{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:A4N5NIZZ4UUWVUF6BQDLC643QZ","short_pith_number":"pith:A4N5NIZZ","canonical_record":{"source":{"id":"2404.03862","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T02:27:09Z","cross_cats_sorted":[],"title_canon_sha256":"da9b609cab17e332416a3d44f8a92b321d3e5bcd2d63c30262e9ad8807898bc0","abstract_canon_sha256":"9bb9b02411253850cf033ba4787d92dd6d6abafc1f00e33125471fce1c951b08"},"schema_version":"1.0"},"canonical_sha256":"071bd6a339e5296ad0be0c06b17b9b86673908b18712c9138e220b3df8a6f430","source":{"kind":"arxiv","id":"2404.03862","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03862","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03862v4","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03862","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"A4N5NIZZ4UUW","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"A4N5NIZZ4UUWVUF6","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"A4N5NIZZ","created_at":"2026-07-05T10:18:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:A4N5NIZZ4UUWVUF6BQDLC643QZ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.03862","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T02:27:09Z","cross_cats_sorted":[],"title_canon_sha256":"da9b609cab17e332416a3d44f8a92b321d3e5bcd2d63c30262e9ad8807898bc0","abstract_canon_sha256":"9bb9b02411253850cf033ba4787d92dd6d6abafc1f00e33125471fce1c951b08"},"schema_version":"1.0"},"canonical_sha256":"071bd6a339e5296ad0be0c06b17b9b86673908b18712c9138e220b3df8a6f430","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:08.247521Z","signature_b64":"uxoERevztoCACjghB35qir0Doel/k1e2A0Dworj7Sd911VC3AbWVMjP9CT3abYO6LyHM3GY6G1n2thynf/oDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"071bd6a339e5296ad0be0c06b17b9b86673908b18712c9138e220b3df8a6f430","last_reissued_at":"2026-07-05T10:18:08.247051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:08.247051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.03862","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qAAx2mk+FbUeU+SyKupFyvYZAZINriVFO5pLGGQodUDtJqqymJhAqQJcbPPCSmDqCO2lXawQPdL0xXjHMsbSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T11:54:03.752648Z"},"content_sha256":"5a4d0df5f2d7a3ac8b42de19665af6b13b16c163a2c8c5a264c663d87e714ef6","schema_version":"1.0","event_id":"sha256:5a4d0df5f2d7a3ac8b42de19665af6b13b16c163a2c8c5a264c663d87e714ef6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:A4N5NIZZ4UUWVUF6BQDLC643QZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Daniel Khashabi, Jingyu Zhang, Marc Marone, Tianjian Li","submitted_at":"2024-04-05T02:27:09Z","abstract_excerpt":"To trust the fluent generations of large language models (LLMs), humans must be able to verify their correctness against trusted, external sources. Recent efforts, such as providing citations via retrieved documents or post-hoc provenance, enhance verifiability but provide no guarantees on their correctness. To address these limitations, we tackle the verifiability goal with a different philosophy: trivializing the verification process by developing models that quote verbatim statements from trusted sources in their pre-training data. We propose Quote-Tuning, which demonstrates the feasibility"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03862","kind":"arxiv","version":4},"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/2404.03862/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":"2026-07-05T10:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YR/SdGJdP8qIAn00v9VfYs9Jbvv6UKVfr9QLkj5K0naAyyuq7obUK585Km8oBs7ZCdjt4rnRREgJP+7q5lxmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T11:54:03.753155Z"},"content_sha256":"313909adf34d4503f0a17e9133768739ff526d56ba074a06a900cbbfd7511ed0","schema_version":"1.0","event_id":"sha256:313909adf34d4503f0a17e9133768739ff526d56ba074a06a900cbbfd7511ed0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A4N5NIZZ4UUWVUF6BQDLC643QZ/bundle.json","state_url":"https://pith.science/pith/A4N5NIZZ4UUWVUF6BQDLC643QZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A4N5NIZZ4UUWVUF6BQDLC643QZ/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":"2026-08-20T11:54:03Z","links":{"resolver":"https://pith.science/pith/A4N5NIZZ4UUWVUF6BQDLC643QZ","bundle":"https://pith.science/pith/A4N5NIZZ4UUWVUF6BQDLC643QZ/bundle.json","state":"https://pith.science/pith/A4N5NIZZ4UUWVUF6BQDLC643QZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A4N5NIZZ4UUWVUF6BQDLC643QZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A4N5NIZZ4UUWVUF6BQDLC643QZ","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":"9bb9b02411253850cf033ba4787d92dd6d6abafc1f00e33125471fce1c951b08","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T02:27:09Z","title_canon_sha256":"da9b609cab17e332416a3d44f8a92b321d3e5bcd2d63c30262e9ad8807898bc0"},"schema_version":"1.0","source":{"id":"2404.03862","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03862","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03862v4","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03862","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"A4N5NIZZ4UUW","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"A4N5NIZZ4UUWVUF6","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"A4N5NIZZ","created_at":"2026-07-05T10:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:313909adf34d4503f0a17e9133768739ff526d56ba074a06a900cbbfd7511ed0","target":"graph","created_at":"2026-07-05T10:18:08Z","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/2404.03862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To trust the fluent generations of large language models (LLMs), humans must be able to verify their correctness against trusted, external sources. Recent efforts, such as providing citations via retrieved documents or post-hoc provenance, enhance verifiability but provide no guarantees on their correctness. To address these limitations, we tackle the verifiability goal with a different philosophy: trivializing the verification process by developing models that quote verbatim statements from trusted sources in their pre-training data. We propose Quote-Tuning, which demonstrates the feasibility","authors_text":"Benjamin Van Durme, Daniel Khashabi, Jingyu Zhang, Marc Marone, Tianjian Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T02:27:09Z","title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03862","kind":"arxiv","version":4},"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":"sha256:5a4d0df5f2d7a3ac8b42de19665af6b13b16c163a2c8c5a264c663d87e714ef6","target":"record","created_at":"2026-07-05T10:18:08Z","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":"9bb9b02411253850cf033ba4787d92dd6d6abafc1f00e33125471fce1c951b08","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T02:27:09Z","title_canon_sha256":"da9b609cab17e332416a3d44f8a92b321d3e5bcd2d63c30262e9ad8807898bc0"},"schema_version":"1.0","source":{"id":"2404.03862","kind":"arxiv","version":4}},"canonical_sha256":"071bd6a339e5296ad0be0c06b17b9b86673908b18712c9138e220b3df8a6f430","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"071bd6a339e5296ad0be0c06b17b9b86673908b18712c9138e220b3df8a6f430","first_computed_at":"2026-07-05T10:18:08.247051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:08.247051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uxoERevztoCACjghB35qir0Doel/k1e2A0Dworj7Sd911VC3AbWVMjP9CT3abYO6LyHM3GY6G1n2thynf/oDBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:08.247521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.03862","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a4d0df5f2d7a3ac8b42de19665af6b13b16c163a2c8c5a264c663d87e714ef6","sha256:313909adf34d4503f0a17e9133768739ff526d56ba074a06a900cbbfd7511ed0"],"state_sha256":"38288c203b8b3e704a1d32d15753ad81fb57741e480a245f7f133c2a4c2f6397"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Fsngzsfem9Ct/R3j49T0LCnPXn4ED9b3kmtTTv75v+Bhffm4BL1Nf0QxsnMxvVZZzar2+GQ6aMtlWEVd50bAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T11:54:03.758434Z","bundle_sha256":"97699459b15c2efbf4d0022b40f7bb2b7fbd10f8c1816f0471be09d43be206d8"}}