{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:52LSVBLYBQB5CLCF3MREBINDKH","short_pith_number":"pith:52LSVBLY","canonical_record":{"source":{"id":"2211.10841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-11-20T01:28:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bc0229f12ab7fc276d14e15468ff7bdc01f21b34cfda2eed6f29c4c24f84d851","abstract_canon_sha256":"e6163a81e1db3dc163c4deb824ad10374c8be22f5049bc5856df6c3cd64d8b26"},"schema_version":"1.0"},"canonical_sha256":"ee972a85780c03d12c45db2240a1a351fa8cc2349a855182e53a23dcb2ccc4ff","source":{"kind":"arxiv","id":"2211.10841","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.10841","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"arxiv_version","alias_value":"2211.10841v1","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10841","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"pith_short_12","alias_value":"52LSVBLYBQB5","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"pith_short_16","alias_value":"52LSVBLYBQB5CLCF","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"pith_short_8","alias_value":"52LSVBLY","created_at":"2026-07-05T05:17:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:52LSVBLYBQB5CLCF3MREBINDKH","target":"record","payload":{"canonical_record":{"source":{"id":"2211.10841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-11-20T01:28:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bc0229f12ab7fc276d14e15468ff7bdc01f21b34cfda2eed6f29c4c24f84d851","abstract_canon_sha256":"e6163a81e1db3dc163c4deb824ad10374c8be22f5049bc5856df6c3cd64d8b26"},"schema_version":"1.0"},"canonical_sha256":"ee972a85780c03d12c45db2240a1a351fa8cc2349a855182e53a23dcb2ccc4ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:35.478501Z","signature_b64":"Wgo3em5sK86coEC9EP0wUD1obq9+qPw0hway7yxmQtiqF5H5vRbmknTT+aU5mWXMH5ipR8/CEU2IDrvLNqfBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee972a85780c03d12c45db2240a1a351fa8cc2349a855182e53a23dcb2ccc4ff","last_reissued_at":"2026-07-05T05:17:35.477959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:35.477959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.10841","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:17:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mAynVxXtmmbQxAxgjhD4yXv5ttgQX7zRFn9hLqARMAfmbFZZSWKIaQZqjUoFZYEQNGHo7pBVGgY1iTc1YFF9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:50:46.551063Z"},"content_sha256":"3d5194c54533a739fa72d3f518d12c8b4b86766910ee63999457b6c257929037","schema_version":"1.0","event_id":"sha256:3d5194c54533a739fa72d3f518d12c8b4b86766910ee63999457b6c257929037"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:52LSVBLYBQB5CLCF3MREBINDKH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SeDR: Segment Representation Learning for Long Documents Dense Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Dongfang Li, Junying Chen, Qingcai Chen, Yutao Huang","submitted_at":"2022-11-20T01:28:44Z","abstract_excerpt":"Recently, Dense Retrieval (DR) has become a promising solution to document retrieval, where document representations are used to perform effective and efficient semantic search. However, DR remains challenging on long documents, due to the quadratic complexity of its Transformer-based encoder and the finite capacity of a low-dimension embedding. Current DR models use suboptimal strategies such as truncating or splitting-and-pooling to long documents leading to poor utilization of whole document information. In this work, to tackle this problem, we propose Segment representation learning for lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10841","kind":"arxiv","version":1},"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/2211.10841/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":"2026-07-05T05:17:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JSDwc9N9ky0updWHCPwTZAKoxtk6U36D/MPkSFU9c40hA6VXc3wfTKPYy99xWaRvQaC9DDhk0mjKPRETqQ9vBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:50:46.551573Z"},"content_sha256":"4e02be906d8134a1d36f36507c6ab5f379f723bcb51f30ddccda82e6ac33a3db","schema_version":"1.0","event_id":"sha256:4e02be906d8134a1d36f36507c6ab5f379f723bcb51f30ddccda82e6ac33a3db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/52LSVBLYBQB5CLCF3MREBINDKH/bundle.json","state_url":"https://pith.science/pith/52LSVBLYBQB5CLCF3MREBINDKH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/52LSVBLYBQB5CLCF3MREBINDKH/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":"2026-08-06T18:50:46Z","links":{"resolver":"https://pith.science/pith/52LSVBLYBQB5CLCF3MREBINDKH","bundle":"https://pith.science/pith/52LSVBLYBQB5CLCF3MREBINDKH/bundle.json","state":"https://pith.science/pith/52LSVBLYBQB5CLCF3MREBINDKH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/52LSVBLYBQB5CLCF3MREBINDKH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:52LSVBLYBQB5CLCF3MREBINDKH","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":"e6163a81e1db3dc163c4deb824ad10374c8be22f5049bc5856df6c3cd64d8b26","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-11-20T01:28:44Z","title_canon_sha256":"bc0229f12ab7fc276d14e15468ff7bdc01f21b34cfda2eed6f29c4c24f84d851"},"schema_version":"1.0","source":{"id":"2211.10841","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.10841","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"arxiv_version","alias_value":"2211.10841v1","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10841","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"pith_short_12","alias_value":"52LSVBLYBQB5","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"pith_short_16","alias_value":"52LSVBLYBQB5CLCF","created_at":"2026-07-05T05:17:35Z"},{"alias_kind":"pith_short_8","alias_value":"52LSVBLY","created_at":"2026-07-05T05:17:35Z"}],"graph_snapshots":[{"event_id":"sha256:4e02be906d8134a1d36f36507c6ab5f379f723bcb51f30ddccda82e6ac33a3db","target":"graph","created_at":"2026-07-05T05:17:35Z","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/2211.10841/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Dense Retrieval (DR) has become a promising solution to document retrieval, where document representations are used to perform effective and efficient semantic search. However, DR remains challenging on long documents, due to the quadratic complexity of its Transformer-based encoder and the finite capacity of a low-dimension embedding. Current DR models use suboptimal strategies such as truncating or splitting-and-pooling to long documents leading to poor utilization of whole document information. In this work, to tackle this problem, we propose Segment representation learning for lo","authors_text":"Dongfang Li, Junying Chen, Qingcai Chen, Yutao Huang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-11-20T01:28:44Z","title":"SeDR: Segment Representation Learning for Long Documents Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10841","kind":"arxiv","version":1},"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":"sha256:3d5194c54533a739fa72d3f518d12c8b4b86766910ee63999457b6c257929037","target":"record","created_at":"2026-07-05T05:17:35Z","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":"e6163a81e1db3dc163c4deb824ad10374c8be22f5049bc5856df6c3cd64d8b26","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-11-20T01:28:44Z","title_canon_sha256":"bc0229f12ab7fc276d14e15468ff7bdc01f21b34cfda2eed6f29c4c24f84d851"},"schema_version":"1.0","source":{"id":"2211.10841","kind":"arxiv","version":1}},"canonical_sha256":"ee972a85780c03d12c45db2240a1a351fa8cc2349a855182e53a23dcb2ccc4ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee972a85780c03d12c45db2240a1a351fa8cc2349a855182e53a23dcb2ccc4ff","first_computed_at":"2026-07-05T05:17:35.477959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:35.477959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wgo3em5sK86coEC9EP0wUD1obq9+qPw0hway7yxmQtiqF5H5vRbmknTT+aU5mWXMH5ipR8/CEU2IDrvLNqfBAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:35.478501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.10841","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d5194c54533a739fa72d3f518d12c8b4b86766910ee63999457b6c257929037","sha256:4e02be906d8134a1d36f36507c6ab5f379f723bcb51f30ddccda82e6ac33a3db"],"state_sha256":"1650db665deec9c26f31e69ce5cf70a3522a3948b7070e431a961c27359780c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NzwNWrbQCsYKutHnO/V8Z4yx4IyiXUslycfjhA5YOu0VMedU18F+qxK/11O7O50RQTljBe4Z8XcLu3rl/DPLAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:50:46.556183Z","bundle_sha256":"e5db5697a1c0c9cd777fac8e376149f94eb7a015fd8e08a61940b3880cd1d579"}}