{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UF5SOZFYBHUXS4NXIR2XDCJLP5","short_pith_number":"pith:UF5SOZFY","canonical_record":{"source":{"id":"2409.11059","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T10:38:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec23fbb02b0fe3fae699e26dae0c002b25d6eb8401a062c40da5c7830ac31602","abstract_canon_sha256":"caa09c13e6dae23431286ff86dda829ee0886c1630007facf3470b640e186bd5"},"schema_version":"1.0"},"canonical_sha256":"a17b2764b809e97971b7447571892b7f64a2150126a31073ad591740f09c10e3","source":{"kind":"arxiv","id":"2409.11059","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11059","created_at":"2026-07-05T09:08:30Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11059v2","created_at":"2026-07-05T09:08:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11059","created_at":"2026-07-05T09:08:30Z"},{"alias_kind":"pith_short_12","alias_value":"UF5SOZFYBHUX","created_at":"2026-07-05T09:08:30Z"},{"alias_kind":"pith_short_16","alias_value":"UF5SOZFYBHUXS4NX","created_at":"2026-07-05T09:08:30Z"},{"alias_kind":"pith_short_8","alias_value":"UF5SOZFY","created_at":"2026-07-05T09:08:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UF5SOZFYBHUXS4NXIR2XDCJLP5","target":"record","payload":{"canonical_record":{"source":{"id":"2409.11059","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T10:38:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec23fbb02b0fe3fae699e26dae0c002b25d6eb8401a062c40da5c7830ac31602","abstract_canon_sha256":"caa09c13e6dae23431286ff86dda829ee0886c1630007facf3470b640e186bd5"},"schema_version":"1.0"},"canonical_sha256":"a17b2764b809e97971b7447571892b7f64a2150126a31073ad591740f09c10e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:30.051051Z","signature_b64":"k4PSPsIzAt9oA0fEUHgWV8roh3xYfIl7eS/Hm8mc7v7jmi3FKCH3dJg09zloEpIzMHDyoepeWhhh1PX5WURPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a17b2764b809e97971b7447571892b7f64a2150126a31073ad591740f09c10e3","last_reissued_at":"2026-07-05T09:08:30.050627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:30.050627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.11059","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":"2026-07-05T09:08:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+OSouuNoZqCzT9XAcKy4uiJ/wOuEiR2Sy9KCkTrvTTHRB4kbfjL95t5C7DNoe9o7KsbJH78AhR4iqfpLYGlwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:57:11.578338Z"},"content_sha256":"bd90d1bbd7ddf5115fe7cfd74397781011ecf7f84da917a3cbf7522ca43993d3","schema_version":"1.0","event_id":"sha256:bd90d1bbd7ddf5115fe7cfd74397781011ecf7f84da917a3cbf7522ca43993d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UF5SOZFYBHUXS4NXIR2XDCJLP5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OneEncoder: A Lightweight Framework for Progressive Alignment of Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bilal Faye, Hanane Azzag, Mustapha Lebbah","submitted_at":"2024-09-17T10:38:46Z","abstract_excerpt":"Cross-modal alignment Learning integrates information from different modalities like text, image, audio and video to create unified models. This approach develops shared representations and learns correlations between modalities, enabling applications such as visual question answering and audiovisual content analysis. Current techniques rely on large modality-specific encoders, necessitating fine-tuning or training from scratch on vast aligned datasets (e.g., text-image, text-audio, image-audio). This approach has limitations: (i) it is very expensive due to the need for training large encoder"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11059","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/2409.11059/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":"2026-07-05T09:08:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UhVfrivyMeCGURHbF2wKtzC1pjmKUD5ngt4XO9iu3XhUaXtz33EOlcSJvto5YMZYyA4BbZqcaMXeAuisew02Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:57:11.578738Z"},"content_sha256":"1ddedbd4d214e2c3050c591b4fb84b6276bad463eedcc60a905dc622b942c74e","schema_version":"1.0","event_id":"sha256:1ddedbd4d214e2c3050c591b4fb84b6276bad463eedcc60a905dc622b942c74e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UF5SOZFYBHUXS4NXIR2XDCJLP5/bundle.json","state_url":"https://pith.science/pith/UF5SOZFYBHUXS4NXIR2XDCJLP5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UF5SOZFYBHUXS4NXIR2XDCJLP5/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":"2026-08-05T22:57:11Z","links":{"resolver":"https://pith.science/pith/UF5SOZFYBHUXS4NXIR2XDCJLP5","bundle":"https://pith.science/pith/UF5SOZFYBHUXS4NXIR2XDCJLP5/bundle.json","state":"https://pith.science/pith/UF5SOZFYBHUXS4NXIR2XDCJLP5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UF5SOZFYBHUXS4NXIR2XDCJLP5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UF5SOZFYBHUXS4NXIR2XDCJLP5","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":"caa09c13e6dae23431286ff86dda829ee0886c1630007facf3470b640e186bd5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T10:38:46Z","title_canon_sha256":"ec23fbb02b0fe3fae699e26dae0c002b25d6eb8401a062c40da5c7830ac31602"},"schema_version":"1.0","source":{"id":"2409.11059","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11059","created_at":"2026-07-05T09:08:30Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11059v2","created_at":"2026-07-05T09:08:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11059","created_at":"2026-07-05T09:08:30Z"},{"alias_kind":"pith_short_12","alias_value":"UF5SOZFYBHUX","created_at":"2026-07-05T09:08:30Z"},{"alias_kind":"pith_short_16","alias_value":"UF5SOZFYBHUXS4NX","created_at":"2026-07-05T09:08:30Z"},{"alias_kind":"pith_short_8","alias_value":"UF5SOZFY","created_at":"2026-07-05T09:08:30Z"}],"graph_snapshots":[{"event_id":"sha256:1ddedbd4d214e2c3050c591b4fb84b6276bad463eedcc60a905dc622b942c74e","target":"graph","created_at":"2026-07-05T09:08:30Z","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/2409.11059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-modal alignment Learning integrates information from different modalities like text, image, audio and video to create unified models. This approach develops shared representations and learns correlations between modalities, enabling applications such as visual question answering and audiovisual content analysis. Current techniques rely on large modality-specific encoders, necessitating fine-tuning or training from scratch on vast aligned datasets (e.g., text-image, text-audio, image-audio). This approach has limitations: (i) it is very expensive due to the need for training large encoder","authors_text":"Bilal Faye, Hanane Azzag, Mustapha Lebbah","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T10:38:46Z","title":"OneEncoder: A Lightweight Framework for Progressive Alignment of Modalities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11059","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:bd90d1bbd7ddf5115fe7cfd74397781011ecf7f84da917a3cbf7522ca43993d3","target":"record","created_at":"2026-07-05T09:08:30Z","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":"caa09c13e6dae23431286ff86dda829ee0886c1630007facf3470b640e186bd5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T10:38:46Z","title_canon_sha256":"ec23fbb02b0fe3fae699e26dae0c002b25d6eb8401a062c40da5c7830ac31602"},"schema_version":"1.0","source":{"id":"2409.11059","kind":"arxiv","version":2}},"canonical_sha256":"a17b2764b809e97971b7447571892b7f64a2150126a31073ad591740f09c10e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a17b2764b809e97971b7447571892b7f64a2150126a31073ad591740f09c10e3","first_computed_at":"2026-07-05T09:08:30.050627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:30.050627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k4PSPsIzAt9oA0fEUHgWV8roh3xYfIl7eS/Hm8mc7v7jmi3FKCH3dJg09zloEpIzMHDyoepeWhhh1PX5WURPAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:30.051051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11059","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd90d1bbd7ddf5115fe7cfd74397781011ecf7f84da917a3cbf7522ca43993d3","sha256:1ddedbd4d214e2c3050c591b4fb84b6276bad463eedcc60a905dc622b942c74e"],"state_sha256":"b6692584183810abd16391ccaa0d422b934fed25870206a8496daa34f68bd139"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zAOrCTrvoAqYm1zY/xrCkw4TAl/2r87AdRJxDJdRED51IcEPmc1nJ8PEaMUr0QTvnz8qY2DT/opNuvr54pGGBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:57:11.581613Z","bundle_sha256":"b963df465f8dc37f051206cfe7431d17fc82d29b8e978e764d305f54bead0ac3"}}