{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JMSHY6UCCXYQN4OMRDIPF5F47A","short_pith_number":"pith:JMSHY6UC","canonical_record":{"source":{"id":"2608.06305","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T17:23:13Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"cbb56330904cc1c244636fd8c9949464a14b5ff73e41a601abb07c752802b146","abstract_canon_sha256":"c75f012c9e7484d5df46c6d6a560deedb80d3a875619a6d03267a1fa97a32ecb"},"schema_version":"1.0"},"canonical_sha256":"4b247c7a8215f106f1cc88d0f2f4bcf83ffffbef00c724ec94f1c9bee5f52a73","source":{"kind":"arxiv","id":"2608.06305","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06305","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06305v1","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06305","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"pith_short_12","alias_value":"JMSHY6UCCXYQ","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"pith_short_16","alias_value":"JMSHY6UCCXYQN4OM","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"pith_short_8","alias_value":"JMSHY6UC","created_at":"2026-08-07T01:41:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JMSHY6UCCXYQN4OMRDIPF5F47A","target":"record","payload":{"canonical_record":{"source":{"id":"2608.06305","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T17:23:13Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"cbb56330904cc1c244636fd8c9949464a14b5ff73e41a601abb07c752802b146","abstract_canon_sha256":"c75f012c9e7484d5df46c6d6a560deedb80d3a875619a6d03267a1fa97a32ecb"},"schema_version":"1.0"},"canonical_sha256":"4b247c7a8215f106f1cc88d0f2f4bcf83ffffbef00c724ec94f1c9bee5f52a73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T01:41:19.969898Z","signature_b64":"kLZf9EAlI4Yxt81k30QNo42LaLeo/YFSAu0o6ArkshUPpGRpd0mwQAcnjxnA8CPABNiPL6wS6gFTkEMHd2FLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b247c7a8215f106f1cc88d0f2f4bcf83ffffbef00c724ec94f1c9bee5f52a73","last_reissued_at":"2026-08-07T01:41:19.968481Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T01:41:19.968481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.06305","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":"2026-08-07T01:41:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FsnhSjaH/ZxQAJ7pSarkDf3db+NA4bAd0DPZipUDjfHsoM8NhokAGAK7HxTS1ByxKDRO/x4D0G7LltWc292OAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:21:40.647669Z"},"content_sha256":"0865bc2f4829c929c6ead7cc6829881e1cecc78ebdaafded5df07987eca1151c","schema_version":"1.0","event_id":"sha256:0865bc2f4829c929c6ead7cc6829881e1cecc78ebdaafded5df07987eca1151c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JMSHY6UCCXYQN4OMRDIPF5F47A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Ayush Vyas, Sagar Tamang, Tabarakul Hazarika","submitted_at":"2026-08-06T17:23:13Z","abstract_excerpt":"Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important class of documents -- financial statements, audit reports, regulatory returns -- this design is structurally unsound, and we make the argument measurable. On a 780-page government financial report, 86.8% of content lines are table rows, thousands of near-identical figures compete in one embedding space, and a figure inherits its unit from a header a median of 13 lines above it -- so a chunk boundar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06305","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/2608.06305/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":"2026-08-07T01:41:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cZPZxIrPK50G41fzerYDYhJEZjggoLNQHGn/vg6x43Ev97OMH/ohlF474GpoELFyjSL0pQMB+O0m09FvT3LuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:21:40.648167Z"},"content_sha256":"2f3b8ed9fa51a95dee5da6e74ecbd80dcb1848596f963e4d6594d2df244ac1ff","schema_version":"1.0","event_id":"sha256:2f3b8ed9fa51a95dee5da6e74ecbd80dcb1848596f963e4d6594d2df244ac1ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A/bundle.json","state_url":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMSHY6UCCXYQN4OMRDIPF5F47A/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":"2026-08-09T00:21:40Z","links":{"resolver":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A","bundle":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A/bundle.json","state":"https://pith.science/pith/JMSHY6UCCXYQN4OMRDIPF5F47A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMSHY6UCCXYQN4OMRDIPF5F47A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JMSHY6UCCXYQN4OMRDIPF5F47A","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":"c75f012c9e7484d5df46c6d6a560deedb80d3a875619a6d03267a1fa97a32ecb","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T17:23:13Z","title_canon_sha256":"cbb56330904cc1c244636fd8c9949464a14b5ff73e41a601abb07c752802b146"},"schema_version":"1.0","source":{"id":"2608.06305","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06305","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06305v1","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06305","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"pith_short_12","alias_value":"JMSHY6UCCXYQ","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"pith_short_16","alias_value":"JMSHY6UCCXYQN4OM","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"pith_short_8","alias_value":"JMSHY6UC","created_at":"2026-08-07T01:41:19Z"}],"graph_snapshots":[{"event_id":"sha256:2f3b8ed9fa51a95dee5da6e74ecbd80dcb1848596f963e4d6594d2df244ac1ff","target":"graph","created_at":"2026-08-07T01:41:19Z","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/2608.06305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important class of documents -- financial statements, audit reports, regulatory returns -- this design is structurally unsound, and we make the argument measurable. On a 780-page government financial report, 86.8% of content lines are table rows, thousands of near-identical figures compete in one embedding space, and a figure inherits its unit from a header a median of 13 lines above it -- so a chunk boundar","authors_text":"Ayush Vyas, Sagar Tamang, Tabarakul Hazarika","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T17:23:13Z","title":"Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06305","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":"sha256:0865bc2f4829c929c6ead7cc6829881e1cecc78ebdaafded5df07987eca1151c","target":"record","created_at":"2026-08-07T01:41:19Z","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":"c75f012c9e7484d5df46c6d6a560deedb80d3a875619a6d03267a1fa97a32ecb","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T17:23:13Z","title_canon_sha256":"cbb56330904cc1c244636fd8c9949464a14b5ff73e41a601abb07c752802b146"},"schema_version":"1.0","source":{"id":"2608.06305","kind":"arxiv","version":1}},"canonical_sha256":"4b247c7a8215f106f1cc88d0f2f4bcf83ffffbef00c724ec94f1c9bee5f52a73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b247c7a8215f106f1cc88d0f2f4bcf83ffffbef00c724ec94f1c9bee5f52a73","first_computed_at":"2026-08-07T01:41:19.968481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T01:41:19.968481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kLZf9EAlI4Yxt81k30QNo42LaLeo/YFSAu0o6ArkshUPpGRpd0mwQAcnjxnA8CPABNiPL6wS6gFTkEMHd2FLCg==","signature_status":"signed_v1","signed_at":"2026-08-07T01:41:19.969898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06305","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0865bc2f4829c929c6ead7cc6829881e1cecc78ebdaafded5df07987eca1151c","sha256:2f3b8ed9fa51a95dee5da6e74ecbd80dcb1848596f963e4d6594d2df244ac1ff"],"state_sha256":"4150d681daa66d0e5fc3d07cedbc3d5d9bb7baf34128fe29817f8544c9e7d486"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cdUTcCGyOMSMccKRjhOA7W+WBL5vZlU2gEgXMB7ufNXrkLZVR+HHrZT0JRJaabeADCug3bBJw3lGSOCx2KToAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:21:40.652989Z","bundle_sha256":"4854fbb4560b95d869473a99c34ece7296ddf3e4bfd48d13f724e3efc0b4c494"}}