{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZQXGCG5532266QY7JPTQ63SLT5","short_pith_number":"pith:ZQXGCG55","canonical_record":{"source":{"id":"2104.06967","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-04-14T16:49:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f07ac27e4d48653ee346114e2ed1f749dfe625a281dc193957fe0fcba4b96774","abstract_canon_sha256":"e0a3843bad6d87fead676fa22bba6d5d0e6c21b52a02b34a530e2c5839f539cb"},"schema_version":"1.0"},"canonical_sha256":"cc2e611bbddeb5ef431f4be70f6e4b9f6a23e7ff9d35a8bf50a046730e9b6097","source":{"kind":"arxiv","id":"2104.06967","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06967","created_at":"2026-07-05T02:43:33Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06967v2","created_at":"2026-07-05T02:43:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06967","created_at":"2026-07-05T02:43:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZQXGCG553226","created_at":"2026-07-05T02:43:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZQXGCG5532266QY7","created_at":"2026-07-05T02:43:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZQXGCG55","created_at":"2026-07-05T02:43:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZQXGCG5532266QY7JPTQ63SLT5","target":"record","payload":{"canonical_record":{"source":{"id":"2104.06967","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-04-14T16:49:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f07ac27e4d48653ee346114e2ed1f749dfe625a281dc193957fe0fcba4b96774","abstract_canon_sha256":"e0a3843bad6d87fead676fa22bba6d5d0e6c21b52a02b34a530e2c5839f539cb"},"schema_version":"1.0"},"canonical_sha256":"cc2e611bbddeb5ef431f4be70f6e4b9f6a23e7ff9d35a8bf50a046730e9b6097","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:43:34.000322Z","signature_b64":"dqmSI4CTN+LAy8tKvfomLtIGND4En5aEL8mdbXY4zNdh8qGowlkFA0gl5XKRefXii366YeL+St4fY7+kyoQrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc2e611bbddeb5ef431f4be70f6e4b9f6a23e7ff9d35a8bf50a046730e9b6097","last_reissued_at":"2026-07-05T02:43:33.999920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:43:33.999920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.06967","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":"2026-07-05T02:43:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yTXo+ZcxrbAIfH6g+5shWfrLuhHz5T8Rx1dD6e2CIYadyugdaqenSaSqnn0QUFdKYByZzbyruPOIoqfmTe34DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:50:38.953114Z"},"content_sha256":"083899fb5f6c7fb29e8402b052725018d7d5388856f131c5fe04b4204cc39bc3","schema_version":"1.0","event_id":"sha256:083899fb5f6c7fb29e8402b052725018d7d5388856f131c5fe04b4204cc39bc3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZQXGCG5532266QY7JPTQ63SLT5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Allan Hanbury, Jheng-Hong Yang, Jimmy Lin, Sebastian Hofst\\\"atter, Sheng-Chieh Lin","submitted_at":"2021-04-14T16:49:18Z","abstract_excerpt":"A vital step towards the widespread adoption of neural retrieval models is their resource efficiency throughout the training, indexing and query workflows. The neural IR community made great advancements in training effective dual-encoder dense retrieval (DR) models recently. A dense text retrieval model uses a single vector representation per query and passage to score a match, which enables low-latency first stage retrieval with a nearest neighbor search. Increasingly common, training approaches require enormous compute power, as they either conduct negative passage sampling out of a continu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06967","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/2104.06967/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":"2026-07-05T02:43:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R5Drcf2FQynZRFSnwby0v9tF5Bx8Du2MRP2f6x6oeN9RpiRrC+YAaugFFq6dnxKIrdKBEcKk7FAP0mvQD0H5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:50:38.953633Z"},"content_sha256":"5503b9d08f1f9607ccb9ae54ca2c31de3e1dfdf2f0cbb194e5d839679debd689","schema_version":"1.0","event_id":"sha256:5503b9d08f1f9607ccb9ae54ca2c31de3e1dfdf2f0cbb194e5d839679debd689"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQXGCG5532266QY7JPTQ63SLT5/bundle.json","state_url":"https://pith.science/pith/ZQXGCG5532266QY7JPTQ63SLT5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQXGCG5532266QY7JPTQ63SLT5/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":"2026-08-09T18:50:38Z","links":{"resolver":"https://pith.science/pith/ZQXGCG5532266QY7JPTQ63SLT5","bundle":"https://pith.science/pith/ZQXGCG5532266QY7JPTQ63SLT5/bundle.json","state":"https://pith.science/pith/ZQXGCG5532266QY7JPTQ63SLT5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQXGCG5532266QY7JPTQ63SLT5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZQXGCG5532266QY7JPTQ63SLT5","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":"e0a3843bad6d87fead676fa22bba6d5d0e6c21b52a02b34a530e2c5839f539cb","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-04-14T16:49:18Z","title_canon_sha256":"f07ac27e4d48653ee346114e2ed1f749dfe625a281dc193957fe0fcba4b96774"},"schema_version":"1.0","source":{"id":"2104.06967","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06967","created_at":"2026-07-05T02:43:33Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06967v2","created_at":"2026-07-05T02:43:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06967","created_at":"2026-07-05T02:43:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZQXGCG553226","created_at":"2026-07-05T02:43:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZQXGCG5532266QY7","created_at":"2026-07-05T02:43:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZQXGCG55","created_at":"2026-07-05T02:43:33Z"}],"graph_snapshots":[{"event_id":"sha256:5503b9d08f1f9607ccb9ae54ca2c31de3e1dfdf2f0cbb194e5d839679debd689","target":"graph","created_at":"2026-07-05T02:43:33Z","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/2104.06967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A vital step towards the widespread adoption of neural retrieval models is their resource efficiency throughout the training, indexing and query workflows. The neural IR community made great advancements in training effective dual-encoder dense retrieval (DR) models recently. A dense text retrieval model uses a single vector representation per query and passage to score a match, which enables low-latency first stage retrieval with a nearest neighbor search. Increasingly common, training approaches require enormous compute power, as they either conduct negative passage sampling out of a continu","authors_text":"Allan Hanbury, Jheng-Hong Yang, Jimmy Lin, Sebastian Hofst\\\"atter, Sheng-Chieh Lin","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-04-14T16:49:18Z","title":"Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06967","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":"sha256:083899fb5f6c7fb29e8402b052725018d7d5388856f131c5fe04b4204cc39bc3","target":"record","created_at":"2026-07-05T02:43:33Z","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":"e0a3843bad6d87fead676fa22bba6d5d0e6c21b52a02b34a530e2c5839f539cb","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-04-14T16:49:18Z","title_canon_sha256":"f07ac27e4d48653ee346114e2ed1f749dfe625a281dc193957fe0fcba4b96774"},"schema_version":"1.0","source":{"id":"2104.06967","kind":"arxiv","version":2}},"canonical_sha256":"cc2e611bbddeb5ef431f4be70f6e4b9f6a23e7ff9d35a8bf50a046730e9b6097","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc2e611bbddeb5ef431f4be70f6e4b9f6a23e7ff9d35a8bf50a046730e9b6097","first_computed_at":"2026-07-05T02:43:33.999920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:43:33.999920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dqmSI4CTN+LAy8tKvfomLtIGND4En5aEL8mdbXY4zNdh8qGowlkFA0gl5XKRefXii366YeL+St4fY7+kyoQrAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:43:34.000322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.06967","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:083899fb5f6c7fb29e8402b052725018d7d5388856f131c5fe04b4204cc39bc3","sha256:5503b9d08f1f9607ccb9ae54ca2c31de3e1dfdf2f0cbb194e5d839679debd689"],"state_sha256":"4d2c4a8a9d62f3e8443a3cbc2637c94d21246a931f95b152976c74834198d7fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"URLtgawS8w/djApacrMQXbFsV+tpEVD1Sr69JwlbdoghT344bN27BkjA1l7GBqD7oWBxzJZGEONcpdHRI6R+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:50:38.958782Z","bundle_sha256":"bd85ed67750d12a9713441b416ba3aa93a34ed84e8df93aa414dd66ad9234931"}}