{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VZKEU67W7JB7FGHB5F44S5DL4B","short_pith_number":"pith:VZKEU67W","canonical_record":{"source":{"id":"2509.07512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-09T08:47:13Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"e785d2400f593a3b0ffa1c39947a7f9e7dea6bd17e236d109721862fce9935d1","abstract_canon_sha256":"ef774d567a29b06f436d9fd2680e017334585af5aa594080d81c4192d11c37da"},"schema_version":"1.0"},"canonical_sha256":"ae544a7bf6fa43f298e1e979c9746be06f92abd941993487c5ee24ae8898a738","source":{"kind":"arxiv","id":"2509.07512","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.07512","created_at":"2026-07-05T12:07:22Z"},{"alias_kind":"arxiv_version","alias_value":"2509.07512v1","created_at":"2026-07-05T12:07:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07512","created_at":"2026-07-05T12:07:22Z"},{"alias_kind":"pith_short_12","alias_value":"VZKEU67W7JB7","created_at":"2026-07-05T12:07:22Z"},{"alias_kind":"pith_short_16","alias_value":"VZKEU67W7JB7FGHB","created_at":"2026-07-05T12:07:22Z"},{"alias_kind":"pith_short_8","alias_value":"VZKEU67W","created_at":"2026-07-05T12:07:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VZKEU67W7JB7FGHB5F44S5DL4B","target":"record","payload":{"canonical_record":{"source":{"id":"2509.07512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-09T08:47:13Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"e785d2400f593a3b0ffa1c39947a7f9e7dea6bd17e236d109721862fce9935d1","abstract_canon_sha256":"ef774d567a29b06f436d9fd2680e017334585af5aa594080d81c4192d11c37da"},"schema_version":"1.0"},"canonical_sha256":"ae544a7bf6fa43f298e1e979c9746be06f92abd941993487c5ee24ae8898a738","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:22.899594Z","signature_b64":"3P89EwliA8K3cHpD5PW9ko63mTKaFSfyGLrrBYQEiIleeQaXP9kzNomRqRub1ScLjdBpKbw1Zp+cZn+RpPXhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae544a7bf6fa43f298e1e979c9746be06f92abd941993487c5ee24ae8898a738","last_reissued_at":"2026-07-05T12:07:22.899009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:22.899009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.07512","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":"2026-07-05T12:07:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gBhmIx3pV0lqXK5ee4/gthkYKxA85pjEues0nNy5pTQ5R2n/lV9GEyAS9p8bRxclrXEptD9MLDlMNMkHjDYNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:36:17.113505Z"},"content_sha256":"37ade7c0a3661e74e89c7bc0da92295ac5d214f736a88fd270c1d39507e56c8a","schema_version":"1.0","event_id":"sha256:37ade7c0a3661e74e89c7bc0da92295ac5d214f736a88fd270c1d39507e56c8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VZKEU67W7JB7FGHB5F44S5DL4B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ALLabel: Three-stage Active Learning for LLM-based Entity Recognition using Demonstration Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Lei Shi, Qiji Zhou, Weize Wu, Yue Zhang, Zihan Chen","submitted_at":"2025-09-09T08:47:13Z","abstract_excerpt":"Many contemporary data-driven research efforts in the natural sciences, such as chemistry and materials science, require large-scale, high-performance entity recognition from scientific datasets. Large language models (LLMs) have increasingly been adopted to solve the entity recognition task, with the same trend being observed on all-spectrum NLP tasks. The prevailing entity recognition LLMs rely on fine-tuned technology, yet the fine-tuning process often incurs significant cost. To achieve a best performance-cost trade-off, we propose ALLabel, a three-stage framework designed to select the mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07512","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/2509.07512/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":"2026-07-05T12:07:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iJKusdShnMjcbL2InPZdUIAeH9/SI7kqbSf/6BFFkvZr5dlg7l1fJaL6JoJm56+Gs8WZEPxwgMZPg2K374IbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:36:17.114703Z"},"content_sha256":"3e4cb538e0c0a26d5bbf66c8dcdbd08a214ce479b879f8b22a308efe8bf5b309","schema_version":"1.0","event_id":"sha256:3e4cb538e0c0a26d5bbf66c8dcdbd08a214ce479b879f8b22a308efe8bf5b309"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B/bundle.json","state_url":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VZKEU67W7JB7FGHB5F44S5DL4B/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":"2026-08-05T08:36:17Z","links":{"resolver":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B","bundle":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B/bundle.json","state":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VZKEU67W7JB7FGHB5F44S5DL4B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VZKEU67W7JB7FGHB5F44S5DL4B","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":"ef774d567a29b06f436d9fd2680e017334585af5aa594080d81c4192d11c37da","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-09T08:47:13Z","title_canon_sha256":"e785d2400f593a3b0ffa1c39947a7f9e7dea6bd17e236d109721862fce9935d1"},"schema_version":"1.0","source":{"id":"2509.07512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.07512","created_at":"2026-07-05T12:07:22Z"},{"alias_kind":"arxiv_version","alias_value":"2509.07512v1","created_at":"2026-07-05T12:07:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07512","created_at":"2026-07-05T12:07:22Z"},{"alias_kind":"pith_short_12","alias_value":"VZKEU67W7JB7","created_at":"2026-07-05T12:07:22Z"},{"alias_kind":"pith_short_16","alias_value":"VZKEU67W7JB7FGHB","created_at":"2026-07-05T12:07:22Z"},{"alias_kind":"pith_short_8","alias_value":"VZKEU67W","created_at":"2026-07-05T12:07:22Z"}],"graph_snapshots":[{"event_id":"sha256:3e4cb538e0c0a26d5bbf66c8dcdbd08a214ce479b879f8b22a308efe8bf5b309","target":"graph","created_at":"2026-07-05T12:07:22Z","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/2509.07512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many contemporary data-driven research efforts in the natural sciences, such as chemistry and materials science, require large-scale, high-performance entity recognition from scientific datasets. Large language models (LLMs) have increasingly been adopted to solve the entity recognition task, with the same trend being observed on all-spectrum NLP tasks. The prevailing entity recognition LLMs rely on fine-tuned technology, yet the fine-tuning process often incurs significant cost. To achieve a best performance-cost trade-off, we propose ALLabel, a three-stage framework designed to select the mo","authors_text":"Lei Shi, Qiji Zhou, Weize Wu, Yue Zhang, Zihan Chen","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-09T08:47:13Z","title":"ALLabel: Three-stage Active Learning for LLM-based Entity Recognition using Demonstration Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07512","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":"sha256:37ade7c0a3661e74e89c7bc0da92295ac5d214f736a88fd270c1d39507e56c8a","target":"record","created_at":"2026-07-05T12:07:22Z","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":"ef774d567a29b06f436d9fd2680e017334585af5aa594080d81c4192d11c37da","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-09T08:47:13Z","title_canon_sha256":"e785d2400f593a3b0ffa1c39947a7f9e7dea6bd17e236d109721862fce9935d1"},"schema_version":"1.0","source":{"id":"2509.07512","kind":"arxiv","version":1}},"canonical_sha256":"ae544a7bf6fa43f298e1e979c9746be06f92abd941993487c5ee24ae8898a738","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae544a7bf6fa43f298e1e979c9746be06f92abd941993487c5ee24ae8898a738","first_computed_at":"2026-07-05T12:07:22.899009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:22.899009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3P89EwliA8K3cHpD5PW9ko63mTKaFSfyGLrrBYQEiIleeQaXP9kzNomRqRub1ScLjdBpKbw1Zp+cZn+RpPXhDA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:22.899594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.07512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37ade7c0a3661e74e89c7bc0da92295ac5d214f736a88fd270c1d39507e56c8a","sha256:3e4cb538e0c0a26d5bbf66c8dcdbd08a214ce479b879f8b22a308efe8bf5b309"],"state_sha256":"d53f4fc58c6260f33d296aa2a697dab1c2548b433e8bc60f96d54cd20bb9aa5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9/aR8pYg5hYgi0P+Z78MH5mBP16P8Kb/HoJqOVcxrsOjtLHPwssUQkoQTh2zF+2T8n1liY9nrtkM9WBcTcABCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:36:17.162475Z","bundle_sha256":"c77391ed3165a6f9af362bf56f7fe0077d18db06353543dbfd0ed637bf099804"}}