{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6J4EYKOMYOXQ36LFZJY5DK2H4E","short_pith_number":"pith:6J4EYKOM","canonical_record":{"source":{"id":"2312.06648","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-11T18:57:35Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"7ab6ea3c38d6a79d00140ad28fd1928c1f3b10782a9bb21398ba5b61e625db99","abstract_canon_sha256":"491a5a148ca5f5ee2c67303b5a60f5d2a27380657667289047bccb6feeecfd5c"},"schema_version":"1.0"},"canonical_sha256":"f2784c29ccc3af0df965ca71d1ab47e10b1b56a57f6e6a347611d1e0cb3120b1","source":{"kind":"arxiv","id":"2312.06648","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06648","created_at":"2026-07-05T09:15:28Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06648v3","created_at":"2026-07-05T09:15:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06648","created_at":"2026-07-05T09:15:28Z"},{"alias_kind":"pith_short_12","alias_value":"6J4EYKOMYOXQ","created_at":"2026-07-05T09:15:28Z"},{"alias_kind":"pith_short_16","alias_value":"6J4EYKOMYOXQ36LF","created_at":"2026-07-05T09:15:28Z"},{"alias_kind":"pith_short_8","alias_value":"6J4EYKOM","created_at":"2026-07-05T09:15:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6J4EYKOMYOXQ36LFZJY5DK2H4E","target":"record","payload":{"canonical_record":{"source":{"id":"2312.06648","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-11T18:57:35Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"7ab6ea3c38d6a79d00140ad28fd1928c1f3b10782a9bb21398ba5b61e625db99","abstract_canon_sha256":"491a5a148ca5f5ee2c67303b5a60f5d2a27380657667289047bccb6feeecfd5c"},"schema_version":"1.0"},"canonical_sha256":"f2784c29ccc3af0df965ca71d1ab47e10b1b56a57f6e6a347611d1e0cb3120b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:28.632031Z","signature_b64":"IdwqFI9u9TeIiP/GnEfiqEVp30Ulvh/gdZNRE1iq4TIqulS5SKMvf1L/atdFCRTm1AOXSVmjfmVNPcM7ECu6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2784c29ccc3af0df965ca71d1ab47e10b1b56a57f6e6a347611d1e0cb3120b1","last_reissued_at":"2026-07-05T09:15:28.631500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:28.631500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.06648","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":"2026-07-05T09:15:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wphn+rB737/JlatppWzS0SqSRRCGVG0xRIQLLSXvtni9QoOjuJCDBwYxYijIwG63JhafjfmH34linGqy3BOXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:54:32.893080Z"},"content_sha256":"546f8a65c3435f1fda5f9749f9608d53a6dc9690a8964dfb21b53ed0556bde87","schema_version":"1.0","event_id":"sha256:546f8a65c3435f1fda5f9749f9608d53a6dc9690a8964dfb21b53ed0556bde87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6J4EYKOMYOXQ36LFZJY5DK2H4E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dense X Retrieval: What Retrieval Granularity Should We Use?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Hongming Zhang, Hongwei Wang, Kaixin Ma, Sihao Chen, Tong Chen, Wenhao Yu, Xinran Zhao","submitted_at":"2023-12-11T18:57:35Z","abstract_excerpt":"Dense retrieval has become a prominent method to obtain relevant context or world knowledge in open-domain NLP tasks. When we use a learned dense retriever on a retrieval corpus at inference time, an often-overlooked design choice is the retrieval unit in which the corpus is indexed, e.g. document, passage, or sentence. We discover that the retrieval unit choice significantly impacts the performance of both retrieval and downstream tasks. Distinct from the typical approach of using passages or sentences, we introduce a novel retrieval unit, proposition, for dense retrieval. Propositions are de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06648","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/2312.06648/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":"2026-07-05T09:15:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJA5PP0Kdpgh6oQ4XuBDrq0A/Ifosfa4uWQ4XESE/g6Yk1oS+0rIKmXkMmqwGGaD/if9qwISYd2WpQwKjcsDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:54:32.893620Z"},"content_sha256":"23ec63fe3d21c4d2ce9f02cb14f0fbe40e9aaa629564c07110e575ad7f446c72","schema_version":"1.0","event_id":"sha256:23ec63fe3d21c4d2ce9f02cb14f0fbe40e9aaa629564c07110e575ad7f446c72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6J4EYKOMYOXQ36LFZJY5DK2H4E/bundle.json","state_url":"https://pith.science/pith/6J4EYKOMYOXQ36LFZJY5DK2H4E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6J4EYKOMYOXQ36LFZJY5DK2H4E/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":"2026-08-10T06:54:32Z","links":{"resolver":"https://pith.science/pith/6J4EYKOMYOXQ36LFZJY5DK2H4E","bundle":"https://pith.science/pith/6J4EYKOMYOXQ36LFZJY5DK2H4E/bundle.json","state":"https://pith.science/pith/6J4EYKOMYOXQ36LFZJY5DK2H4E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6J4EYKOMYOXQ36LFZJY5DK2H4E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6J4EYKOMYOXQ36LFZJY5DK2H4E","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":"491a5a148ca5f5ee2c67303b5a60f5d2a27380657667289047bccb6feeecfd5c","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-11T18:57:35Z","title_canon_sha256":"7ab6ea3c38d6a79d00140ad28fd1928c1f3b10782a9bb21398ba5b61e625db99"},"schema_version":"1.0","source":{"id":"2312.06648","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06648","created_at":"2026-07-05T09:15:28Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06648v3","created_at":"2026-07-05T09:15:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06648","created_at":"2026-07-05T09:15:28Z"},{"alias_kind":"pith_short_12","alias_value":"6J4EYKOMYOXQ","created_at":"2026-07-05T09:15:28Z"},{"alias_kind":"pith_short_16","alias_value":"6J4EYKOMYOXQ36LF","created_at":"2026-07-05T09:15:28Z"},{"alias_kind":"pith_short_8","alias_value":"6J4EYKOM","created_at":"2026-07-05T09:15:28Z"}],"graph_snapshots":[{"event_id":"sha256:23ec63fe3d21c4d2ce9f02cb14f0fbe40e9aaa629564c07110e575ad7f446c72","target":"graph","created_at":"2026-07-05T09:15:28Z","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/2312.06648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense retrieval has become a prominent method to obtain relevant context or world knowledge in open-domain NLP tasks. When we use a learned dense retriever on a retrieval corpus at inference time, an often-overlooked design choice is the retrieval unit in which the corpus is indexed, e.g. document, passage, or sentence. We discover that the retrieval unit choice significantly impacts the performance of both retrieval and downstream tasks. Distinct from the typical approach of using passages or sentences, we introduce a novel retrieval unit, proposition, for dense retrieval. Propositions are de","authors_text":"Dong Yu, Hongming Zhang, Hongwei Wang, Kaixin Ma, Sihao Chen, Tong Chen, Wenhao Yu, Xinran Zhao","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-11T18:57:35Z","title":"Dense X Retrieval: What Retrieval Granularity Should We Use?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06648","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":"sha256:546f8a65c3435f1fda5f9749f9608d53a6dc9690a8964dfb21b53ed0556bde87","target":"record","created_at":"2026-07-05T09:15:28Z","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":"491a5a148ca5f5ee2c67303b5a60f5d2a27380657667289047bccb6feeecfd5c","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-11T18:57:35Z","title_canon_sha256":"7ab6ea3c38d6a79d00140ad28fd1928c1f3b10782a9bb21398ba5b61e625db99"},"schema_version":"1.0","source":{"id":"2312.06648","kind":"arxiv","version":3}},"canonical_sha256":"f2784c29ccc3af0df965ca71d1ab47e10b1b56a57f6e6a347611d1e0cb3120b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2784c29ccc3af0df965ca71d1ab47e10b1b56a57f6e6a347611d1e0cb3120b1","first_computed_at":"2026-07-05T09:15:28.631500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:28.631500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IdwqFI9u9TeIiP/GnEfiqEVp30Ulvh/gdZNRE1iq4TIqulS5SKMvf1L/atdFCRTm1AOXSVmjfmVNPcM7ECu6Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:28.632031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06648","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:546f8a65c3435f1fda5f9749f9608d53a6dc9690a8964dfb21b53ed0556bde87","sha256:23ec63fe3d21c4d2ce9f02cb14f0fbe40e9aaa629564c07110e575ad7f446c72"],"state_sha256":"62ca50415874cccffab3205aea82eea5ecd78b924d43e8d2ef1093fafdc96e98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VDY9an87BRFarT7noq7XSf1RUt2sCe/ld0QVIBCvpTIo0V3nXPZLnkCAm5w2MmUMhMJEoRX4TTP+FOY6BrheCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:54:32.900493Z","bundle_sha256":"e1802941c529c409265eabefc8b24dc62df63755f2b2c5c91a70996b222d2ad7"}}