{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NKNEIJNF2G7SH3GMMUNNHPPMWJ","short_pith_number":"pith:NKNEIJNF","canonical_record":{"source":{"id":"2104.12763","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-26T17:55:33Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"f445f75a4cd57b4390d7c15d4bb2b56ac2e4fb0ab7d389282df22d77b9327d51","abstract_canon_sha256":"239294aac396706f7b92aa0254f7a95955db7ff54a128dbd894537cda1f2ff24"},"schema_version":"1.0"},"canonical_sha256":"6a9a4425a5d1bf23eccc651ad3bdecb253eac2bd09436cf1fec682775b2d56a9","source":{"kind":"arxiv","id":"2104.12763","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.12763","created_at":"2026-07-05T03:21:47Z"},{"alias_kind":"arxiv_version","alias_value":"2104.12763v2","created_at":"2026-07-05T03:21:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.12763","created_at":"2026-07-05T03:21:47Z"},{"alias_kind":"pith_short_12","alias_value":"NKNEIJNF2G7S","created_at":"2026-07-05T03:21:47Z"},{"alias_kind":"pith_short_16","alias_value":"NKNEIJNF2G7SH3GM","created_at":"2026-07-05T03:21:47Z"},{"alias_kind":"pith_short_8","alias_value":"NKNEIJNF","created_at":"2026-07-05T03:21:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NKNEIJNF2G7SH3GMMUNNHPPMWJ","target":"record","payload":{"canonical_record":{"source":{"id":"2104.12763","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-26T17:55:33Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"f445f75a4cd57b4390d7c15d4bb2b56ac2e4fb0ab7d389282df22d77b9327d51","abstract_canon_sha256":"239294aac396706f7b92aa0254f7a95955db7ff54a128dbd894537cda1f2ff24"},"schema_version":"1.0"},"canonical_sha256":"6a9a4425a5d1bf23eccc651ad3bdecb253eac2bd09436cf1fec682775b2d56a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:47.541912Z","signature_b64":"W0Yf49TSGJFy0fvr6QYH0yHvOYKOTOoDHQLPrT1SUdih/fyzePnACFoJ0QnOTassdi0NjDtDCHkXbCpCNXEqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a9a4425a5d1bf23eccc651ad3bdecb253eac2bd09436cf1fec682775b2d56a9","last_reissued_at":"2026-07-05T03:21:47.541412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:47.541412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.12763","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":"2026-07-05T03:21:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9gjsCm83h4aPFb+IclMDH4V49Vr4QWdJ4RVBlPXC6Q8dg24YE+kMQitG5YFZeCr6wCcwkH/r89u/234yxAR1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:27:37.783584Z"},"content_sha256":"6e868504185609005a0f9b19fbbd4e39ffa30c9a7274b0276914837dca8467b1","schema_version":"1.0","event_id":"sha256:6e868504185609005a0f9b19fbbd4e39ffa30c9a7274b0276914837dca8467b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NKNEIJNF2G7SH3GMMUNNHPPMWJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aishwarya Kamath, Gabriel Synnaeve, Ishan Misra, Mannat Singh, Nicolas Carion, Yann LeCun","submitted_at":"2021-04-26T17:55:33Z","abstract_excerpt":"Multi-modal reasoning systems rely on a pre-trained object detector to extract regions of interest from the image. However, this crucial module is typically used as a black box, trained independently of the downstream task and on a fixed vocabulary of objects and attributes. This makes it challenging for such systems to capture the long tail of visual concepts expressed in free form text. In this paper we propose MDETR, an end-to-end modulated detector that detects objects in an image conditioned on a raw text query, like a caption or a question. We use a transformer-based architecture to reas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.12763","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/2104.12763/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":"2026-07-05T03:21:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mmkw3xSdUdpVXzo4tloNDGDQlMCkYZdKqJ9KvwStvbXGtvMDbZqWukuVXEP7VUk5twjGXS8Ud6cVluAf4/PWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:27:37.784132Z"},"content_sha256":"d237fa650fa8c7923f61c613889d639a20a988d9434cd8a1e7facd9a8bf8eb4b","schema_version":"1.0","event_id":"sha256:d237fa650fa8c7923f61c613889d639a20a988d9434cd8a1e7facd9a8bf8eb4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NKNEIJNF2G7SH3GMMUNNHPPMWJ/bundle.json","state_url":"https://pith.science/pith/NKNEIJNF2G7SH3GMMUNNHPPMWJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NKNEIJNF2G7SH3GMMUNNHPPMWJ/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":"2026-08-07T21:27:37Z","links":{"resolver":"https://pith.science/pith/NKNEIJNF2G7SH3GMMUNNHPPMWJ","bundle":"https://pith.science/pith/NKNEIJNF2G7SH3GMMUNNHPPMWJ/bundle.json","state":"https://pith.science/pith/NKNEIJNF2G7SH3GMMUNNHPPMWJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NKNEIJNF2G7SH3GMMUNNHPPMWJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NKNEIJNF2G7SH3GMMUNNHPPMWJ","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":"239294aac396706f7b92aa0254f7a95955db7ff54a128dbd894537cda1f2ff24","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-26T17:55:33Z","title_canon_sha256":"f445f75a4cd57b4390d7c15d4bb2b56ac2e4fb0ab7d389282df22d77b9327d51"},"schema_version":"1.0","source":{"id":"2104.12763","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.12763","created_at":"2026-07-05T03:21:47Z"},{"alias_kind":"arxiv_version","alias_value":"2104.12763v2","created_at":"2026-07-05T03:21:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.12763","created_at":"2026-07-05T03:21:47Z"},{"alias_kind":"pith_short_12","alias_value":"NKNEIJNF2G7S","created_at":"2026-07-05T03:21:47Z"},{"alias_kind":"pith_short_16","alias_value":"NKNEIJNF2G7SH3GM","created_at":"2026-07-05T03:21:47Z"},{"alias_kind":"pith_short_8","alias_value":"NKNEIJNF","created_at":"2026-07-05T03:21:47Z"}],"graph_snapshots":[{"event_id":"sha256:d237fa650fa8c7923f61c613889d639a20a988d9434cd8a1e7facd9a8bf8eb4b","target":"graph","created_at":"2026-07-05T03:21:47Z","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/2104.12763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal reasoning systems rely on a pre-trained object detector to extract regions of interest from the image. However, this crucial module is typically used as a black box, trained independently of the downstream task and on a fixed vocabulary of objects and attributes. This makes it challenging for such systems to capture the long tail of visual concepts expressed in free form text. In this paper we propose MDETR, an end-to-end modulated detector that detects objects in an image conditioned on a raw text query, like a caption or a question. We use a transformer-based architecture to reas","authors_text":"Aishwarya Kamath, Gabriel Synnaeve, Ishan Misra, Mannat Singh, Nicolas Carion, Yann LeCun","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-26T17:55:33Z","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.12763","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":"sha256:6e868504185609005a0f9b19fbbd4e39ffa30c9a7274b0276914837dca8467b1","target":"record","created_at":"2026-07-05T03:21:47Z","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":"239294aac396706f7b92aa0254f7a95955db7ff54a128dbd894537cda1f2ff24","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-26T17:55:33Z","title_canon_sha256":"f445f75a4cd57b4390d7c15d4bb2b56ac2e4fb0ab7d389282df22d77b9327d51"},"schema_version":"1.0","source":{"id":"2104.12763","kind":"arxiv","version":2}},"canonical_sha256":"6a9a4425a5d1bf23eccc651ad3bdecb253eac2bd09436cf1fec682775b2d56a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a9a4425a5d1bf23eccc651ad3bdecb253eac2bd09436cf1fec682775b2d56a9","first_computed_at":"2026-07-05T03:21:47.541412Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:47.541412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W0Yf49TSGJFy0fvr6QYH0yHvOYKOTOoDHQLPrT1SUdih/fyzePnACFoJ0QnOTassdi0NjDtDCHkXbCpCNXEqAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:47.541912Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.12763","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e868504185609005a0f9b19fbbd4e39ffa30c9a7274b0276914837dca8467b1","sha256:d237fa650fa8c7923f61c613889d639a20a988d9434cd8a1e7facd9a8bf8eb4b"],"state_sha256":"0b74d051c701ee459000a8668e3b3ef886fa6401c8fa6ac84f85e98d52ac2e57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uNiesPVoCRd9aMlvyK1SGejp4brNBxiPPNsKA0tSU+9JHeU3amNkLoW3C2SOpiBsgUQqkc4+vn2h+CT7/brIDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:27:37.788526Z","bundle_sha256":"899125e77467e41264fc8d4e760fe532128ceb06f0bd0b61e8d6ac1196e9608d"}}