{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DJEFPVP22W6ILWI5QTLY6NJYSW","short_pith_number":"pith:DJEFPVP2","canonical_record":{"source":{"id":"2506.01015","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T13:57:42Z","cross_cats_sorted":[],"title_canon_sha256":"3151298b311700ac8a429be5122fe5a4265c4574348f4e621972a21af027ec20","abstract_canon_sha256":"12a42ed259c8931623181647fe1c20491ffa8ed45985b3861d794e5d7d04c5aa"},"schema_version":"1.0"},"canonical_sha256":"1a4857d5fad5bc85d91d84d78f3538959891217b006f675ee1409f44a41e93eb","source":{"kind":"arxiv","id":"2506.01015","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01015","created_at":"2026-05-17T23:39:01Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01015v2","created_at":"2026-05-17T23:39:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01015","created_at":"2026-05-17T23:39:01Z"},{"alias_kind":"pith_short_12","alias_value":"DJEFPVP22W6I","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DJEFPVP22W6ILWI5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DJEFPVP2","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DJEFPVP22W6ILWI5QTLY6NJYSW","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01015","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T13:57:42Z","cross_cats_sorted":[],"title_canon_sha256":"3151298b311700ac8a429be5122fe5a4265c4574348f4e621972a21af027ec20","abstract_canon_sha256":"12a42ed259c8931623181647fe1c20491ffa8ed45985b3861d794e5d7d04c5aa"},"schema_version":"1.0"},"canonical_sha256":"1a4857d5fad5bc85d91d84d78f3538959891217b006f675ee1409f44a41e93eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:01.304735Z","signature_b64":"+W578p+eIi9Giinw7igsyOuSAAHmOd+2WXlkuyraSclTJ71pG2tEEtHW/wnUkAYugjOVHrN28SXnIf8ejf9EDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a4857d5fad5bc85d91d84d78f3538959891217b006f675ee1409f44a41e93eb","last_reissued_at":"2026-05-17T23:39:01.304097Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:01.304097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01015","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":"2026-05-17T23:39:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mWUwL0YCeA109QQvH7YALS8//cIB6KiPhNTo1IhZnTbfM9HsrexngTxvjxGyfkecqVUXiLnYkVF8W6frqSkJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T23:16:00.040587Z"},"content_sha256":"78311c9826489170c80dfe3469c35eecc01f35e59fcb091dea9707598ed5fad8","schema_version":"1.0","event_id":"sha256:78311c9826489170c80dfe3469c35eecc01f35e59fcb091dea9707598ed5fad8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DJEFPVP22W6ILWI5QTLY6NJYSW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Peng, Chong Wang, Gustavo Carneiro, Jingkun Chen, Junde Wu, Junlin Han, Yuanhong Chen, Yu Tian, Yuyuan Liu","submitted_at":"2025-06-01T13:57:42Z","abstract_excerpt":"Segment Anything Model 2 (SAM2) exhibits strong generalisation for promptable segmentation in video clips; however, its integration with the audio modality remains underexplored. Existing approaches either convert audio into visual prompts (e.g., boxes) via foundation models, or inject adapters into the image encoder for audio-visual fusion. Yet both directions fall short in human-in-the-loop scenarios due to limited prompt accuracy and increased inference overhead. In particular, these adapter-based methods often suffer from audio prompt dilution, where the signal gradually weakens as it prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01015","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":""},"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":"2026-05-17T23:39:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ErDp0VGjC0aqChOP2jsx/C8Zvgv98sQ2L1sL3/WD4XQ2XV9yhZukkHCtJC0cJeHmwvTj5ZuKAHXtPyJH6s8iAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T23:16:00.041375Z"},"content_sha256":"bc908348beda933de67b9825516af9715bb92f9dfc2f71beb6a60f35b76ea3d5","schema_version":"1.0","event_id":"sha256:bc908348beda933de67b9825516af9715bb92f9dfc2f71beb6a60f35b76ea3d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW/bundle.json","state_url":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DJEFPVP22W6ILWI5QTLY6NJYSW/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":"2026-05-21T23:16:00Z","links":{"resolver":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW","bundle":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW/bundle.json","state":"https://pith.science/pith/DJEFPVP22W6ILWI5QTLY6NJYSW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DJEFPVP22W6ILWI5QTLY6NJYSW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DJEFPVP22W6ILWI5QTLY6NJYSW","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":"12a42ed259c8931623181647fe1c20491ffa8ed45985b3861d794e5d7d04c5aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T13:57:42Z","title_canon_sha256":"3151298b311700ac8a429be5122fe5a4265c4574348f4e621972a21af027ec20"},"schema_version":"1.0","source":{"id":"2506.01015","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01015","created_at":"2026-05-17T23:39:01Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01015v2","created_at":"2026-05-17T23:39:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01015","created_at":"2026-05-17T23:39:01Z"},{"alias_kind":"pith_short_12","alias_value":"DJEFPVP22W6I","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DJEFPVP22W6ILWI5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DJEFPVP2","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:bc908348beda933de67b9825516af9715bb92f9dfc2f71beb6a60f35b76ea3d5","target":"graph","created_at":"2026-05-17T23:39:01Z","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"},"paper":{"abstract_excerpt":"Segment Anything Model 2 (SAM2) exhibits strong generalisation for promptable segmentation in video clips; however, its integration with the audio modality remains underexplored. Existing approaches either convert audio into visual prompts (e.g., boxes) via foundation models, or inject adapters into the image encoder for audio-visual fusion. Yet both directions fall short in human-in-the-loop scenarios due to limited prompt accuracy and increased inference overhead. In particular, these adapter-based methods often suffer from audio prompt dilution, where the signal gradually weakens as it prop","authors_text":"Can Peng, Chong Wang, Gustavo Carneiro, Jingkun Chen, Junde Wu, Junlin Han, Yuanhong Chen, Yu Tian, Yuyuan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T13:57:42Z","title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01015","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":"sha256:78311c9826489170c80dfe3469c35eecc01f35e59fcb091dea9707598ed5fad8","target":"record","created_at":"2026-05-17T23:39:01Z","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":"12a42ed259c8931623181647fe1c20491ffa8ed45985b3861d794e5d7d04c5aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T13:57:42Z","title_canon_sha256":"3151298b311700ac8a429be5122fe5a4265c4574348f4e621972a21af027ec20"},"schema_version":"1.0","source":{"id":"2506.01015","kind":"arxiv","version":2}},"canonical_sha256":"1a4857d5fad5bc85d91d84d78f3538959891217b006f675ee1409f44a41e93eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a4857d5fad5bc85d91d84d78f3538959891217b006f675ee1409f44a41e93eb","first_computed_at":"2026-05-17T23:39:01.304097Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:01.304097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+W578p+eIi9Giinw7igsyOuSAAHmOd+2WXlkuyraSclTJ71pG2tEEtHW/wnUkAYugjOVHrN28SXnIf8ejf9EDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:01.304735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01015","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78311c9826489170c80dfe3469c35eecc01f35e59fcb091dea9707598ed5fad8","sha256:bc908348beda933de67b9825516af9715bb92f9dfc2f71beb6a60f35b76ea3d5"],"state_sha256":"8abaeb17eed51cc82c22f338f1f374ef5a1225efda8e3f992568620a39e1e5ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I7fCNRYSvUmSFkfai8KPWyzrWqh9fAhfzoqBHyKa+UHpY2xeUPmSixdtIE1TVYJiyRXygVzWE57e60+zTqFkAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T23:16:00.044580Z","bundle_sha256":"27ce2cd0597a20099b42026ac8a4e637e91789232da351d358c6e1f5f2b943e0"}}