{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:H3PRPCNSYJORLJZOYGHNUFRQVJ","short_pith_number":"pith:H3PRPCNS","canonical_record":{"source":{"id":"2412.08196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T08:36:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c799a95ca056ba210851aa841411e2a8e1aa9b7c17f477f304dc7ac5f1c0990e","abstract_canon_sha256":"ddf17f687f2f11be9338db3f86301c362265eed798f9ff54da2c0d7e911b52d9"},"schema_version":"1.0"},"canonical_sha256":"3edf1789b2c25d15a72ec18eda1630aa5a8c66d76556d9492bff18c34dd828f1","source":{"kind":"arxiv","id":"2412.08196","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08196","created_at":"2026-07-05T09:47:45Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08196v1","created_at":"2026-07-05T09:47:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08196","created_at":"2026-07-05T09:47:45Z"},{"alias_kind":"pith_short_12","alias_value":"H3PRPCNSYJOR","created_at":"2026-07-05T09:47:45Z"},{"alias_kind":"pith_short_16","alias_value":"H3PRPCNSYJORLJZO","created_at":"2026-07-05T09:47:45Z"},{"alias_kind":"pith_short_8","alias_value":"H3PRPCNS","created_at":"2026-07-05T09:47:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:H3PRPCNSYJORLJZOYGHNUFRQVJ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T08:36:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c799a95ca056ba210851aa841411e2a8e1aa9b7c17f477f304dc7ac5f1c0990e","abstract_canon_sha256":"ddf17f687f2f11be9338db3f86301c362265eed798f9ff54da2c0d7e911b52d9"},"schema_version":"1.0"},"canonical_sha256":"3edf1789b2c25d15a72ec18eda1630aa5a8c66d76556d9492bff18c34dd828f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:45.876197Z","signature_b64":"bKm8ehUeA+uGRdAJwIUZEXZn7J1Q8xQDVWFCLa7/a2HjMFMWguB3cOV4GiaZV1ockd4FFuI/B4T8msy42F4SBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3edf1789b2c25d15a72ec18eda1630aa5a8c66d76556d9492bff18c34dd828f1","last_reissued_at":"2026-07-05T09:47:45.875785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:45.875785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08196","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":"2026-07-05T09:47:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aoZWHCt/9aN8Mef/lMLDM98XaKd5dgrnQkPDM0ojkPkU356V+5B2hE5MAsFYdP5U5JgxGxhbEBlCzz+tozVDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T17:29:44.820074Z"},"content_sha256":"d3aa05d20d97757569afcb531d1039820430c42e0959f3783239e1e13b521adf","schema_version":"1.0","event_id":"sha256:d3aa05d20d97757569afcb531d1039820430c42e0959f3783239e1e13b521adf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:H3PRPCNSYJORLJZOYGHNUFRQVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocSum: Domain-Adaptive Pre-training for Document Abstractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Antoine Doucet, Phan Phuong Mai Chau, Souhail Bakkali","submitted_at":"2024-12-11T08:36:50Z","abstract_excerpt":"Abstractive summarization has made significant strides in condensing and rephrasing large volumes of text into coherent summaries. However, summarizing administrative documents presents unique challenges due to domain-specific terminology, OCR-generated errors, and the scarcity of annotated datasets for model fine-tuning. Existing models often struggle to adapt to the intricate structure and specialized content of such documents. To address these limitations, we introduce DocSum, a domain-adaptive abstractive summarization framework tailored for administrative documents. Leveraging pre-trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08196","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/2412.08196/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":"2026-07-05T09:47:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1OzuUK0GPeRRtVAsq4B5AeVUKRJz6rpxmsagw5fKKgMOdn1zaJLHtQ6lZrbazasb2Y7K7NYPomakF3hNBG9nCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T17:29:44.820477Z"},"content_sha256":"f20f8a8388fe69be9b6fe0c6f45280f67ed43d93236872e45835721889cc4d2e","schema_version":"1.0","event_id":"sha256:f20f8a8388fe69be9b6fe0c6f45280f67ed43d93236872e45835721889cc4d2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ/bundle.json","state_url":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ/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":"2026-07-20T17:29:44Z","links":{"resolver":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ","bundle":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ/bundle.json","state":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H3PRPCNSYJORLJZOYGHNUFRQVJ","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":"ddf17f687f2f11be9338db3f86301c362265eed798f9ff54da2c0d7e911b52d9","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T08:36:50Z","title_canon_sha256":"c799a95ca056ba210851aa841411e2a8e1aa9b7c17f477f304dc7ac5f1c0990e"},"schema_version":"1.0","source":{"id":"2412.08196","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08196","created_at":"2026-07-05T09:47:45Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08196v1","created_at":"2026-07-05T09:47:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08196","created_at":"2026-07-05T09:47:45Z"},{"alias_kind":"pith_short_12","alias_value":"H3PRPCNSYJOR","created_at":"2026-07-05T09:47:45Z"},{"alias_kind":"pith_short_16","alias_value":"H3PRPCNSYJORLJZO","created_at":"2026-07-05T09:47:45Z"},{"alias_kind":"pith_short_8","alias_value":"H3PRPCNS","created_at":"2026-07-05T09:47:45Z"}],"graph_snapshots":[{"event_id":"sha256:f20f8a8388fe69be9b6fe0c6f45280f67ed43d93236872e45835721889cc4d2e","target":"graph","created_at":"2026-07-05T09:47:45Z","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/2412.08196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Abstractive summarization has made significant strides in condensing and rephrasing large volumes of text into coherent summaries. However, summarizing administrative documents presents unique challenges due to domain-specific terminology, OCR-generated errors, and the scarcity of annotated datasets for model fine-tuning. Existing models often struggle to adapt to the intricate structure and specialized content of such documents. To address these limitations, we introduce DocSum, a domain-adaptive abstractive summarization framework tailored for administrative documents. Leveraging pre-trainin","authors_text":"Antoine Doucet, Phan Phuong Mai Chau, Souhail Bakkali","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T08:36:50Z","title":"DocSum: Domain-Adaptive Pre-training for Document Abstractive Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08196","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:d3aa05d20d97757569afcb531d1039820430c42e0959f3783239e1e13b521adf","target":"record","created_at":"2026-07-05T09:47:45Z","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":"ddf17f687f2f11be9338db3f86301c362265eed798f9ff54da2c0d7e911b52d9","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T08:36:50Z","title_canon_sha256":"c799a95ca056ba210851aa841411e2a8e1aa9b7c17f477f304dc7ac5f1c0990e"},"schema_version":"1.0","source":{"id":"2412.08196","kind":"arxiv","version":1}},"canonical_sha256":"3edf1789b2c25d15a72ec18eda1630aa5a8c66d76556d9492bff18c34dd828f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3edf1789b2c25d15a72ec18eda1630aa5a8c66d76556d9492bff18c34dd828f1","first_computed_at":"2026-07-05T09:47:45.875785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:45.875785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bKm8ehUeA+uGRdAJwIUZEXZn7J1Q8xQDVWFCLa7/a2HjMFMWguB3cOV4GiaZV1ockd4FFuI/B4T8msy42F4SBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:45.876197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08196","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3aa05d20d97757569afcb531d1039820430c42e0959f3783239e1e13b521adf","sha256:f20f8a8388fe69be9b6fe0c6f45280f67ed43d93236872e45835721889cc4d2e"],"state_sha256":"352940792b6b133f7224a3ede40f75f0371efd545a3d24714e5cd8fea88389dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8LLE6hNCD0m6H4EFor8dw1XzGHHwPzbQIHLdKj26kRT3yClqk1lQN0Jc6jTDAh6oCi/IYywypO1rwbzRLSxPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T17:29:44.822781Z","bundle_sha256":"8f0286e80df30c9a139d3255ef3c48f2939c6eaba93a307df4473e361c2b8292"}}