{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5WWTDNK72RYSVRRQ5U4QLWVRAG","short_pith_number":"pith:5WWTDNK7","canonical_record":{"source":{"id":"2405.12363","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T20:27:00Z","cross_cats_sorted":[],"title_canon_sha256":"722bacb50f0885181669458dcecd407b7cd7d18990720182c6366aa14ece9972","abstract_canon_sha256":"fd3830f2094f97ceafcf8bf5d21675cc2a349590abf9bff6d2020c706f9c1e05"},"schema_version":"1.0"},"canonical_sha256":"edad31b55fd4712ac630ed3905dab10188c2e1e9f828a4f45a77a9dbfcbdd1b4","source":{"kind":"arxiv","id":"2405.12363","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12363","created_at":"2026-07-05T09:01:00Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12363v2","created_at":"2026-07-05T09:01:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12363","created_at":"2026-07-05T09:01:00Z"},{"alias_kind":"pith_short_12","alias_value":"5WWTDNK72RYS","created_at":"2026-07-05T09:01:00Z"},{"alias_kind":"pith_short_16","alias_value":"5WWTDNK72RYSVRRQ","created_at":"2026-07-05T09:01:00Z"},{"alias_kind":"pith_short_8","alias_value":"5WWTDNK7","created_at":"2026-07-05T09:01:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5WWTDNK72RYSVRRQ5U4QLWVRAG","target":"record","payload":{"canonical_record":{"source":{"id":"2405.12363","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T20:27:00Z","cross_cats_sorted":[],"title_canon_sha256":"722bacb50f0885181669458dcecd407b7cd7d18990720182c6366aa14ece9972","abstract_canon_sha256":"fd3830f2094f97ceafcf8bf5d21675cc2a349590abf9bff6d2020c706f9c1e05"},"schema_version":"1.0"},"canonical_sha256":"edad31b55fd4712ac630ed3905dab10188c2e1e9f828a4f45a77a9dbfcbdd1b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:00.352861Z","signature_b64":"VxofetNTz9V0AKubTAIU4N8hn8+1/ppQpGiMmFHw/ZdPXvN2R5vQ7RFiXIGRDt1q//glAB5o+J5KL/UxTEDXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edad31b55fd4712ac630ed3905dab10188c2e1e9f828a4f45a77a9dbfcbdd1b4","last_reissued_at":"2026-07-05T09:01:00.352431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:00.352431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.12363","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:01:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UkF07NYfMF6z71atiqfKSZfeXqqDjnzNJCmbn3XPxZFGHVi48BnQcv/hcm148KzkbFVLBVQbCVbWDbyaB3OiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:52:41.913557Z"},"content_sha256":"218ad248bd6e9e299798e203c6a12f43445242506def2035e648e8246b983ecc","schema_version":"1.0","event_id":"sha256:218ad248bd6e9e299798e203c6a12f43445242506def2035e648e8246b983ecc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5WWTDNK72RYSVRRQ5U4QLWVRAG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Question-Based Retrieval using Atomic Units for Enterprise RAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mark Gales, Vatsal Raina","submitted_at":"2024-05-20T20:27:00Z","abstract_excerpt":"Enterprise retrieval augmented generation (RAG) offers a highly flexible framework for combining powerful large language models (LLMs) with internal, possibly temporally changing, documents. In RAG, documents are first chunked. Relevant chunks are then retrieved for a user query, which are passed as context to a synthesizer LLM to generate the query response. However, the retrieval step can limit performance, as incorrect chunks can lead the synthesizer LLM to generate a false response. This work applies a zero-shot adaptation of standard dense retrieval steps for more accurate chunk recall. S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12363","kind":"arxiv","version":2},"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/2405.12363/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":"2026-07-05T09:01:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GHEuQQBA0amtKvn16bY4dFji06ruRaNLN3E4oLPP9fg3GGqnTpY0c0cQxPJGwu1mvMAftKHoC7tQEJ/OLMScCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:52:41.914429Z"},"content_sha256":"75b051bbc5503fc86f867f89faff1075d623eb8ceefbeb80f812d8cb7082a876","schema_version":"1.0","event_id":"sha256:75b051bbc5503fc86f867f89faff1075d623eb8ceefbeb80f812d8cb7082a876"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WWTDNK72RYSVRRQ5U4QLWVRAG/bundle.json","state_url":"https://pith.science/pith/5WWTDNK72RYSVRRQ5U4QLWVRAG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WWTDNK72RYSVRRQ5U4QLWVRAG/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":"2026-08-08T23:52:41Z","links":{"resolver":"https://pith.science/pith/5WWTDNK72RYSVRRQ5U4QLWVRAG","bundle":"https://pith.science/pith/5WWTDNK72RYSVRRQ5U4QLWVRAG/bundle.json","state":"https://pith.science/pith/5WWTDNK72RYSVRRQ5U4QLWVRAG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WWTDNK72RYSVRRQ5U4QLWVRAG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5WWTDNK72RYSVRRQ5U4QLWVRAG","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":"fd3830f2094f97ceafcf8bf5d21675cc2a349590abf9bff6d2020c706f9c1e05","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T20:27:00Z","title_canon_sha256":"722bacb50f0885181669458dcecd407b7cd7d18990720182c6366aa14ece9972"},"schema_version":"1.0","source":{"id":"2405.12363","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12363","created_at":"2026-07-05T09:01:00Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12363v2","created_at":"2026-07-05T09:01:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12363","created_at":"2026-07-05T09:01:00Z"},{"alias_kind":"pith_short_12","alias_value":"5WWTDNK72RYS","created_at":"2026-07-05T09:01:00Z"},{"alias_kind":"pith_short_16","alias_value":"5WWTDNK72RYSVRRQ","created_at":"2026-07-05T09:01:00Z"},{"alias_kind":"pith_short_8","alias_value":"5WWTDNK7","created_at":"2026-07-05T09:01:00Z"}],"graph_snapshots":[{"event_id":"sha256:75b051bbc5503fc86f867f89faff1075d623eb8ceefbeb80f812d8cb7082a876","target":"graph","created_at":"2026-07-05T09:01:00Z","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/2405.12363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Enterprise retrieval augmented generation (RAG) offers a highly flexible framework for combining powerful large language models (LLMs) with internal, possibly temporally changing, documents. In RAG, documents are first chunked. Relevant chunks are then retrieved for a user query, which are passed as context to a synthesizer LLM to generate the query response. However, the retrieval step can limit performance, as incorrect chunks can lead the synthesizer LLM to generate a false response. This work applies a zero-shot adaptation of standard dense retrieval steps for more accurate chunk recall. S","authors_text":"Mark Gales, Vatsal Raina","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T20:27:00Z","title":"Question-Based Retrieval using Atomic Units for Enterprise RAG"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12363","kind":"arxiv","version":2},"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":"sha256:218ad248bd6e9e299798e203c6a12f43445242506def2035e648e8246b983ecc","target":"record","created_at":"2026-07-05T09:01:00Z","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":"fd3830f2094f97ceafcf8bf5d21675cc2a349590abf9bff6d2020c706f9c1e05","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T20:27:00Z","title_canon_sha256":"722bacb50f0885181669458dcecd407b7cd7d18990720182c6366aa14ece9972"},"schema_version":"1.0","source":{"id":"2405.12363","kind":"arxiv","version":2}},"canonical_sha256":"edad31b55fd4712ac630ed3905dab10188c2e1e9f828a4f45a77a9dbfcbdd1b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edad31b55fd4712ac630ed3905dab10188c2e1e9f828a4f45a77a9dbfcbdd1b4","first_computed_at":"2026-07-05T09:01:00.352431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:00.352431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VxofetNTz9V0AKubTAIU4N8hn8+1/ppQpGiMmFHw/ZdPXvN2R5vQ7RFiXIGRDt1q//glAB5o+J5KL/UxTEDXBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:00.352861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.12363","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:218ad248bd6e9e299798e203c6a12f43445242506def2035e648e8246b983ecc","sha256:75b051bbc5503fc86f867f89faff1075d623eb8ceefbeb80f812d8cb7082a876"],"state_sha256":"d95ff5bf545b409bc30630135d377913157d1742b8410f05ce7fa6b272c894f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HbFH7tY2mk+nlrWhk4LHqVjNGV9N7Ogks4KS8pQ6hXmrVHmiILIHyK+f7tmdPJdKBK9WDewYcrEfiR0mg/EZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:52:41.919346Z","bundle_sha256":"dec10c77478ffc2e741827594d1d25d87fb19bbe997fa5f7334278e9bde7e5b5"}}