{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AOQ52BP33AK34HBCFLGZJFJ4CR","short_pith_number":"pith:AOQ52BP3","canonical_record":{"source":{"id":"2502.07286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T06:06:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0b89db9c58f9528367f362c67e6239bf3751d0205eda736798919f847470f5b1","abstract_canon_sha256":"028d4b3456928b623e2c104932065b60724319ce9c25337e9d4c2568f46e7663"},"schema_version":"1.0"},"canonical_sha256":"03a1dd05fbd815be1c222acd94953c144023d83272a6d7d27e54a3ce9dcd9b85","source":{"kind":"arxiv","id":"2502.07286","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07286","created_at":"2026-07-05T10:12:35Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07286v1","created_at":"2026-07-05T10:12:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07286","created_at":"2026-07-05T10:12:35Z"},{"alias_kind":"pith_short_12","alias_value":"AOQ52BP33AK3","created_at":"2026-07-05T10:12:35Z"},{"alias_kind":"pith_short_16","alias_value":"AOQ52BP33AK34HBC","created_at":"2026-07-05T10:12:35Z"},{"alias_kind":"pith_short_8","alias_value":"AOQ52BP3","created_at":"2026-07-05T10:12:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AOQ52BP33AK34HBCFLGZJFJ4CR","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T06:06:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0b89db9c58f9528367f362c67e6239bf3751d0205eda736798919f847470f5b1","abstract_canon_sha256":"028d4b3456928b623e2c104932065b60724319ce9c25337e9d4c2568f46e7663"},"schema_version":"1.0"},"canonical_sha256":"03a1dd05fbd815be1c222acd94953c144023d83272a6d7d27e54a3ce9dcd9b85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:35.333284Z","signature_b64":"J2RoG+LFeYHmktDxaFSb92oicD7GGpo5dEWEA97n4Kx0A88J8dQvmeASJC9BBj8QfNLfSn8mpBJWUOVHZXB4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03a1dd05fbd815be1c222acd94953c144023d83272a6d7d27e54a3ce9dcd9b85","last_reissued_at":"2026-07-05T10:12:35.332777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:35.332777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07286","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":"2026-07-05T10:12:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lB7HG47jCdtfpvdCgDcwqMT6VZKGxap+IWjD+Ex3eNazpvhFE/Bwn1P/GL8tObJ0tZ6z2umavoEsvj1//1SmCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T03:13:03.272708Z"},"content_sha256":"27d2af72f6fc9d1d50b5f05721c6ad620a07cf97368805a96d57b1a0fc64a700","schema_version":"1.0","event_id":"sha256:27d2af72f6fc9d1d50b5f05721c6ad620a07cf97368805a96d57b1a0fc64a700"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AOQ52BP33AK34HBCFLGZJFJ4CR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Small Language Model Makes an Effective Long Text Extractor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fanjin Zhang, Jie Tang, Yelin Chen","submitted_at":"2025-02-11T06:06:25Z","abstract_excerpt":"Named Entity Recognition (NER) is a fundamental problem in natural language processing (NLP). However, the task of extracting longer entity spans (e.g., awards) from extended texts (e.g., homepages) is barely explored. Current NER methods predominantly fall into two categories: span-based methods and generation-based methods. Span-based methods require the enumeration of all possible token-pair spans, followed by classification on each span, resulting in substantial redundant computations and excessive GPU memory usage. In contrast, generation-based methods involve prompting or fine-tuning lar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07286","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/2502.07286/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":"2026-07-05T10:12:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"thN9de87aBF5uvUjlfup4M5boIj72/DpgX3YQL5IdiEKJ2SMO62aiEMexpRs3T4HzABzwlPWr8bZbGrWxWgwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T03:13:03.273224Z"},"content_sha256":"9fcb770d6d273454184aaecfe1a572790179721eb8fb88d47560022ffd7d1f77","schema_version":"1.0","event_id":"sha256:9fcb770d6d273454184aaecfe1a572790179721eb8fb88d47560022ffd7d1f77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AOQ52BP33AK34HBCFLGZJFJ4CR/bundle.json","state_url":"https://pith.science/pith/AOQ52BP33AK34HBCFLGZJFJ4CR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AOQ52BP33AK34HBCFLGZJFJ4CR/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":"2026-08-20T03:13:03Z","links":{"resolver":"https://pith.science/pith/AOQ52BP33AK34HBCFLGZJFJ4CR","bundle":"https://pith.science/pith/AOQ52BP33AK34HBCFLGZJFJ4CR/bundle.json","state":"https://pith.science/pith/AOQ52BP33AK34HBCFLGZJFJ4CR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AOQ52BP33AK34HBCFLGZJFJ4CR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AOQ52BP33AK34HBCFLGZJFJ4CR","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":"028d4b3456928b623e2c104932065b60724319ce9c25337e9d4c2568f46e7663","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T06:06:25Z","title_canon_sha256":"0b89db9c58f9528367f362c67e6239bf3751d0205eda736798919f847470f5b1"},"schema_version":"1.0","source":{"id":"2502.07286","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07286","created_at":"2026-07-05T10:12:35Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07286v1","created_at":"2026-07-05T10:12:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07286","created_at":"2026-07-05T10:12:35Z"},{"alias_kind":"pith_short_12","alias_value":"AOQ52BP33AK3","created_at":"2026-07-05T10:12:35Z"},{"alias_kind":"pith_short_16","alias_value":"AOQ52BP33AK34HBC","created_at":"2026-07-05T10:12:35Z"},{"alias_kind":"pith_short_8","alias_value":"AOQ52BP3","created_at":"2026-07-05T10:12:35Z"}],"graph_snapshots":[{"event_id":"sha256:9fcb770d6d273454184aaecfe1a572790179721eb8fb88d47560022ffd7d1f77","target":"graph","created_at":"2026-07-05T10:12:35Z","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/2502.07286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Named Entity Recognition (NER) is a fundamental problem in natural language processing (NLP). However, the task of extracting longer entity spans (e.g., awards) from extended texts (e.g., homepages) is barely explored. Current NER methods predominantly fall into two categories: span-based methods and generation-based methods. Span-based methods require the enumeration of all possible token-pair spans, followed by classification on each span, resulting in substantial redundant computations and excessive GPU memory usage. In contrast, generation-based methods involve prompting or fine-tuning lar","authors_text":"Fanjin Zhang, Jie Tang, Yelin Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T06:06:25Z","title":"Small Language Model Makes an Effective Long Text Extractor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07286","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":"sha256:27d2af72f6fc9d1d50b5f05721c6ad620a07cf97368805a96d57b1a0fc64a700","target":"record","created_at":"2026-07-05T10:12:35Z","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":"028d4b3456928b623e2c104932065b60724319ce9c25337e9d4c2568f46e7663","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T06:06:25Z","title_canon_sha256":"0b89db9c58f9528367f362c67e6239bf3751d0205eda736798919f847470f5b1"},"schema_version":"1.0","source":{"id":"2502.07286","kind":"arxiv","version":1}},"canonical_sha256":"03a1dd05fbd815be1c222acd94953c144023d83272a6d7d27e54a3ce9dcd9b85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03a1dd05fbd815be1c222acd94953c144023d83272a6d7d27e54a3ce9dcd9b85","first_computed_at":"2026-07-05T10:12:35.332777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:35.332777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J2RoG+LFeYHmktDxaFSb92oicD7GGpo5dEWEA97n4Kx0A88J8dQvmeASJC9BBj8QfNLfSn8mpBJWUOVHZXB4BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:35.333284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07286","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27d2af72f6fc9d1d50b5f05721c6ad620a07cf97368805a96d57b1a0fc64a700","sha256:9fcb770d6d273454184aaecfe1a572790179721eb8fb88d47560022ffd7d1f77"],"state_sha256":"df3e9fef1e1a92c771509c6a30ecb97d03b5f840cbad35f6321f4d30b3cba455"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QkzsSxcBHjhwYmmS86wyYKu0JdcJzYZufkkfkqm5ki0CuqLzGMeBPUZXAehqMDyab3+Ltgpe7As00oz3Qpx+CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T03:13:03.282022Z","bundle_sha256":"515ed25509eba8c474a416f4616aef187f35556251f4d10052b2eae597de82c4"}}