{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KUIF43SIEKC46TR3ITLWQM6KKA","short_pith_number":"pith:KUIF43SI","canonical_record":{"source":{"id":"2504.05358","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-04-07T09:34:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"195f2c0ca66b713a281fd1192435ad07dc39fd41515e85fd81d06a9caac6843a","abstract_canon_sha256":"b83778f0e83123f4184061f4ac7817c966caf539f8f35989d59eeb7b17e4fa82"},"schema_version":"1.0"},"canonical_sha256":"55105e6e482285cf4e3b44d76833ca5007c689dac67944d878a1d586f7fbc60f","source":{"kind":"arxiv","id":"2504.05358","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05358","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05358v1","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05358","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"pith_short_12","alias_value":"KUIF43SIEKC4","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"pith_short_16","alias_value":"KUIF43SIEKC46TR3","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"pith_short_8","alias_value":"KUIF43SI","created_at":"2026-07-05T10:45:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KUIF43SIEKC46TR3ITLWQM6KKA","target":"record","payload":{"canonical_record":{"source":{"id":"2504.05358","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-04-07T09:34:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"195f2c0ca66b713a281fd1192435ad07dc39fd41515e85fd81d06a9caac6843a","abstract_canon_sha256":"b83778f0e83123f4184061f4ac7817c966caf539f8f35989d59eeb7b17e4fa82"},"schema_version":"1.0"},"canonical_sha256":"55105e6e482285cf4e3b44d76833ca5007c689dac67944d878a1d586f7fbc60f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:41.036177Z","signature_b64":"uImUzBfUjan8RVKn/JCg2W1z0Hqyqp/fqYlg+RdSz0f5agpI6Pcwhdlt58eIbgLPY2aKiA1jD79N31HnDelxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55105e6e482285cf4e3b44d76833ca5007c689dac67944d878a1d586f7fbc60f","last_reissued_at":"2026-07-05T10:45:41.035654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:41.035654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.05358","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":"2026-07-05T10:45:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0nG5AtxI/M97GEyphFnz3j+mGw7UbK9hoeql0SaB/3KniyFYUhDfS5G4fTgKI7fWYhH/vqdHcYvodR1rhp/BBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:37:38.612762Z"},"content_sha256":"4b010734acd864fdb389f8fa5add19a3113073f7a24e6151d64d16411ae55a21","schema_version":"1.0","event_id":"sha256:4b010734acd864fdb389f8fa5add19a3113073f7a24e6151d64d16411ae55a21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KUIF43SIEKC46TR3ITLWQM6KKA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Haotian Shangguan, Mao Mao, Shuo Li, Xi Chen","submitted_at":"2025-04-07T09:34:14Z","abstract_excerpt":"The use of AI in legal analysis and prediction (LegalAI) has gained widespread attention, with past research focusing on retrieval-based methods and fine-tuning large models. However, these approaches often require large datasets and underutilize the capabilities of modern large language models (LLMs). In this paper, inspired by the debate phase of real courtroom trials, we propose a novel legal judgment prediction model based on the Debate-Feedback architecture, which integrates LLM multi-agent debate and reliability evaluation models. Unlike traditional methods, our model achieves significan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05358","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/2504.05358/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":"2026-07-05T10:45:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lOwFajzKIPgnhddHMihvtjuZ6Tm+AwwVe3Oy1CdPImqYK2ICNJCVZ9hWmrT2Ls67pn4YltnXG9fG7sztkzwNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:37:38.613292Z"},"content_sha256":"727ad9ba08b3c953288129160c898866128f601e8a7c2d1b5ab6f2195188dd08","schema_version":"1.0","event_id":"sha256:727ad9ba08b3c953288129160c898866128f601e8a7c2d1b5ab6f2195188dd08"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KUIF43SIEKC46TR3ITLWQM6KKA/bundle.json","state_url":"https://pith.science/pith/KUIF43SIEKC46TR3ITLWQM6KKA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KUIF43SIEKC46TR3ITLWQM6KKA/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":"2026-08-09T18:37:38Z","links":{"resolver":"https://pith.science/pith/KUIF43SIEKC46TR3ITLWQM6KKA","bundle":"https://pith.science/pith/KUIF43SIEKC46TR3ITLWQM6KKA/bundle.json","state":"https://pith.science/pith/KUIF43SIEKC46TR3ITLWQM6KKA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KUIF43SIEKC46TR3ITLWQM6KKA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KUIF43SIEKC46TR3ITLWQM6KKA","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":"b83778f0e83123f4184061f4ac7817c966caf539f8f35989d59eeb7b17e4fa82","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-04-07T09:34:14Z","title_canon_sha256":"195f2c0ca66b713a281fd1192435ad07dc39fd41515e85fd81d06a9caac6843a"},"schema_version":"1.0","source":{"id":"2504.05358","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05358","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05358v1","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05358","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"pith_short_12","alias_value":"KUIF43SIEKC4","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"pith_short_16","alias_value":"KUIF43SIEKC46TR3","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"pith_short_8","alias_value":"KUIF43SI","created_at":"2026-07-05T10:45:41Z"}],"graph_snapshots":[{"event_id":"sha256:727ad9ba08b3c953288129160c898866128f601e8a7c2d1b5ab6f2195188dd08","target":"graph","created_at":"2026-07-05T10:45:41Z","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/2504.05358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of AI in legal analysis and prediction (LegalAI) has gained widespread attention, with past research focusing on retrieval-based methods and fine-tuning large models. However, these approaches often require large datasets and underutilize the capabilities of modern large language models (LLMs). In this paper, inspired by the debate phase of real courtroom trials, we propose a novel legal judgment prediction model based on the Debate-Feedback architecture, which integrates LLM multi-agent debate and reliability evaluation models. Unlike traditional methods, our model achieves significan","authors_text":"Haotian Shangguan, Mao Mao, Shuo Li, Xi Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-04-07T09:34:14Z","title":"Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05358","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":"sha256:4b010734acd864fdb389f8fa5add19a3113073f7a24e6151d64d16411ae55a21","target":"record","created_at":"2026-07-05T10:45:41Z","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":"b83778f0e83123f4184061f4ac7817c966caf539f8f35989d59eeb7b17e4fa82","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-04-07T09:34:14Z","title_canon_sha256":"195f2c0ca66b713a281fd1192435ad07dc39fd41515e85fd81d06a9caac6843a"},"schema_version":"1.0","source":{"id":"2504.05358","kind":"arxiv","version":1}},"canonical_sha256":"55105e6e482285cf4e3b44d76833ca5007c689dac67944d878a1d586f7fbc60f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55105e6e482285cf4e3b44d76833ca5007c689dac67944d878a1d586f7fbc60f","first_computed_at":"2026-07-05T10:45:41.035654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:41.035654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uImUzBfUjan8RVKn/JCg2W1z0Hqyqp/fqYlg+RdSz0f5agpI6Pcwhdlt58eIbgLPY2aKiA1jD79N31HnDelxCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:41.036177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.05358","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b010734acd864fdb389f8fa5add19a3113073f7a24e6151d64d16411ae55a21","sha256:727ad9ba08b3c953288129160c898866128f601e8a7c2d1b5ab6f2195188dd08"],"state_sha256":"deb8dac645f110b0e054fe81d604da1086ef54bc477f1cf049798d5630194da1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/YJmGJTLU5WFItUIe+eHDgMVWFlEDWhRJOhNMmXHAnmbw6E90TU4OHvoMZ5L+I6Iv5U/WTOA2f4gud4XVQkrAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:37:38.617301Z","bundle_sha256":"faf054925073fb0694f004c6a3eb52564f80e9912a973cb8339ba03fbe566a0e"}}