{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:F63RM22U2UTOC7YEERGG7RP6NV","short_pith_number":"pith:F63RM22U","canonical_record":{"source":{"id":"2104.08253","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-16T17:36:44Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"7602647d7f4ef92bd13e57889b1d5934e4256ed2d4a895d98c36564a8db0e4f1","abstract_canon_sha256":"b3192b396769516004b57fe85cc48d529b158579284f7edf58bbcc26072c993e"},"schema_version":"1.0"},"canonical_sha256":"2fb7166b54d526e17f04244c6fc5fe6d400a3a6935eaae65b7483a1269edd3c0","source":{"kind":"arxiv","id":"2104.08253","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08253","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08253v2","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08253","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_12","alias_value":"F63RM22U2UTO","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_16","alias_value":"F63RM22U2UTOC7YE","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_8","alias_value":"F63RM22U","created_at":"2026-07-05T03:15:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:F63RM22U2UTOC7YEERGG7RP6NV","target":"record","payload":{"canonical_record":{"source":{"id":"2104.08253","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-16T17:36:44Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"7602647d7f4ef92bd13e57889b1d5934e4256ed2d4a895d98c36564a8db0e4f1","abstract_canon_sha256":"b3192b396769516004b57fe85cc48d529b158579284f7edf58bbcc26072c993e"},"schema_version":"1.0"},"canonical_sha256":"2fb7166b54d526e17f04244c6fc5fe6d400a3a6935eaae65b7483a1269edd3c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:52.472527Z","signature_b64":"ahfuNjtttK5pSw/VIxrj4kXviUf14llxdw8TJztlYMYyKv5rmkTAwV85H+JdmoHXQI9zNPbgL4mH/uG4gIIGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fb7166b54d526e17f04244c6fc5fe6d400a3a6935eaae65b7483a1269edd3c0","last_reissued_at":"2026-07-05T03:15:52.472083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:52.472083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.08253","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":"2026-07-05T03:15:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tb/E8/3y3CfsCIzSkj+h9S+JhcrWrXDt9YrtEWL45f1SUV34Ws7IyXeGvUVHEG6lUmy9fUSiLl8oUN3asxb3DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:55:27.786164Z"},"content_sha256":"634867e9923141b07d5e9348e2db40d038deff6f441010d7bc0f8a9b94a7c951","schema_version":"1.0","event_id":"sha256:634867e9923141b07d5e9348e2db40d038deff6f441010d7bc0f8a9b94a7c951"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:F63RM22U2UTOC7YEERGG7RP6NV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Condenser: a Pre-training Architecture for Dense Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jamie Callan, Luyu Gao","submitted_at":"2021-04-16T17:36:44Z","abstract_excerpt":"Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient text comparison and retrieval. However, dense encoders require a lot of data and sophisticated techniques to effectively train and suffer in low data situations. This paper finds a key reason is that standard LMs' internal attention structure is not ready-to-use for dense encoders, which needs to aggregate text information into the dense representation. We pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08253","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/2104.08253/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":"2026-07-05T03:15:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OPYCesjZTpOa1Q6wkS4+0rRMHDuZgLFNzBQSOXx9xjfEuu86dVcxYXkRJYPCg4zwxwRe4t1rhI21jU1jxAyKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:55:27.787075Z"},"content_sha256":"78c1b9d2c912161d26ac737d39a4376c85c44b76aac7b1e7e18499c548946b59","schema_version":"1.0","event_id":"sha256:78c1b9d2c912161d26ac737d39a4376c85c44b76aac7b1e7e18499c548946b59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F63RM22U2UTOC7YEERGG7RP6NV/bundle.json","state_url":"https://pith.science/pith/F63RM22U2UTOC7YEERGG7RP6NV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F63RM22U2UTOC7YEERGG7RP6NV/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":"2026-08-08T04:55:27Z","links":{"resolver":"https://pith.science/pith/F63RM22U2UTOC7YEERGG7RP6NV","bundle":"https://pith.science/pith/F63RM22U2UTOC7YEERGG7RP6NV/bundle.json","state":"https://pith.science/pith/F63RM22U2UTOC7YEERGG7RP6NV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F63RM22U2UTOC7YEERGG7RP6NV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:F63RM22U2UTOC7YEERGG7RP6NV","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":"b3192b396769516004b57fe85cc48d529b158579284f7edf58bbcc26072c993e","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-16T17:36:44Z","title_canon_sha256":"7602647d7f4ef92bd13e57889b1d5934e4256ed2d4a895d98c36564a8db0e4f1"},"schema_version":"1.0","source":{"id":"2104.08253","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08253","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08253v2","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08253","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_12","alias_value":"F63RM22U2UTO","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_16","alias_value":"F63RM22U2UTOC7YE","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_8","alias_value":"F63RM22U","created_at":"2026-07-05T03:15:52Z"}],"graph_snapshots":[{"event_id":"sha256:78c1b9d2c912161d26ac737d39a4376c85c44b76aac7b1e7e18499c548946b59","target":"graph","created_at":"2026-07-05T03:15:52Z","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/2104.08253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient text comparison and retrieval. However, dense encoders require a lot of data and sophisticated techniques to effectively train and suffer in low data situations. This paper finds a key reason is that standard LMs' internal attention structure is not ready-to-use for dense encoders, which needs to aggregate text information into the dense representation. We pr","authors_text":"Jamie Callan, Luyu Gao","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-16T17:36:44Z","title":"Condenser: a Pre-training Architecture for Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08253","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":"sha256:634867e9923141b07d5e9348e2db40d038deff6f441010d7bc0f8a9b94a7c951","target":"record","created_at":"2026-07-05T03:15:52Z","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":"b3192b396769516004b57fe85cc48d529b158579284f7edf58bbcc26072c993e","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-16T17:36:44Z","title_canon_sha256":"7602647d7f4ef92bd13e57889b1d5934e4256ed2d4a895d98c36564a8db0e4f1"},"schema_version":"1.0","source":{"id":"2104.08253","kind":"arxiv","version":2}},"canonical_sha256":"2fb7166b54d526e17f04244c6fc5fe6d400a3a6935eaae65b7483a1269edd3c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fb7166b54d526e17f04244c6fc5fe6d400a3a6935eaae65b7483a1269edd3c0","first_computed_at":"2026-07-05T03:15:52.472083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:52.472083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ahfuNjtttK5pSw/VIxrj4kXviUf14llxdw8TJztlYMYyKv5rmkTAwV85H+JdmoHXQI9zNPbgL4mH/uG4gIIGDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:52.472527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08253","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:634867e9923141b07d5e9348e2db40d038deff6f441010d7bc0f8a9b94a7c951","sha256:78c1b9d2c912161d26ac737d39a4376c85c44b76aac7b1e7e18499c548946b59"],"state_sha256":"ba9a75efa83ef5598558aa816bf95d6f17d6affc112d10f77a36a872329e86ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UHJ6gxbQUHrQDPofp1JnmAXgzQu/x5tY5AlkGpeWCwQ2/r5QEDAvgPHpxJGYhBFhzhRYjHgNwz077d/qAk8YDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:55:27.792456Z","bundle_sha256":"136a6f29dfd23622671294f04815545a840d8bf2cf2e61c3a4891b63f5fa67bb"}}