9695cf46c759","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:57.680854Z","signature_b64":"1V/FSu/A6utOXJRZcNYFzP09OFiKLp5RH7gKBpr7I6ioTzRqZ795upd2WPVGlHblHYDfthHlPOXtzaP1hWcOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58cb45029efa007ccfece6dcfe346ea5455ea56d0b0da95228ef9695cf46c759","last_reissued_at":"2026-07-05T02:15:57.680431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:57.680431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.00181","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":"2026-07-05T02:15:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZXRxQFm6uDmiLVDwsJbu5EhgxjwcmIOsnCs4nzWU1gD5ymX/WqPqdR8H2lozjBMyJ+GA4vBNOX9AfAKISPkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:49:06.220420Z"},"content_sha256":"ed5b9f2dda5eca97649c8ff73e7289ef564e15f61f8aacc6ce3c73caa67fe4ce","schema_version":"1.0","event_id":"sha256:ed5b9f2dda5eca97649c8ff73e7289ef564e15f61f8aacc6ce3c73caa67fe4ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LDFUKAU67IAHZT7M43OP4NDOUV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse, Dense, and Attentional Representations for Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jacob Eisenstein, Kristina Toutanova, Michael Collins, Yi Luan","submitted_at":"2020-05-01T02:21:17Z","abstract_excerpt":"Dual encoders perform retrieval by encoding documents and queries into dense lowdimensional vectors, scoring each document by its inner product with the query. We investigate the capacity of this architecture relative to sparse bag-of-words models and attentional neural networks. Using both theoretical and empirical analysis, we establish connections between the encoding dimension, the margin between gold and lower-ranked documents, and the document length, suggesting limitations in the capacity of fixed-length encodings to support precise retrieval of long documents. Building on these insight"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00181","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/2005.00181/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":"2026-07-05T02:15:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zb4tr8HfdctgYN1fKj4SrEXRevZ/WDoBSE08RdhqoJSh9Vs6PDdc9dQ6/KdDECHwZqaJnRzMxLdvB8+VX2sdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:49:06.220808Z"},"content_sha256":"376026961288ab8638ca5c8901fd79943bda3306454c930ce4ecaa1a9f6c93aa","schema_version":"1.0","event_id":"sha256:376026961288ab8638ca5c8901fd79943bda3306454c930ce4ecaa1a9f6c93aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LDFUKAU67IAHZT7M43OP4NDOUV/bundle.json","state_url":"https://pith.science/pith/LDFUKAU67IAHZT7M43OP4NDOUV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LDFUKAU67IAHZT7M43OP4NDOUV/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":"2026-07-06T10:49:06Z","links":{"resolver":"https://pith.science/pith/LDFUKAU67IAHZT7M43OP4NDOUV","bundle":"https://pith.science/pith/LDFUKAU67IAHZT7M43OP4NDOUV/bundle.json","state":"https://pith.science/pith/LDFUKAU67IAHZT7M43OP4NDOUV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LDFUKAU67IAHZT7M43OP4NDOUV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LDFUKAU67IAHZT7M43OP4NDOUV","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":"55a6e358feafe88168dde6b64b0734d847b013ebab75394ac9a7ca2367bcb0f9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T02:21:17Z","title_canon_sha256":"ca232320bc2953582d9b7fefa899bd808d13c77cbcb560f4fffe4314c6918f00"},"schema_version":"1.0","source":{"id":"2005.00181","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00181","created_at":"2026-07-05T02:15:57Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00181v3","created_at":"2026-07-05T02:15:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00181","created_at":"2026-07-05T02:15:57Z"},{"alias_kind":"pith_short_12","alias_value":"LDFUKAU67IAH","created_at":"2026-07-05T02:15:57Z"},{"alias_kind":"pith_short_16","alias_value":"LDFUKAU67IAHZT7M","created_at":"2026-07-05T02:15:57Z"},{"alias_kind":"pith_short_8","alias_value":"LDFUKAU6","created_at":"2026-07-05T02:15:57Z"}],"graph_snapshots":[{"event_id":"sha256:376026961288ab8638ca5c8901fd79943bda3306454c930ce4ecaa1a9f6c93aa","target":"graph","created_at":"2026-07-05T02:15:57Z","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/2005.00181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dual encoders perform retrieval by encoding documents and queries into dense lowdimensional vectors, scoring each document by its inner product with the query. We investigate the capacity of this architecture relative to sparse bag-of-words models and attentional neural networks. Using both theoretical and empirical analysis, we establish connections between the encoding dimension, the margin between gold and lower-ranked documents, and the document length, suggesting limitations in the capacity of fixed-length encodings to support precise retrieval of long documents. Building on these insight","authors_text":"Jacob Eisenstein, Kristina Toutanova, Michael Collins, Yi Luan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T02:21:17Z","title":"Sparse, Dense, and Attentional Representations for Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00181","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:ed5b9f2dda5eca97649c8ff73e7289ef564e15f61f8aacc6ce3c73caa67fe4ce","target":"record","created_at":"2026-07-05T02:15:57Z","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":"55a6e358feafe88168dde6b64b0734d847b013ebab75394ac9a7ca2367bcb0f9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T02:21:17Z","title_canon_sha256":"ca232320bc2953582d9b7fefa899bd808d13c77cbcb560f4fffe4314c6918f00"},"schema_version":"1.0","source":{"id":"2005.00181","kind":"arxiv","version":3}},"canonical_sha256":"58cb45029efa007ccfece6dcfe346ea5455ea56d0b0da95228ef9695cf46c759","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58cb45029efa007ccfece6dcfe346ea5455ea56d0b0da95228ef9695cf46c759","first_computed_at":"2026-07-05T02:15:57.680431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:15:57.680431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1V/FSu/A6utOXJRZcNYFzP09OFiKLp5RH7gKBpr7I6ioTzRqZ795upd2WPVGlHblHYDfthHlPOXtzaP1hWcOBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:15:57.680854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00181","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed5b9f2dda5eca97649c8ff73e7289ef564e15f61f8aacc6ce3c73caa67fe4ce","sha256:376026961288ab8638ca5c8901fd79943bda3306454c930ce4ecaa1a9f6c93aa"],"state_sha256":"8896240533b6846f4bc23f604edf91558e28d42bfc435bb159da2eab803804c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"//MmKCsxM6QKrP3FQJh79K7RUqO6V/XcCXaUNqDeqXGdp9V6+9N6pQJXMgJ8C+uxIQ8SPSJd1OcP01ShucpIAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:49:06.222871Z","bundle_sha256":"58e9a7d3f4eb95eaf1ac463d30aee86593dfd3ec48001267046304d9e4b5398f"}}