{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BU55T2XDY35BSQTUHDONOXH3V4","short_pith_number":"pith:BU55T2XD","canonical_record":{"source":{"id":"2505.24782","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-30T16:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"9ddd714f19370be6b274565d66d5fa629bcdf090c149736ab67b27f18fd8527c","abstract_canon_sha256":"ae4c98f4d47b5d59972e7145d4f9cd084642e210835f1a37a368a1c6d30a8bed"},"schema_version":"1.0"},"canonical_sha256":"0d3bd9eae3c6fa19427438dcd75cfbaf33ecb6bab33171c7cc63b0ec95ec5cb8","source":{"kind":"arxiv","id":"2505.24782","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24782","created_at":"2026-07-05T11:17:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24782v2","created_at":"2026-07-05T11:17:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24782","created_at":"2026-07-05T11:17:24Z"},{"alias_kind":"pith_short_12","alias_value":"BU55T2XDY35B","created_at":"2026-07-05T11:17:24Z"},{"alias_kind":"pith_short_16","alias_value":"BU55T2XDY35BSQTU","created_at":"2026-07-05T11:17:24Z"},{"alias_kind":"pith_short_8","alias_value":"BU55T2XD","created_at":"2026-07-05T11:17:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BU55T2XDY35BSQTUHDONOXH3V4","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24782","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-30T16:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"9ddd714f19370be6b274565d66d5fa629bcdf090c149736ab67b27f18fd8527c","abstract_canon_sha256":"ae4c98f4d47b5d59972e7145d4f9cd084642e210835f1a37a368a1c6d30a8bed"},"schema_version":"1.0"},"canonical_sha256":"0d3bd9eae3c6fa19427438dcd75cfbaf33ecb6bab33171c7cc63b0ec95ec5cb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:24.453500Z","signature_b64":"v0VXlIyVKtHt4kOHBrSrwPHElXufagvUqHUoMpQcwSBcHr+F4+oidvFEtJj69s4BpYDaWN8YA3kO9WQ9NXO3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d3bd9eae3c6fa19427438dcd75cfbaf33ecb6bab33171c7cc63b0ec95ec5cb8","last_reissued_at":"2026-07-05T11:17:24.453017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:24.453017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24782","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":"2026-07-05T11:17:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FJ78dBO7yQslI5EhuIQt61unEZ29iUK0vWZmYDyMwrX3waGwpwhExpKxZXT1oGdAMvY/J4q5N8ZOqqaOol+qCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:25:46.726479Z"},"content_sha256":"2f78a2a8dd0b616c1a1697394f185d8a1912f92191a5e68113504ef3305b6091","schema_version":"1.0","event_id":"sha256:2f78a2a8dd0b616c1a1697394f185d8a1912f92191a5e68113504ef3305b6091"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BU55T2XDY35BSQTUHDONOXH3V4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Antoine Bosselut, C\\'eline Hudelot, Gautier Viaud, Manuel Faysse, Max Conti, Pierre Colombo","submitted_at":"2025-05-30T16:43:28Z","abstract_excerpt":"A limitation of modern document retrieval embedding methods is that they typically encode passages (chunks) from the same documents independently, often overlooking crucial contextual information from the rest of the document that could greatly improve individual chunk representations.\n  In this work, we introduce ConTEB (Context-aware Text Embedding Benchmark), a benchmark designed to evaluate retrieval models on their ability to leverage document-wide context. Our results show that state-of-the-art embedding models struggle in retrieval scenarios where context is required. To address this li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24782","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/2505.24782/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":"2026-07-05T11:17:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D7n0gH0OHRd7/TByYZdQm+S1j1B2eY+XED43bL3ja0bu0aIV4ai0JJGckvDPspb/Vl/iS6VJ72T9QqUAhwPlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:25:46.726984Z"},"content_sha256":"7b77816054ddf618beb9b825468e6eba8ed267acbc3abd6f2864cb6b8c5ccadb","schema_version":"1.0","event_id":"sha256:7b77816054ddf618beb9b825468e6eba8ed267acbc3abd6f2864cb6b8c5ccadb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BU55T2XDY35BSQTUHDONOXH3V4/bundle.json","state_url":"https://pith.science/pith/BU55T2XDY35BSQTUHDONOXH3V4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BU55T2XDY35BSQTUHDONOXH3V4/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":"2026-08-08T22:25:46Z","links":{"resolver":"https://pith.science/pith/BU55T2XDY35BSQTUHDONOXH3V4","bundle":"https://pith.science/pith/BU55T2XDY35BSQTUHDONOXH3V4/bundle.json","state":"https://pith.science/pith/BU55T2XDY35BSQTUHDONOXH3V4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BU55T2XDY35BSQTUHDONOXH3V4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BU55T2XDY35BSQTUHDONOXH3V4","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":"ae4c98f4d47b5d59972e7145d4f9cd084642e210835f1a37a368a1c6d30a8bed","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-30T16:43:28Z","title_canon_sha256":"9ddd714f19370be6b274565d66d5fa629bcdf090c149736ab67b27f18fd8527c"},"schema_version":"1.0","source":{"id":"2505.24782","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24782","created_at":"2026-07-05T11:17:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24782v2","created_at":"2026-07-05T11:17:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24782","created_at":"2026-07-05T11:17:24Z"},{"alias_kind":"pith_short_12","alias_value":"BU55T2XDY35B","created_at":"2026-07-05T11:17:24Z"},{"alias_kind":"pith_short_16","alias_value":"BU55T2XDY35BSQTU","created_at":"2026-07-05T11:17:24Z"},{"alias_kind":"pith_short_8","alias_value":"BU55T2XD","created_at":"2026-07-05T11:17:24Z"}],"graph_snapshots":[{"event_id":"sha256:7b77816054ddf618beb9b825468e6eba8ed267acbc3abd6f2864cb6b8c5ccadb","target":"graph","created_at":"2026-07-05T11:17:24Z","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/2505.24782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A limitation of modern document retrieval embedding methods is that they typically encode passages (chunks) from the same documents independently, often overlooking crucial contextual information from the rest of the document that could greatly improve individual chunk representations.\n  In this work, we introduce ConTEB (Context-aware Text Embedding Benchmark), a benchmark designed to evaluate retrieval models on their ability to leverage document-wide context. Our results show that state-of-the-art embedding models struggle in retrieval scenarios where context is required. To address this li","authors_text":"Antoine Bosselut, C\\'eline Hudelot, Gautier Viaud, Manuel Faysse, Max Conti, Pierre Colombo","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-30T16:43:28Z","title":"Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24782","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":"sha256:2f78a2a8dd0b616c1a1697394f185d8a1912f92191a5e68113504ef3305b6091","target":"record","created_at":"2026-07-05T11:17:24Z","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":"ae4c98f4d47b5d59972e7145d4f9cd084642e210835f1a37a368a1c6d30a8bed","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-30T16:43:28Z","title_canon_sha256":"9ddd714f19370be6b274565d66d5fa629bcdf090c149736ab67b27f18fd8527c"},"schema_version":"1.0","source":{"id":"2505.24782","kind":"arxiv","version":2}},"canonical_sha256":"0d3bd9eae3c6fa19427438dcd75cfbaf33ecb6bab33171c7cc63b0ec95ec5cb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d3bd9eae3c6fa19427438dcd75cfbaf33ecb6bab33171c7cc63b0ec95ec5cb8","first_computed_at":"2026-07-05T11:17:24.453017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:24.453017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v0VXlIyVKtHt4kOHBrSrwPHElXufagvUqHUoMpQcwSBcHr+F4+oidvFEtJj69s4BpYDaWN8YA3kO9WQ9NXO3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:24.453500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24782","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f78a2a8dd0b616c1a1697394f185d8a1912f92191a5e68113504ef3305b6091","sha256:7b77816054ddf618beb9b825468e6eba8ed267acbc3abd6f2864cb6b8c5ccadb"],"state_sha256":"ae64089033dd5be981c558fa18d1f4fdb3fc31677f5bac60a7398ed1f7c9ff10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mmz9+wsczD2WVnuwtH507NMFEPLs+AffqLxfTRucKecys9LUYD+2vo9ohL4BlEvlGq4OeDw5WBtlXBkZeMvqAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:25:46.730812Z","bundle_sha256":"c51b82b5fd026332524349a708fb0d794a6c5fefa93d4ff5c0f5d2ba2f84ee79"}}