{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3RQRZZ326EOOK2IC5VMT4HQDUW","short_pith_number":"pith:3RQRZZ32","canonical_record":{"source":{"id":"2508.20778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-28T13:34:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0813e113cc6dbd2c552c197cbb8d4bca24b7bd3f6defb4efad799058d4dfe034","abstract_canon_sha256":"295b174a4b0f0b3330e76eaa2910e39180dd8516a6f8c6fcdb9639ab32e9beae"},"schema_version":"1.0"},"canonical_sha256":"dc611ce77af11ce56902ed593e1e03a595667deb640bd87590c95bce7c1cee89","source":{"kind":"arxiv","id":"2508.20778","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20778","created_at":"2026-07-05T12:02:07Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20778v2","created_at":"2026-07-05T12:02:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20778","created_at":"2026-07-05T12:02:07Z"},{"alias_kind":"pith_short_12","alias_value":"3RQRZZ326EOO","created_at":"2026-07-05T12:02:07Z"},{"alias_kind":"pith_short_16","alias_value":"3RQRZZ326EOOK2IC","created_at":"2026-07-05T12:02:07Z"},{"alias_kind":"pith_short_8","alias_value":"3RQRZZ32","created_at":"2026-07-05T12:02:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3RQRZZ326EOOK2IC5VMT4HQDUW","target":"record","payload":{"canonical_record":{"source":{"id":"2508.20778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-28T13:34:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0813e113cc6dbd2c552c197cbb8d4bca24b7bd3f6defb4efad799058d4dfe034","abstract_canon_sha256":"295b174a4b0f0b3330e76eaa2910e39180dd8516a6f8c6fcdb9639ab32e9beae"},"schema_version":"1.0"},"canonical_sha256":"dc611ce77af11ce56902ed593e1e03a595667deb640bd87590c95bce7c1cee89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:07.546252Z","signature_b64":"FKo2wZBWQyeLrPuCoRAQYwY/ckk2Uea8VTKgecSMpmtLyKCG2ll6Kdosnwk7DBK9WxBOaiRrDMEKRxIKMIPUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc611ce77af11ce56902ed593e1e03a595667deb640bd87590c95bce7c1cee89","last_reissued_at":"2026-07-05T12:02:07.545670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:07.545670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.20778","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":"2026-07-05T12:02:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xydERGc67R32n3RBGBb/+nBF80V07+tqXcGecpGyCdZ1jsEp0CuFwOlwrcjLXTunShU168qfdfG6K6zEFyXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:47:38.030485Z"},"content_sha256":"ecd14df5dbce2ec33e631a132884d6efefd5d43a15d3d45fdb3af6218b07f8e6","schema_version":"1.0","event_id":"sha256:ecd14df5dbce2ec33e631a132884d6efefd5d43a15d3d45fdb3af6218b07f8e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3RQRZZ326EOOK2IC5VMT4HQDUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Xinhao Huang, Ying Zhou, Yipeng Yu, Zeyi Wen, Zhibo Ren, Zulong Chen","submitted_at":"2025-08-28T13:34:42Z","abstract_excerpt":"In long structured document retrieval, existing methods typically fine-tune pre-trained language models (PLMs) using contrastive learning on datasets lacking explicit structural information. This practice suffers from two critical issues: 1) current methods fail to leverage structural features and element-level semantics effectively, and 2) the lack of datasets containing structural metadata. To bridge these gaps, we propose \\our, a novel contrastive learning framework. It leverages structure-aware learning to preserve semantic hierarchies and masked element alignment for fine-grained semantic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20778","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/2508.20778/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":"2026-07-05T12:02:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"taMoYkrFe6VZKxRaPRyZYrOngNe+LIqhj/G6F47XlBbOuucxRZ8Z2cfWk2inq6hwaK7sXSaHjtC0XqXH/qW7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:47:38.032375Z"},"content_sha256":"85a22f820f00e5a319529b6f6972d8c4e26ebf2d089396f37882bf54b1c7cf4b","schema_version":"1.0","event_id":"sha256:85a22f820f00e5a319529b6f6972d8c4e26ebf2d089396f37882bf54b1c7cf4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW/bundle.json","state_url":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RQRZZ326EOOK2IC5VMT4HQDUW/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":"2026-08-06T03:47:38Z","links":{"resolver":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW","bundle":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW/bundle.json","state":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RQRZZ326EOOK2IC5VMT4HQDUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3RQRZZ326EOOK2IC5VMT4HQDUW","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":"295b174a4b0f0b3330e76eaa2910e39180dd8516a6f8c6fcdb9639ab32e9beae","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-28T13:34:42Z","title_canon_sha256":"0813e113cc6dbd2c552c197cbb8d4bca24b7bd3f6defb4efad799058d4dfe034"},"schema_version":"1.0","source":{"id":"2508.20778","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20778","created_at":"2026-07-05T12:02:07Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20778v2","created_at":"2026-07-05T12:02:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20778","created_at":"2026-07-05T12:02:07Z"},{"alias_kind":"pith_short_12","alias_value":"3RQRZZ326EOO","created_at":"2026-07-05T12:02:07Z"},{"alias_kind":"pith_short_16","alias_value":"3RQRZZ326EOOK2IC","created_at":"2026-07-05T12:02:07Z"},{"alias_kind":"pith_short_8","alias_value":"3RQRZZ32","created_at":"2026-07-05T12:02:07Z"}],"graph_snapshots":[{"event_id":"sha256:85a22f820f00e5a319529b6f6972d8c4e26ebf2d089396f37882bf54b1c7cf4b","target":"graph","created_at":"2026-07-05T12:02:07Z","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/2508.20778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In long structured document retrieval, existing methods typically fine-tune pre-trained language models (PLMs) using contrastive learning on datasets lacking explicit structural information. This practice suffers from two critical issues: 1) current methods fail to leverage structural features and element-level semantics effectively, and 2) the lack of datasets containing structural metadata. To bridge these gaps, we propose \\our, a novel contrastive learning framework. It leverages structure-aware learning to preserve semantic hierarchies and masked element alignment for fine-grained semantic","authors_text":"Xinhao Huang, Ying Zhou, Yipeng Yu, Zeyi Wen, Zhibo Ren, Zulong Chen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-28T13:34:42Z","title":"SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20778","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:ecd14df5dbce2ec33e631a132884d6efefd5d43a15d3d45fdb3af6218b07f8e6","target":"record","created_at":"2026-07-05T12:02:07Z","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":"295b174a4b0f0b3330e76eaa2910e39180dd8516a6f8c6fcdb9639ab32e9beae","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-28T13:34:42Z","title_canon_sha256":"0813e113cc6dbd2c552c197cbb8d4bca24b7bd3f6defb4efad799058d4dfe034"},"schema_version":"1.0","source":{"id":"2508.20778","kind":"arxiv","version":2}},"canonical_sha256":"dc611ce77af11ce56902ed593e1e03a595667deb640bd87590c95bce7c1cee89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc611ce77af11ce56902ed593e1e03a595667deb640bd87590c95bce7c1cee89","first_computed_at":"2026-07-05T12:02:07.545670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:07.545670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FKo2wZBWQyeLrPuCoRAQYwY/ckk2Uea8VTKgecSMpmtLyKCG2ll6Kdosnwk7DBK9WxBOaiRrDMEKRxIKMIPUCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:07.546252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.20778","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecd14df5dbce2ec33e631a132884d6efefd5d43a15d3d45fdb3af6218b07f8e6","sha256:85a22f820f00e5a319529b6f6972d8c4e26ebf2d089396f37882bf54b1c7cf4b"],"state_sha256":"94113cc0470df5b2f1d811ae793ff656e1b7837823f858bf96877d3b73e7ed35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aIkyyHci3vu7mulywsiuCu5l4TuSLZhOXKj75w2T+5mdYKW0xJXyIKnOieU6wNsohDusVdtNF5yPrgR84jrBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:47:38.068826Z","bundle_sha256":"7cae60f19ae3f9f6606017e47d4cf0bdcd8e53a7fdb9589d6347a4a5bc8ad42c"}}