{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5QW57EG2YQCUQJ6SZCXENLTSCM","short_pith_number":"pith:5QW57EG2","canonical_record":{"source":{"id":"2503.20853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T17:59:51Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"4f165c1d6627727c68dd7ba23e5fa51154f37a6efb40b2b931ec204f634f57be","abstract_canon_sha256":"5162a78075c5f91a20df196412351d804824e6e2bbfc7e3bbd3a2b83dae73b6b"},"schema_version":"1.0"},"canonical_sha256":"ec2ddf90dac4054827d2c8ae46ae72133c9f09e60905640866368726538c6664","source":{"kind":"arxiv","id":"2503.20853","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.20853","created_at":"2026-07-05T10:39:49Z"},{"alias_kind":"arxiv_version","alias_value":"2503.20853v1","created_at":"2026-07-05T10:39:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20853","created_at":"2026-07-05T10:39:49Z"},{"alias_kind":"pith_short_12","alias_value":"5QW57EG2YQCU","created_at":"2026-07-05T10:39:49Z"},{"alias_kind":"pith_short_16","alias_value":"5QW57EG2YQCUQJ6S","created_at":"2026-07-05T10:39:49Z"},{"alias_kind":"pith_short_8","alias_value":"5QW57EG2","created_at":"2026-07-05T10:39:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5QW57EG2YQCUQJ6SZCXENLTSCM","target":"record","payload":{"canonical_record":{"source":{"id":"2503.20853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T17:59:51Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"4f165c1d6627727c68dd7ba23e5fa51154f37a6efb40b2b931ec204f634f57be","abstract_canon_sha256":"5162a78075c5f91a20df196412351d804824e6e2bbfc7e3bbd3a2b83dae73b6b"},"schema_version":"1.0"},"canonical_sha256":"ec2ddf90dac4054827d2c8ae46ae72133c9f09e60905640866368726538c6664","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:49.202864Z","signature_b64":"0VdDvnpYvuRZu6gXHabKTzaOMuQAk8J9kncvRZQTh0IRiJ3wrPuDXyDBASSqcDimmSotwaCjNoqSFp169Y/vBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec2ddf90dac4054827d2c8ae46ae72133c9f09e60905640866368726538c6664","last_reissued_at":"2026-07-05T10:39:49.202394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:49.202394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.20853","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":"2026-07-05T10:39:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GmYm2s2z+ZVxIBju24gmKG7Ln8Yku/HMulQkwIe7NovJr+liSjbJiksipQcdxP6L3xqmmHu0z/udc9rwhyWvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:46:12.863715Z"},"content_sha256":"846f53230cc66a212faff2f25bf2d8879e1e5e8d88dad65e2653c697bfc9f586","schema_version":"1.0","event_id":"sha256:846f53230cc66a212faff2f25bf2d8879e1e5e8d88dad65e2653c697bfc9f586"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5QW57EG2YQCUQJ6SZCXENLTSCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Multimodal Discrete Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexander Swerdlow, Deepak Pathak, Katerina Fragkiadaki, Mihir Prabhudesai, Siddharth Gandhi","submitted_at":"2025-03-26T17:59:51Z","abstract_excerpt":"Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches, which process tokens sequentially from left to right, or top to bottom. These models jointly handle images, text, video, and audio for various tasks such as image captioning, question answering, and image generation. In this work, we explore discrete diffusion models as a unified generative formulation in the joint text and image domain, building upon their recent success in text generation. Discrete diffusion models offer several advantages over AR models, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20853","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/2503.20853/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":"2026-07-05T10:39:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UZBgc9K50huLiXgvDctH5mNsZhgFyTfEGB9kFxpWPp8qqezB3xlDH5YpUdd6I1RPazHo6LdmOcrsedY3x2TUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:46:12.864489Z"},"content_sha256":"9344224bce3c0c7f6569d0f22b84f76cd659a9a5ca8ce6ee8eeba58a787758ec","schema_version":"1.0","event_id":"sha256:9344224bce3c0c7f6569d0f22b84f76cd659a9a5ca8ce6ee8eeba58a787758ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5QW57EG2YQCUQJ6SZCXENLTSCM/bundle.json","state_url":"https://pith.science/pith/5QW57EG2YQCUQJ6SZCXENLTSCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5QW57EG2YQCUQJ6SZCXENLTSCM/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":"2026-08-07T04:46:12Z","links":{"resolver":"https://pith.science/pith/5QW57EG2YQCUQJ6SZCXENLTSCM","bundle":"https://pith.science/pith/5QW57EG2YQCUQJ6SZCXENLTSCM/bundle.json","state":"https://pith.science/pith/5QW57EG2YQCUQJ6SZCXENLTSCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5QW57EG2YQCUQJ6SZCXENLTSCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5QW57EG2YQCUQJ6SZCXENLTSCM","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":"5162a78075c5f91a20df196412351d804824e6e2bbfc7e3bbd3a2b83dae73b6b","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T17:59:51Z","title_canon_sha256":"4f165c1d6627727c68dd7ba23e5fa51154f37a6efb40b2b931ec204f634f57be"},"schema_version":"1.0","source":{"id":"2503.20853","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.20853","created_at":"2026-07-05T10:39:49Z"},{"alias_kind":"arxiv_version","alias_value":"2503.20853v1","created_at":"2026-07-05T10:39:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20853","created_at":"2026-07-05T10:39:49Z"},{"alias_kind":"pith_short_12","alias_value":"5QW57EG2YQCU","created_at":"2026-07-05T10:39:49Z"},{"alias_kind":"pith_short_16","alias_value":"5QW57EG2YQCUQJ6S","created_at":"2026-07-05T10:39:49Z"},{"alias_kind":"pith_short_8","alias_value":"5QW57EG2","created_at":"2026-07-05T10:39:49Z"}],"graph_snapshots":[{"event_id":"sha256:9344224bce3c0c7f6569d0f22b84f76cd659a9a5ca8ce6ee8eeba58a787758ec","target":"graph","created_at":"2026-07-05T10:39:49Z","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/2503.20853/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches, which process tokens sequentially from left to right, or top to bottom. These models jointly handle images, text, video, and audio for various tasks such as image captioning, question answering, and image generation. In this work, we explore discrete diffusion models as a unified generative formulation in the joint text and image domain, building upon their recent success in text generation. Discrete diffusion models offer several advantages over AR models, ","authors_text":"Alexander Swerdlow, Deepak Pathak, Katerina Fragkiadaki, Mihir Prabhudesai, Siddharth Gandhi","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T17:59:51Z","title":"Unified Multimodal Discrete Diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20853","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":"sha256:846f53230cc66a212faff2f25bf2d8879e1e5e8d88dad65e2653c697bfc9f586","target":"record","created_at":"2026-07-05T10:39:49Z","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":"5162a78075c5f91a20df196412351d804824e6e2bbfc7e3bbd3a2b83dae73b6b","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T17:59:51Z","title_canon_sha256":"4f165c1d6627727c68dd7ba23e5fa51154f37a6efb40b2b931ec204f634f57be"},"schema_version":"1.0","source":{"id":"2503.20853","kind":"arxiv","version":1}},"canonical_sha256":"ec2ddf90dac4054827d2c8ae46ae72133c9f09e60905640866368726538c6664","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec2ddf90dac4054827d2c8ae46ae72133c9f09e60905640866368726538c6664","first_computed_at":"2026-07-05T10:39:49.202394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:49.202394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0VdDvnpYvuRZu6gXHabKTzaOMuQAk8J9kncvRZQTh0IRiJ3wrPuDXyDBASSqcDimmSotwaCjNoqSFp169Y/vBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:49.202864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.20853","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:846f53230cc66a212faff2f25bf2d8879e1e5e8d88dad65e2653c697bfc9f586","sha256:9344224bce3c0c7f6569d0f22b84f76cd659a9a5ca8ce6ee8eeba58a787758ec"],"state_sha256":"643041f589b2ac051c3b1112c77ed5437e6e8fc805e8b04a92d4980c2027272d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QbMwRBFLcxqRmIDr31KCSryI5n5G1xj6f17sc8KvL24ZmjkDotcbZ5UWvpIXaU3kBbQQRX9ma6REH9wfrN58Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:46:12.870726Z","bundle_sha256":"6af02c6988613b8435622a76ab53a775b9c6d3506cddec0aace7b36aca56155b"}}